Publications [科学出版]

Profiles

Publication List

2015

  • [DOI] Thomas Weise and Raymond Chiong. An Alternative Way of Presenting Statistical Test Results when Evaluating the Performance of Stochastic Approaches. Neurocomputing, 147:235-238, January 5, 2015. Supersedes technical report Thomas Weise: “Illustration of Statistical Test Results for Experiment Evaluation“, 2011
    [Bibtex]
    @article{WC2014AAWOPSTRWETPOSA,
    author = {Thomas Weise and Raymond Chiong},
    title = {An Alternative Way of Presenting Statistical Test Results when Evaluating the Performance of Stochastic Approaches},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Neurocomputing},
    volume = {147},
    pages = {235--238},
    year = {2015},
    month = {January 5, },
    doi = {10.1016/j.neucom.2014.06.071},
    note = {Supersedes technical report Thomas Weise: ``Illustration of Statistical Test Results for Experiment Evaluation``, 2011},
    abstract = {Stochastic approaches such as evolutionary algorithms have been widely used in various science and engineering problems. When comparing the performance of a set of stochastic algorithms, it is necessary to statistically evaluate which algorithms are the most suitable for solving a given problem. The outcome of statistical tests comparing N {\ensuremath{\geq}} 2 processes, where N is the number of algorithms, is often presented in tables. This can become confusing for larger numbers of N. Such a scenario is, however, very common in both numerical and combinatorial optimization, as well as in the domain of stochastic algorithms in general. In this letter, we introduce an alternative way of visually presenting the results of statistical tests for multiple processes in a compact and easy-to-read manner using a directed acyclic graph (DAG), in the form of a simplified Hasse diagram. The rationale of doing so is based on the fact that the outcome of the tests is always at least a strict partial order, which can be appropriately presented via a DAG. The goal of this brief communication is to promote the use of this approach as a means for presenting the results of comparisons between different optimization methods.},
    sortkey = {0799995analternativewayof},
    }

2014

  • Yan Jiang, Thomas Weise, Jörg Lässig, Raymond Chiong, and Rukshan Athauda. Comparing a Hybrid Branch and Bound Algorithm with Evolutionary Computation Methods, Local Search and their Hybrids on the TSP. In Proceedings of the IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS’14), Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI’14), Orlando, FL, USA: Caribe Royale All-Suite Hotel and Convention Center, December 9–12, 2014. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{JWLCA2014CAHBABAWECMLSATHOTT,
    author = {Yan Jiang and Thomas Weise and J{\"{o}}rg L{\"{a}}ssig and Raymond Chiong and Rukshan Athauda},
    title = {Comparing a Hybrid Branch and Bound Algorithm with Evolutionary Computation Methods, Local Search and their Hybrids on the TSP},
    booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS'14), Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI'14)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Orlando, FL, USA: Caribe Royale All-Suite Hotel and Convention Center},
    year = {2014},
    month = {December 9--12, },
    url = {http://www.it-weise.de/documents/files/JWLCA2014CAHBABAWECMLSATHOTT.pdf},
    abstract = {Benchmarking is one of the most important ways to investigate the performance of metaheuristic optimization algorithms. Yet, most experimental algorithm evaluations in the literature limit themselves to simple statistics for comparing end results. Furthermore, comparisons between algorithms from different ''families'' are rare. In this study, we use the TSP Suite - an open source software framework - to investigate the performance of the Branch and Bound (BB) algorithm for the Traveling Salesman Problem (TSP). We compare this BB algorithm to an Evolutionary Algorithm (EA), an Ant Colony Optimization (ACO) approach, as well as three different Local Search (LS) algorithms. Our comparisons are based on a variety of different performance measures and statistics computed over the entire optimization process. The experimental results show that the BB algorithm performs well on very small TSP instances, but is not a good choice for any medium to large-scale problem instances. Subsequently, we investigate whether hybridizing BB with LS would give rise to similar positive results like the hybrid versions of EA and ACO have. This turns out to be true - the ``Memetic`` BB algorithms are able to improve the performance of pure BB algorithms significantly. It is worth pointing out that, while the results presented in this paper are consistent with previous findings in the literature, our results have been obtained through a much more comprehensive and solid experimental procedure.},
    sortkey = {0799965comparingahybridbranch},
    }
  • Abhishek Awasthi, Jörg Lässig, Oliver Kramer, and Thomas Weise. Common Due-Window Problem: Polynomial Algorithms for a Given Processing Sequence. In Proceedings of the IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS’14), Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI’14), Orlando, FL, USA: Caribe Royale All-Suite Hotel and Convention Center, December 9–12, 2014. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{ALKW2014CDWPPAFAGPS,
    author = {Abhishek Awasthi and J{\"{o}}rg L{\"{a}}ssig and Oliver Kramer and Thomas Weise},
    title = {Common Due-Window Problem: Polynomial Algorithms for a Given Processing Sequence},
    booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS'14), Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI'14)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Orlando, FL, USA: Caribe Royale All-Suite Hotel and Convention Center},
    year = {2014},
    month = {December 9--12, },
    url = {http://www.it-weise.de/documents/files/ALKW2014CDWPPAFAGPS.pdf},
    abstract = {The paper considers the Common Due-Window (CDW) problem where a single machine processes a certain number of jobs against a common due-window. Each job possesses different processing times but different and asymmetric earliness and tardiness penalties. The objective of the problem is to find the processing sequence of jobs, their completion times and the position of the given due-window to minimize the total penalty incurred due to tardiness and earliness of the jobs. This work presents exact polynomial algorithms for optimizing a given job sequence for a single machine with the run-time complexity of O(n2), where n is the number of jobs. We also provide an O(n) algorithm for optimizing the CDW with unit processing times. The algorithms take a sequence consisting of all the jobs (Ji; i = 1; 2; : : : ; n) as input and return the optimal completion times, which offers the minimum possible total penalty for the sequence. Furthermore, we implement our polynomial algorithms in conjunction with Simulated Annealing (SA) to obtain the best processing sequence. We compare our results with that of Biskup and Feldmann [1] for different due-window lengths.},
    sortkey = {0799965commonduewindowproblempolynomial},
    }
  • [DOI] Chao Gao, Thomas Weise, and Jinlong Li. Improve the 3-flip Neighborhood Local Search by Random Flat Move for the Set Covering Problem. In Ying Tan, Yuhui Shi, and Carlos Artemio Coello Coello, editors, Advances in Swarm Intelligence: Proceedings of the Fifth International Conference on Swarm Intelligence, Part 1 (ICSI’14), volume 8794 of Lecture Notes in Computer Science (LNCS), pages 27-35, Hefei, Anhui, China, October 17–20, 2014. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [Bibtex]
    @inproceedings{GWL2014IT3FNLSBRFMFTSCP,
    author = {Chao Gao and Thomas Weise and Jinlong Li},
    title = {Improve the 3-flip Neighborhood Local Search by Random Flat Move for the Set Covering Problem},
    booktitle = {Advances in Swarm Intelligence: Proceedings of the Fifth International Conference on Swarm Intelligence, Part 1 (ICSI'14)},
    editor = {Ying Tan and Yuhui Shi and Carlos Artemio {Coello Coello}},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Hefei, Anhui, China},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {8794},
    pages = {27--35},
    year = {2014},
    month = {October 17--20, },
    url = {http://www.it-weise.de/documents/files/GWL2014IT3FNLSBRFMFTSCP.pdf},
    doi = {10.1007/978-3-319-11857-4_4},
    abstract = {The 3-flip neighborhood local search (3FNLS) is an excellent heuristic algorithm for the set covering problem which has dominating performance on the most challenging crew scheduling instances from Italy railways. We introduce a method to further improve the effectiveness of 3FNLS by incorporating random flat move to its search process. Empirical studies show that this can obviously improve the solution qualities of 3FNLS on the benchmark instances. Moreover, it updates two best known solutions within reasonable time.},
    sortkey = {0799907improvethe3flipneighborhood},
    }
  • [DOI] Thomas Weise, Raymond Chiong, Ke Tang, Jörg Lässig, Shigeyoshi Tsutsui, Wenxiang Chen, Zbigniew Michalewicz, and Xin Yao. Benchmarking Optimization Algorithms: An Open Source Framework for the Traveling Salesman Problem. IEEE Computational Intelligence Magazine (CIM), 9(3):40-52, August 2014. Featured article and selected paper at the website of the IEEE Computational Intelligence Society (http://cis.ieee.org/).
    [PDF] [Bibtex]
    @article{WCTLTCMY2014BOAAOSFFTTSP,
    author = {Thomas Weise and Raymond Chiong and Ke Tang and J{\"{o}}rg L{\"{a}}ssig and Shigeyoshi Tsutsui and Wenxiang Chen and Zbigniew Michalewicz and Xin Yao},
    title = {Benchmarking Optimization Algorithms: An Open Source Framework for the Traveling Salesman Problem},
    publisher = {Piscataway, NJ, USA: IEEE Computational Intelligence Society},
    journal = {IEEE Computational Intelligence Magazine (CIM)},
    number = {3},
    volume = {9},
    pages = {40--52},
    year = {2014},
    month = {August},
    url = {http://www.it-weise.de/documents/files/WCTLTCMY2014BOAAOSFFTTSP.pdf},
    doi = {10.1109/MCI.2014.2326101},
    note = {Featured article and selected paper at the website of the IEEE Computational Intelligence Society (http://cis.ieee.org/).},
    abstract = {We introduce an experimentation procedure for evaluating and comparing optimization algorithms based on the Traveling Salesman Problem (TSP).We argue that end-of-run results alone do not give sufficient information about an algorithm{\textquoteright}s performance, so our approach analyzes the algorithm{\textquoteright}s progress over time. Comparisons of performance curves in diagrams can be formalized by comparing the areas under them. Algorithms can be ranked according to a performance metric. Rankings based on different metrics can then be aggregated into a global ranking, which provides a quick overview of the quality of algorithms in comparison. An open source software framework, the TSP Suite, applies this experimental procedure to the TSP. The framework can support researchers in implementing TSP solvers, unit testing them, and running experiments in a parallel and distributed fashion. It also has an evaluator component, which implements the proposed evaluation process and produces detailed reports. We test the approach by using the TSP Suite to benchmark several local search and evolutionary computation methods. This results in a large set of baseline data, which will be made available to the research community. Our experiments show that the tested pure global optimization algorithms are outperformed by local search, but the best results come from hybrid algorithms.},
    sortkey = {0799823benchmarkingoptimizationalgorithmsan},
    }
  • [DOI] Kai Zhang, Thomas Weise, and Jinlong Li. Fitness Level based Adaptive Operator Selection for Cutting Stock Problems with Contiguity. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC’14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI’14), pages 2539-2546, Beijing, China: Beijing International Convention Center (BICC), July 6–11, 2014. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{ZWL2014FLBAOSFCSPWC,
    author = {Kai Zhang and Thomas Weise and Jinlong Li},
    title = {Fitness Level based Adaptive Operator Selection for Cutting Stock Problems with Contiguity},
    booktitle = {Proceedings of the IEEE Congress on Evolutionary Computation (CEC'14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI'14)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Beijing International Convention Center (BICC)},
    pages = {2539--2546},
    year = {2014},
    month = {July 6--11, },
    url = {http://www.it-weise.de/documents/files/ZWL2014FLBAOSFCSPWC.pdf},
    doi = {10.1109/CEC.2014.6900335},
    abstract = {For most optimization problem and solution representation, multiple different possible search operators exist. In this article, we propose the Fitness Level based Adaptive Operator Selection (FLAOS), a self-adaptation approach that automatically selects the right operator depending on the progress of the search. In FLAOS, the objective values of the solutions discovered during the optimization process are divided into intervals, the fitness levels. For each fitness level, a corresponding probability distribution is maintained which defines which operators are to be used and how often to generate the offsprings. An evolutionary algorithm with FLAOS is proposed to solve one-dimensional cutting stock problems (CSPs) with contiguity. The solution of such a problem should minimize both the trim loss and the number of partially finished items. Experimental studies have been carried out to test the effectiveness of the FLAOS. The solutions found by FLAOS are better than or comparable to those solutions found by previous methods.},
    inspec = {14613209},
    sortkey = {0799797fitnesslevelbasedadaptive},
    }
  • [DOI] Thomas Weise, Mingxu Wan, Ke Tang, and Xin Yao. Evolving Exact Integer Algorithms with Genetic Programming. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC’14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI’14), pages 1816-1823, Beijing, China: Beijing International Convention Center (BICC), July 6–11, 2014. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WWTY2014EEIAWGP,
    author = {Thomas Weise and Mingxu Wan and Ke Tang and Xin Yao},
    title = {Evolving Exact Integer Algorithms with Genetic Programming},
    booktitle = {Proceedings of the IEEE Congress on Evolutionary Computation (CEC'14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI'14)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Beijing International Convention Center (BICC)},
    pages = {1816--1823},
    year = {2014},
    month = {July 6--11, },
    url = {http://www.it-weise.de/documents/files/WWTY2014EEIAWGP.pdf},
    slides = {http://www.it-weise.de/documents/files/WWTY2014EEIAWGP_slides.pdf},
    doi = {10.1109/CEC.2014.6900292},
    abstract = {The synthesis of exact integer algorithms is a hard task for Genetic Programming (GP), as it exhibits epistasis and deceptiveness.{\newline}Most existing studies in this domain only target few and simple problems or test a small set of different representations. In this paper, we present the (to the best of our knowledge) largest study on this domain to date. We first propose a novel benchmark suite of 20 non-trivial problems with a variety of different features.{\newline}We then test two approaches to reduce the impact of the negative features:{\newline}(a) a new nested form of Genetic Programming with Transactional Memory (GPTM) to reduce epistatic effects by allowing instructions in the program code to be permutated with less impact on the program behavior and{\newline}(b) our recently published {\{}Frequency Fitness Assignment{\}} method (GPFFA) to reduce the chance of premature convergence on deceptive problems.{\newline}In a full-factorial experiment with six different loop instructions, GPTM, and GPFFA, we find that GP is able to solve all benchmark problems, although not all of them with a high success rate. Several interesting algorithms are discovered. GPFFA has a tremendous positive impact while GPTM turns out not to be useful.},
    inspec = {14613030},
    sortkey = {0799797evolvingexactintegeralgorithms},
    }
  • [DOI] Chao Gao, Thomas Weise, and Jinlong Li. A Weighting-Based Local Search Heuristic Algorithm for the Set Covering Problem. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC’14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI’14), pages 826-831, Beijing, China: Beijing International Convention Center (BICC), July 6–11, 2014. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{GWL2014AWBLSHAFTSCP,
    author = {Chao Gao and Thomas Weise and Jinlong Li},
    title = {A Weighting-Based Local Search Heuristic Algorithm for the Set Covering Problem},
    booktitle = {Proceedings of the IEEE Congress on Evolutionary Computation (CEC'14), Proceedings of the 2014 World Congress on Computational Intelligence (WCCI'14)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Beijing International Convention Center (BICC)},
    pages = {826--831},
    year = {2014},
    month = {July 6--11, },
    url = {http://www.it-weise.de/documents/files/GWL2014AWBLSHAFTSCP.pdf},
    doi = {10.1109/CEC.2014.6900355},
    abstract = {The Set Covering Problem (SCP) is NP-hard and has many applications. In this paper, we introduce a heuristic algorithm for SCPs based on weighting. In our algorithm, a local search framework is proposed to perturb the candidate solution under the best objective value found during the search, a weighting scheme and several search strategies are adopted to help escape from local optima and make the search more divergent. The effectiveness of our algorithm is evaluated on a set of instances from the OR-Library and Steiner triple systems. The experimental results show that it is very competitive, for it is able to find all the optima or best known results with very small runtimes on non-unicost instances from the ORLibrary and outperforms two excellent solvers we have found in literature on the unicost instances from Steiner triple systems. Furthermore, it is simple and has no instance dependent parameters.},
    inspec = {14613018},
    sortkey = {0799797aweightingbasedlocalsearch},
    }
  • [DOI] Thomas Weise, Mingxu Wan, Ke Tang, Pu Wang, Alexandre Devert, and Xin Yao. Frequency Fitness Assignment. IEEE Transactions on Evolutionary Computation (IEEE-EC), 18(2):226-243, April 2014.
    [PDF] [Bibtex]
    @article{WWTWDY2014FFA,
    author = {Thomas Weise and Mingxu Wan and Ke Tang and Pu Wang and Alexandre Devert and Xin Yao},
    title = {Frequency Fitness Assignment},
    publisher = {Washington, DC, USA: IEEE Computer Society},
    journal = {IEEE Transactions on Evolutionary Computation (IEEE-EC)},
    number = {2},
    volume = {18},
    pages = {226--243},
    year = {2014},
    month = {April},
    url = {http://www.it-weise.de/documents/files/WWTWDY2014FFA.pdf},
    doi = {10.1109/TEVC.2013.2251885},
    abstract = {Metaheuristic optimization procedures such as Evolutionary Algorithms are usually driven by an objective function which rates the quality of a candidate solution. However, it is not clear in practice whether an objective function adequately rewards intermediate solutions on the path to the global optimum and it may exhibit deceptiveness, epistasis, neutrality, ruggedness, and a lack of causality. In this paper, we introduce the Frequency Fitness H, subject to minimization, that rates how often solutions with the same objective value have been discovered so far. The ideas behind this method are that good solutions are hard to find and that if an algorithm gets stuck at a local optimum, the frequency of the objective values of the surrounding solutions will increase over time, which will eventually allow it to leave that region again. We substitute a Frequency Fitness Assignment process (FFA) for the objective function into several different optimization algorithms. We conduct a comprehensive set of experiments: the synthesis of algorithms with Genetic Programming (GP), the solution of MAX-3SAT problems with Genetic Algorithms, classification with Memetic Genetic Programming, and numerical optimization with a (1+1) Evolution Strategy, in order to verify the utility of FFA. Given that they have no access to the original objective function at all, it is surprising that for some problems (e.g., the algorithm synthesis task) the FFAbased algorithm variants perform significantly better. However, this cannot be guaranteed for all tested problems. We thus also analyze scenarios where algorithms using FFA do not perform better or even worse than with the original objective functions.},
    inspec = {14196623},
    sortkey = {0799691frequencyfitnessassignment},
    }
  • [DOI] Pu Wang, Ke Tang, Thomas Weise, Edward P. K. Tsang, and Xin Yao. Multiobjective Genetic Programming for Maximizing ROC Performance. Neurocomputing, 125:102-118, February 11, 2014.
    [PDF] [Bibtex]
    @article{WTWTY2013MOGPFMRP,
    author = {Pu Wang and Ke Tang and Thomas Weise and Edward P. K. Tsang and Xin Yao},
    title = {Multiobjective Genetic Programming for Maximizing ROC Performance},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Neurocomputing},
    volume = {125},
    pages = {102--118},
    year = {2014},
    month = {February 11, },
    url = {http://arxiv.org/abs/1303.3145},
    doi = {10.1016/j.neucom.2012.06.054},
    abstract = {commonly used for visualizing, organizing and selecting classifiers based on their performances. important issue in the ROC literature is to obtain the ROC convex hull (ROCCH) that covers potentially optima for a given set of classifiers [1]. Maximizing the ROCCH means to maximize the true positive rate (tpr) and minimize the false positive rate (fpr) for every classifier in ROC space, while tpr and fpr are conflicting with each other. In this paper, we propose Multiobjective Genetic Programming (MOGP) to obtain a group of nondominated classifiers, with which the maximum ROCCH can be achieved. Four different multiobjective frameworks, including Nondominated Sorting Genetic Algorithm II (NSGA-II), Multiobjective Evolutionary Algorithms Based on Decomposition (MOEA/D), Multiobjective selection based on dominated hypervolume (SMS-EMOA), and Approximation-Guided Evolutionary Multi-Objective (AGEMOA) are adopted into GP, because all of them are successful applied into many problems and have their own characters. To improve the performance of each individual in GP,we further propose a memetic approach into GP by defining two local search strategies specifically designed for classification problems. Experimental results based on 27 well-known UCI data sets show that MOGP performs significantly better than singleobjective algorithms such as FGP, GGP, EGP, and MGP, and other traditional machine learning algorithms such as C4.5, Naive Bayes, and PRIE. The experiments also demonstrate the efficacy of the local search operator in the MOGP framework.},
    eiid = {IP52489144},
    sortkey = {0799637multiobjectivegeneticprogrammingfor},
    }
  • Bo Yuan, Xin Yao, Bin Li, and Thomas Weise. A New Memetic Algorithm with Fitness Approximation for the Defect-Tolerant Logic Mapping in Crossbar-based Nano-architectures. IEEE Transactions on Evolutionary Computation (IEEE-EC), 2014.
    [Bibtex]
    @article{YYLW2014ANMAWFAFTDTLMICBNA,
    author = {Bo Yuan and Xin Yao and Bin Li and Thomas Weise},
    title = {A New Memetic Algorithm with Fitness Approximation for the Defect-Tolerant Logic Mapping in Crossbar-based Nano-architectures},
    publisher = {Washington, DC, USA: IEEE Computer Society},
    journal = {IEEE Transactions on Evolutionary Computation (IEEE-EC)},
    year = {2014},
    abstract = {The defect-tolerant logic mapping (DTLM), which has been proven to be an NP-complete combinatorial search problem, is a key step for logic implementation in emerging crossbar-based nano-architectures. However, no practically satisfactory solution has been suggested for the DTLM till now. In this paper, the problem of DTLM is first modeled as a combinatorial optimization problem through introducing Maximum-Bipartite-Matching (MBM). Then, a new Memetic Algorithm with Fitness Approximation (MA/FA) is proposed to solve the optimization problem efficiently. In MA/FA, a new Greedy Re-assignment Local Search operator, capable of utilizing the domain knowledge and information from problem instances, is designed to help the algorithm find optimal logic mapping with consumption of relatively lower computational resources; A Fitness Approximation method is adopted to reduce the time consumption of fitness evaluation dramatically. In addition, a hybrid fitness evaluation strategy that combines the exact and approximated fitness evaluation methods is presented to balance the accuracy and time efficiency of fitness evaluation. The effectiveness and efficiency of proposed methods are testified and evaluated on a large set of benchmark instances of various scales, and the advantage of MA/FA on keeping good balance between effectiveness and efficiency is also observed.},
    sortkey = {0799558anewmemeticalgorithm},
    }

2013

  • [DOI] Hujun Yin, Ke Tang, Yang Gao, Frank Klawonn, Minho Lee, Thomas Weise, Bin Li, and Xin Yao, editors. Proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL’13), volume 8206/2013 of Lecture Notes in Computer Science (LNCS), Hefei, Anhui, China: Empark Grand Hotel, October 20–23, 2013. Berlin, Germany: Springer-Verlag GmbH.
    [Bibtex]
    @proceedings{PROC2013IDEAL,
    title = {Proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'13)},
    editor = {Hujun Yin and Ke Tang and Yang Gao and Frank Klawonn and Minho Lee and Thomas Weise and Bin Li and Xin Yao},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Hefei, Anhui, China: Empark Grand Hotel},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {8206/2013},
    year = {2013},
    month = {October 20--23, },
    doi = {10.1007/978-3-642-41278-3},
    abstract = {This book constitutes the refereed proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2013, held in Hefei, China, in October 2013.{\newline}The 76 revised full papers presented were carefully reviewed and selected from more than 130 submissions.{\newline}These papers provided a valuable collection of latest research outcomes in data engineering and automated learning, from methodologies, frameworks and techniques to applications. In addition to various topics such as evolutionary algorithms, neural networks, probabilistic modelling, swarm intelligent, multi-objective optimisation, and practical applications in regression, classification, clustering, biological data processing, text processing, video analysis, including a number of special sessions on emerging topics such as adaptation and learning multi-agent systems, big data, swarm intelligence and data mining, and combining learning and optimisation in intelligent data engineering.{\newline}Content Level: Research{\newline}Keywords: ant colony optimization - cloud computing - genetic algorithms - parallel computing - semi-supervised learning{\newline}Related subjects: Artificial Intelligence - Database Management {\&} Information Retrieval - Image Processing - Theoretical Computer Science{\newline}In this digital era and subsequent {``}data rich but information poor{''} quandary, the IDEAL conference serves its purposes perfectly {--} making sense of huge volumes of data, evaluating the complexity of real-world problems, and turning data into information and knowledge. The IDEAL conference attracts international experts, researchers, leading academics, practitioners, and industrialists from communities of machine learning, computational intelligence, data mining, knowledge management, biology, neuroscience, bio-inspired systems and agents, and distributed systems. It has enjoyed a vibrant and successful history in the last 15 years, having been held in over 11 locations in 7 different countries. It continues to evolve to embrace emerging topics and exciting trends. This year IDEAL set foot in mainland China, the fastest growing economy in the world. The conference received about 130 submissions, which were rigorously peer-reviewed by Program Committee members. Only the papers judged to be of highest quality were accepted and included in these proceedings. This volume contains 76 papers accepted and presented at the 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2013), held on 20{--}23 October 2013 in Hefei, China. These papers provided a valuable collection of recent research outcomes in data engineering and automated learning, from methodologies, frameworks, and techniques to applications. In addition to various topics such as evolutionary algorithms; neural networks; probabilistic modelling; swarm intelligent; multi-objective optimization and practical applications in regression, classification, clustering, biological data processing, text processing, and video analysis, IDEAL 2013 also featured a number of special sessions on emerging topics such as adaptation and learning multi-agent systems, big data, swarm intelligence and data mining, and combining learning and optimization in intelligent data engineering. We would like to thank all the people who devoted so much time and effort to the successful running of the conference, in particular the members of the Program Committee and reviewers, as well as the authors who contributed to the conference. We are also very grateful for the hard work of the local organizing team at the University of Science and Technology of China (USTC), especially Prof. Bin Li, in local arrangements, as well as the help provided by the University of Manchester in checking through all the camera-ready files. Continued support and collaboration from Springer, in particular from the LNCS editor, Alfred Hoffman and Anna Kramer, are also greatly appreciated.},
    isbn = {978-3-642-41277-6 and 978-3-642-41278-3},
    sortkey = {0799513proceedingsofthe14th},
    }
  • [DOI] Wei Shi and Thomas Weise. An Initialized ACO for the VRPTW. In Hujun Yin, Ke Tang, Yang Gao, Frank Klawonn, Minho Lee, Thomas Weise, Bin Li, and Xin Yao, editors, Proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL’13), volume 8206/2013 of Lecture Notes in Computer Science (LNCS), pages 93-100, Hefei, Anhui, China: Empark Grand Hotel, October 20–23, 2013. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{SW2013AIAFTV,
    author = {Wei Shi and Thomas Weise},
    title = {An Initialized ACO for the VRPTW},
    booktitle = {Proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'13)},
    editor = {Hujun Yin and Ke Tang and Yang Gao and Frank Klawonn and Minho Lee and Thomas Weise and Bin Li and Xin Yao},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Hefei, Anhui, China: Empark Grand Hotel},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {8206/2013},
    chapter = {12},
    pages = {93--100},
    year = {2013},
    month = {October 20--23, },
    url = {http://www.it-weise.de/documents/files/SW2013AIAFTV.pdf},
    slides = {http://www.it-weise.de/documents/files/SW2013AIAFTV_slides.pdf},
    doi = {10.1007/978-3-642-41278-3_12},
    abstract = {The Vehicle Routing Problem with Time Windows is an important task in logistic planning. The expenditure on employing labor force, i.e., drivers for vehicles, accounts for most of the costs in this domain. We propose an initialized Ant Colony approach, IACO-VRPTW, with the primary goal (f 1) to reduce the number of vehicle needed to serve the customers and the second-priority goal (f 2) of decreasing the travel distance. Compared with methods that optimize f 2, IACO-VRPTW can reach or reduce f 1 in 8 out of 18 instances of the Solomon benchmark set, at the cost of increasing travel distance slightly. IACO-VRPTW can effectively decrease the number of vehicles, travel distance and runtime compared with an ACO without initialization.},
    sciids = {BJS17},
    sciwos = {WOS:000329908900012},
    inspec = {13955885},
    sortkey = {0799513aninitializedacofor},
    }
  • Thomas Weise. TSP, Benchmarking, and EC. In Zhi-Hua and Yang Yu, editors, The 8th International Workshop on Nature Inspired Computation and Applications (NICaiA’13 Autumn), Nanjing, Jiangsu, China: Nanjing University, Xianlin Campus, Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Learning And Mining from DatA group (LAMBDA), October 17–19, 2013.
    [PDF] [Bibtex]
    @inproceedings{W2013TBAE,
    author = {Thomas Weise},
    title = {TSP, Benchmarking, and EC},
    booktitle = {The 8th International Workshop on Nature Inspired Computation and Applications (NICaiA'13 Autumn)},
    editor = {{Zhi-Hua} Zhou and Yang Yu},
    address = {Nanjing, Jiangsu, China: Nanjing University, Xianlin Campus, Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Learning And Mining from DatA group (LAMBDA)},
    year = {2013},
    month = {October 17--19, },
    url = {http://www.it-weise.de/documents/files/W2013TBAE.pdf},
    abstract = {Experimentation with the Traveling Salesman Problem:{\newline}Introduction{\newline}How things could be done{\newline}TSP Suite: What can be done for you{\newline}Results: What has been done{\newline}Summary},
    sortkey = {0799510tspbenchmarkingandec},
    }
  • [DOI] Mani Abedini, Michael Kirley, Raymond Chiong, and Thomas Weise. GPU Accelerated eXtended Classifier System. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM’13), pages 293-300, Singapore: Grand Copthorne Waterfront Hotel, April 16–19, 2013. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{AKCW2013GAECS,
    author = {Mani Abedini and Michael Kirley and Raymond Chiong and Thomas Weise},
    title = {GPU Accelerated eXtended Classifier System},
    booktitle = {Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM'13)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Singapore: Grand Copthorne Waterfront Hotel},
    pages = {293--300},
    year = {2013},
    month = {April 16--19, },
    url = {http://www.it-weise.de/documents/files/AKCW2013GAECS.pdf},
    doi = {10.1109/CIDM.2013.6597250},
    abstract = {XCS - the extended Classifier System - combines an evolutionary algorithm with reinforcement learning to evolve a population of condition-action rules (classifiers). Typically, population-based approaches are slow and increasing the problem size (in terms of the number of features/samples) poses a real threat to the suitability of XCS for real-world applications. Thus, reducing the execution time without losing accuracy is highly desirable. Profiling of the execution of off-the-shelf XCS implementations suggests that the rule matching process is the most computational demanding step. A solution to this is parallelization, i.e., using parallel processing techniques to speed up the matching process (and thus the entire XCS learning process). There are many ways to achieve that, using Graphic Processing Units (GPUs) is one option. Originally, GPUs were designed to conduct a sequence of graphics operations in a massively parallel fashion. Today, GPUs can be used for all sorts of general purpose calculations that are normally handled by the CPU. In this paper, we propose a hybrid rule matching process using both CPU and GPU simultaneously for a maximum performance gain. Our experimental results indicate that this approach does speed up the XCS learning process, and that the GPU is the dominant powerful computing resource in the model.},
    eiid = {20134316873557},
    inspec = {13768347},
    sortkey = {0799311gpuacceleratedextendedclassifier},
    }
  • [DOI] Jin Ouyang, Thomas Weise, Alexandre Devert, and Raymond Chiong. SDGP: A Developmental Approach for Traveling Salesman Problems. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS’13), pages 78-85, Singapore: Grand Copthorne Waterfront Hotel, April 15–19, 2013. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{OWDC2013SADAFTSP,
    author = {Jin Ouyang and Thomas Weise and Alexandre Devert and Raymond Chiong},
    title = {SDGP: A Developmental Approach for Traveling Salesman Problems},
    booktitle = {Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Production and Logistics Systems (CIPLS'13)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Singapore: Grand Copthorne Waterfront Hotel},
    pages = {78--85},
    year = {2013},
    month = {April 15--19, },
    url = {http://www.it-weise.de/documents/files/OWDC2013SADAFTSP.pdf},
    slides = {http://www.it-weise.de/documents/files/OWDC2013SADAFTSP_slides.pdf},
    doi = {10.1109/CIPLS.2013.6595203},
    abstract = {This paper presents an Evolutionary Algorithm using a new ontogenic approach, called Staged Developmental Genetic Programming (SDGP), for solving symmetric Traveling Salesman Problems (TSPs). In SDGP, a genotype-phenotype mapping (gpm) is used to refine candidate solutions to a TSP - these candidate solutions are represented as permutations. The gpm performs several development steps, in each of which such a permutation x is incrementally modified. In each iteration within a development step, the process can choose to either apply one of seven different modifications to a specific section of x or to do nothing. The choice is made by the genotypes g, which are functions assigning a real-valued rating to the possible modifications. Smaller ratings are better and the best-rated modification is then applied, if its rating is lower than a given threshold. The genotypes are evolved using Genetic Programming in the tree-based representation well known from Symbolic Regression. Comprehensive numerical simulation experiments show that our proposed algorithm scales well with the problem size and delivers competitive results. It has an overall quadratic runtime in the number of nodes in the TSPs.},
    eiid = {20134116837899},
    inspec = {13752116},
    sortkey = {0799310sdgpadevelopmentalapproach},
    }
  • [DOI] Yu Wang, Bin Li, and Thomas Weise. Two-Stage Ensemble Memetic Algorithm: Function Optimization and Digital IIR Filter Design. Information Sciences — Informatics and Computer Science Intelligent Systems Applications: An International Journal, 220:408-424, January 20, 2013.
    [Bibtex]
    @article{WLW2013TSEMAFOADIFD,
    author = {Yu Wang and Bin Li and Thomas Weise},
    title = {Two-Stage Ensemble Memetic Algorithm: Function Optimization and Digital IIR Filter Design},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Information Sciences {--} Informatics and Computer Science Intelligent Systems Applications: An International Journal},
    volume = {220},
    pages = {408--424},
    year = {2013},
    month = {January 20, },
    doi = {10.1016/j.ins.2012.07.041},
    abstract = {The research on optimal design of infinite-impulse response (IIR) filters based on optimization techniques has gained much attention in recent years. However, due to the limited performance of the applied optimization techniques, the orders of the filters, which can be obtained, are very low in the previous research. Memetic algorithms (MAs) are widely recognized to have better convergence capability than their conventional counterparts. However, the universality of the MAs, e.g. the ability of solving diverse kinds of digital IIR filter designs, is still limited. In this paper, we design a Two-Stage ensemble Memetic Algorithm (TSMA) framework to more appropriately synthesize the strengths of the evolutionary global search and local search techniques. In the first optimization stage, a competition is held among the candidate local search techniques. Its major idea is to choose the best local search technique and to obtain good initial state. Inheriting the good information of the first stage, the second optimization stage is to implement effective adaptive MA to pursue high-quality solution. The experimental studies presented in this paper contain three aspects: (1) the benefits of the TSMA framework are experimentally investigated by comparing TSMA with its sub-optimizers and recent effective evolutionary algorithms (EAs) on 26 test functions; then (2) TSMA is compared with 4 MAs on the CEC05 functions to comprehensively show the advantages of TSMA; and (3) the TSMA and 6 state-of-the-art algorithms are applied to design high-order digital infinite-impulse response (IIR) filters. The experimental results definitely demonstrate the excellent effectiveness, efficiency and reliability of TSMA on both function optimization and digital IIR filter design tasks.},
    eiid = {20124515652734},
    sciids = {065KF},
    sciwos = {WOS:000313146500027},
    sortkey = {0799216twostageensemblememeticalgorithm},
    }
  • [DOI] Bin Li, Yu Wang, Thomas Weise, and Long Long. Fixed-Point Digital IIR Filter Design using Two-Stage Ensemble Evolutionary Algorithm. Applied Soft Computing, 13(1):329-338, January 2013.
    [Bibtex]
    @article{LWWL2013FPDIFDUTSEEA,
    author = {Bin Li and Yu Wang and Thomas Weise and Long Long},
    title = {Fixed-Point Digital IIR Filter Design using Two-Stage Ensemble Evolutionary Algorithm},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Applied Soft Computing},
    number = {1},
    volume = {13},
    pages = {329--338},
    year = {2013},
    month = {January},
    doi = {10.1016/j.asoc.2012.09.004},
    abstract = {The research on optimal design of infinite-impulse response (IIR) filter design based on various optimization techniques, including evolutionary algorithms (EAs), has gained much attention in recent years. Previously, the parameters of digital IIR filters are encoded with floating-point representations. It is known that a fixed-point representation can effectively save computational resources and is more convenient for direct realization on hardware. Inherently, compared with the floating-point representation, the fixed-point representation would make the search space miss much useful gradient information and therefore, surely rises new challenges for continuous EAs. In this paper, we first analyze the fitness landscape properties of optimal digital IIR filter design. Based on the fitness landscape investigation, a two-stage ensemble evolutionary algorithm (TEEA) is applied to digital IIR filter design with fixed-point representation. In order to fully evaluate the performance of TEEA, we experimentally compare it with five state-of-the-art EAs on four types of digital IIR filters with different settings. Based on the experimental results, we can conclude that TEEA has higher convergence speed, better exploration, and higher success rate. In order to benchmark TEEA further, we apply it to some more difficult problems with shorter word length or higher order. We can find that TEEA can provide satisfying performance on these hard tasks as well.},
    eiid = {20124815716038},
    sciids = {042XY},
    sciwos = {WOS:000311506900029},
    sortkey = {0799195fixedpointdigitaliirfilter},
    }
  • [DOI] Thomas Weise, Brian M. Blake, and Steffen Bleul. Semantic Web Service Composition: The Web Service Challenge Perspective. In Athman Bouguettaya and Quan Z. Sheng, editors, Web Services Foundations — Part 1: Foundations of Web Services, chapter 7, pages 161-187. Secaucus, NJ, USA: Springer-Verlag New York, Inc., 2013.
    [PDF] [Bibtex]
    @incollection{WBB2013SWSCTWSCP,
    author = {Thomas Weise and M. Brian Blake and Steffen Bleul},
    title = {Semantic Web Service Composition: The Web Service Challenge Perspective},
    booktitle = {Web Services Foundations {--} Part 1: Foundations of Web Services},
    editor = {Athman Bouguettaya and Quan Z. Sheng},
    publisher = {Secaucus, NJ, USA: Springer-Verlag New York, Inc.},
    chapter = {7},
    pages = {161--187},
    year = {2013},
    url = {http://www.it-weise.de/documents/files/WBB2013SWSCTWSCP.pdf},
    doi = {10.1007/978-1-4614-7518-7_7},
    abstract = {Service-oriented architecture (SOA) is a software design paradigm for creating highly modular, distributed applications.Web services can implement welldefined, atomic functions which can be composed into high-level business processes. The composition of clearly separable modules is one of the key advantages of SOAs. This article provides an overview of research, challenges, and competitions in this domain. We first define and discuss the general notions of syntactical and semantic discovery/composition and the corresponding quality of service (QoS) features. One focus of this chapter is the Web Service Challenge (WSC), which has established an extensive body of knowledge and community of researchers in the area of web service composition. We discuss the structure, requirements, and utilities provided in the scope of this competition. The paper furthermore includes a detailed literature review of the activities of the WSC event in context of the related initiatives.},
    sortkey = {0799161semanticwebservicecomposition},
    }

2012

  • [DOI] Thomas Weise, Raymond Chiong, and Ke Tang. Evolutionary Optimization: Pitfalls and Booby Traps. Journal of Computer Science and Technology (JCST), 27(5):907-936, September 2012. Special Issue on Evolutionary Computation, edited by Xin Yao and Pietro S. Oliveto.
    [PDF] [Bibtex]
    @article{WCT2012EOPABT,
    author = {Thomas Weise and Raymond Chiong and Ke Tang},
    title = {Evolutionary Optimization: Pitfalls and Booby Traps},
    publisher = {Beijing, China: Chinese Academy of Sciences (CAS), Berlin, Germany: Springer-Verlag GmbH, and Beijing, China: Science in China Press (SCP)},
    journal = {Journal of Computer Science and Technology (JCST)},
    number = {5},
    volume = {27},
    pages = {907--936},
    year = {2012},
    month = {September},
    url = {http://www.it-weise.de/documents/files/WCT2012EOPABT.pdf},
    doi = {10.1007/s11390-012-1274-4},
    note = {Special Issue on Evolutionary Computation, edited by Xin Yao and Pietro S. Oliveto.},
    abstract = {Evolutionary Computation (EC), a collective name for a range of metaheuristic black-box optimization algorithms, is one of the fastest-growing areas in computer science. Many manuals and ``how-to``s on the use of different EC methods as well as a variety of free or commercial software libraries are widely available nowadays. However, when one of these methods is applied to a real-world task, there can be many pitfalls and booby traps lurking - certain aspects of the optimization problem that may lead to unsatisfactory results even if the algorithm appears to be correctly implemented and executed. These include the convergence issues, ruggedness, deceptiveness, and neutrality in the fitness landscape, epistasis, non-separability, noise leading to the need for robustness, as well as dimensionality and scalability issues, among others. In this article, we systematically discuss these related hindrances and present some possible remedies. The goal is to equip practitioners and researchers alike with a clear picture and understanding of what kind of problems can render EC applications unsuccessful and how to avoid them from the start.},
    eiid = {20125115809493},
    sciids = {011VE},
    sciwos = {WOS:000309193600002},
    sortkey = {0799062evolutionaryoptimizationpitfallsand},
    }
  • [DOI] Alexandre Devert, Thomas Weise, and Ke Tang. A Study on Scalable Representations for Evolutionary Optimization of Ground Structures. Evolutionary Computation, 20(3):453-472, Fall 2012.
    [PDF] [Bibtex]
    @article{DWT2011ASOSRFEOOGS,
    author = {Alexandre Devert and Thomas Weise and Ke Tang},
    title = {A Study on Scalable Representations for Evolutionary Optimization of Ground Structures},
    publisher = {Cambridge, MA, USA: MIT Press},
    journal = {Evolutionary Computation},
    number = {3},
    volume = {20},
    pages = {453--472},
    year = {2012},
    month = {Fall},
    url = {http://www.marmakoide.org/download/publications/devweita-ecj-preprint.pdf},
    doi = {10.1162/EVCO_a_00054},
    abstract = {This paper presents a comparative study of two indirect representations, a generative and an ontogenic one, on a set of well-known 2D truss design problems. The generative representation encodes the parameters of a trusses design as a mapping from a 2D space. We test both, a trivial generative approach as well as the state-of-the-art NEAT approach. The ontogenic representation encodes truss design parameters as a truss transformation iterated several times, starting from a trivial initial truss. We focus both on the best objective value obtained and the computational cost to reach a given level of optimality. The study shows that the two representations behave very differently. For experimental settings with equal complexity, with the same optimization algorithm and settings, the generative representation provides results which are far from optimal, whereas the ontogenic representation delivers near-optimal solutions. The ontogenic representation is also much less computationally expensive than a direct representation until very close to the global optimum. The study questions the scalability of the generative representations, while the results for the ontogenic representation display a much better scalability.},
    sciids = {978SX},
    sciwos = {WOS:000306767200005},
    pubmedid = {22004002},
    sortkey = {0799062astudyonscalable},
    }
  • [DOI] Thomas Weise, Ke Tang, and Alexandre Devert. A Developmental Solution to (Dynamic) Capacitated Arc Routing Problems using Genetic Programming. In Terence Soule and Jason H. Moore, editors, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO’12), pages 831-838, Philadelphia, PA, USA: Doubletree by Hilton Hotel Philadelphia Center City, July 7–11, 2012. New York, NY, USA: Association for Computing Machinery (ACM).
    [PDF] [PPT] [Bibtex]
    @inproceedings{WDT2012ADSTDCARPUGP,
    author = {Thomas Weise and Ke Tang and Alexandre Devert},
    title = {A Developmental Solution to (Dynamic) Capacitated Arc Routing Problems using Genetic Programming},
    booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'12)},
    editor = {Terence Soule and Jason H. Moore},
    publisher = {New York, NY, USA: Association for Computing Machinery (ACM)},
    address = {Philadelphia, PA, USA: Doubletree by Hilton Hotel Philadelphia Center City},
    pages = {831--838},
    year = {2012},
    month = {July 7--11, },
    url = {http://www.it-weise.de/documents/files/WDT2012ADSTDCARPUGP.pdf},
    slides = {http://www.it-weise.de/documents/files/WDT2012ADSTDCARPUGP_slides.pdf},
    doi = {10.1145/2330163.2330278},
    abstract = {A developmental, ontogenic approach to Capacitated Arc Routing Problems (CARPs) is introduced. The genotypes of this method are constructive heuristics specified as trees of mathematical functions which are evolved with Genetic Pro- gramming (GP). In a genotype-phenotype mapping, they guide a virtual vehicle which starts at the depot. The geno- type is used to compute a heuristic value for each edge with unsatisfied demands. Local information such as the visiting costs from the current position, the remaining load of the vehicle, and the edge demands are available to the heuris- tic. The virtual vehicle then serves the edge with the low- est heuristic value and is located at its end. This process is repeated until all requirements have been satisfied. The resulting phenotypes are sets of tours which, in turn, are sequences of edges. We show that our method has three advantages: 1) The genotypes can be reused to seed the population in new GP runs. 2) The size of the genotypes is independent from the problem scale. 3) The evolved heuris- tics even work well in modified or dynamic scenarios and are robust in the presence of noise.},
    eiid = {20123315330852},
    sciids = {BCB49},
    sciwos = {WOS:000309611100104},
    sortkey = {0799004adevelopmentalsolutionto},
    }
  • [DOI] Brian M. Blake, Ajay Bansal, Srividya Kona Bansal, Steffen Bleul, and Thomas Weise. Overview of the Web Services Challenge (WSC): Discovery and Composition of Semantic Web Services. In Brian M. Blake, Liliana Cabral, Birgitta König-Ries, Ulrich Küster, and David Martin, editors, Semantic Web Services — Advancement through Evaluation, chapter 19, pages 297-312. Berlin/Heidelberg: Springer-Verlag, June 30, 2012.
    [PDF] [Bibtex]
    @incollection{BBKBBW2012OOTWSCWDACOSWS,
    author = {M. Brian Blake and Ajay Bansal and Srividya {Kona Bansal} and Steffen Bleul and Thomas Weise},
    title = {Overview of the Web Services Challenge (WSC): Discovery and Composition of Semantic Web Services},
    booktitle = {Semantic Web Services {--} Advancement through Evaluation},
    editor = {M. Brian Blake and Liliana Cabral and Birgitta {K{\"{o}}nig-Ries} and Ulrich K{\"{u}}ster and David Martin},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    chapter = {19},
    pages = {297--312},
    year = {2012},
    month = {June 30, },
    url = {http://www.it-weise.de/documents/files/BBKBBW2012OOTWSCWDACOSWS.pdf},
    doi = {10.1007/978-3-642-28735-0_19},
    sortkey = {0798994overviewoftheweb},
    }
  • Ke Tang, Zhenyu Yang, and Thomas Weise. Special Session on Evolutionary Computation for Large Scale Global Optimization at 2012 IEEE World Congress on Computational Intelligence (CEC@WCCI-2012). Technical Report, Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL), June 14, 2012.
    [PDF] [Bibtex]
    @techreport{TYW2012SSOECFLSGO,
    author = {Ke Tang and Zhenyu Yang and Thomas Weise},
    title = {Special Session on Evolutionary Computation for Large Scale Global Optimization at 2012 IEEE World Congress on Computational Intelligence (CEC@WCCI-2012)},
    institution = {Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL)},
    year = {2012},
    month = {June 14, },
    url = {http://www.it-weise.de/documents/files/TYW2012SSOECFLSGO.pdf},
    abstract = {Special Session on{\newline}Evolutionary Computation for Large Scale Global Optimization{\newline}2012 IEEE World Congress on Computational Intelligence (CEC@WCCI-2012){\newline}June 10-15, 2012, Brisbane, Australia{\newline}--------------------------------------------------------------------------------{\newline}Aim and scope (The companion competition){\newline}In the past two decades, different kinds of nature-inspired optimization algorithms have been developed and applied to solve optimization problems, including Simulated Annealing (SA), Evolutionary Algorithms (EAs), Differential Evolution (DE), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Estimation of Distribution Algorithms (EDA), etc. Although these approaches have shown excellent search abilities when applying to some small or medium size problems, many of them will encounter severe difficulties when applying to large scale problems, e.g., problems with up to 1000 variables. The reasons appear to be two-fold. First, the complexity of a problem usually increases with the number of decision variables, number of constraints, or even number of objectives (for multi-objective optimization). This emergent complexity might prevent a previously successful search strategy from finding the optimal solution. Second, the solution space of the problem increases exponentially with the number of decision variables, and a more efficient search strategy is required to explore all the promising regions with limited computational resources.{\newline}Historically, scaling up EAs to large scale problems has attracted much interest, including both theoretical and practical studies. However, existing work in the areas of EAs are still limited given the significance of the scalability issue. Due to this fact, this special session is devoted to highlight the recent advances in EAs for large scale optimization problems, involving single objective or multiple objectives, unconstrained or constrained problems, binary or discrete or real or mixed decision variables. Specifically, we encourage interested researchers to submit their latest work on:{\newline}* Both theoretical and experimental analysis of the scalability of EAs.{\newline}* Novel approaches and algorithms for scaling up EAs to large scale optimization problems.{\newline}* Applications of EAs to real-world large scale optimization problems.{\newline}* Papers on novel test suites that help us in understanding problem characteristics are also welcome.{\newline}Furthermore, a companion competition on Large Scale Global Optimization will also be organized in company with our special session. The competition allows participants to run their own algorithms on 20 benchmark functions, each of which is of 1000 dimensions. The purpose of this competition is to compare different algorithm on the exactly same platform. Researchers are welcome to apply any kind of evolutionary computation approach to the test suite. The approach and the results can be reported in a paper for the special session (i.e., submitted via the online submission system of WCCI-2012).{\newline}Important Dates{\newline}Paper Submission: December 19, 2011{\newline}Acceptance Notification: February 20, 2012{\newline}Final Manuscript Due: April 2, 2012{\newline}For latest news, please refer to http://www.ieee-wcci2012.org.{\newline}Paper Submission{\newline}Manuscripts should be prepared according to the standard format and page limit specified in CEC 2012. For more submission instructions, please see the WCCI submission page at: http://www.ieee-wcci2012.org. Please indicate during submission that your paper is submitted to this special session.{\newline}Special Session Organizers{\newline}Ke Tang{\newline}Nature Inspired Computation and Applications Laboratory (NICAL){\newline}School of Computer Science and Technology{\newline}University of Science and Technology of China, Hefei, Anhui, China{\newline}Email: ketang@ustc.edu.cn, Website: http://staff.ustc.edu.cn/{\verb=~=}ketang{\newline}Zhenyu Yang{\newline}Department of Computer Science and Technology{\newline}East China Normal University, Shanghai, China{\newline}Email: zhyuyang@mail.ustc.edu.cn{\newline}Thomas Weise{\newline}Nature Inspired Computation and Applications Laboratory (NICAL){\newline}School of Computer Science and Technology{\newline}University of Science and Technology of China, Hefei, Anhui, China{\newline}Email: tweise@gmx.de, Website: http://www.it-weise.de{\newline}Program Committee{\newline}* Swagatam Das, Jadavpur University, India{\newline}* Yaochu Jin, University of Surrey, UK{\newline}* Bin Li, University of Science and Technology of China, China{\newline}* Xiaodong Li, RMIT University, Australia{\newline}* Manuel Lozano, University of Granada, Spain{\newline}* Alberto Moraglio, University of Birmingham, UK{\newline}* Mohammad N. Omidvar, RMIT University, Australia{\newline}* Yew Soon Ong, Nanyang Technological University, Singapore{\newline}* Kai Qin, INRIA Grenoble Rhone-Alpes, France{\newline}* Shahryar Rahnamayan, University of Ontario Institute of Technology, Canada{\newline}* Ponnuthurai Nagaratnam Suganthan, Nanyang Technological University, Singapore{\newline}* Yong Wang, Central South University, China{\newline}Related Events{\newline}* CEC'2012 Competition on Large Scale Global Optimization{\newline}* CEC'2010 Special Session and Competition on Large Scale Global Optimization{\newline}* CEC'2008 Special Session and Competition on Large Scale Global Optimization},
    sortkey = {0798978specialsessiononevolutionary},
    }
  • Thomas Weise. Representations for Logistic Planning. In Xin Yao, editor, The Third NICaiA Workshop on Nature Inspired Computation and Its Applications (NICaiA’12), Birmingham, UK: University of Birmingham, Computer Science Building, April 16–17, 2012.
    [PDF] [Bibtex]
    @inproceedings{W2012RFLP,
    author = {Thomas Weise},
    title = {Representations for Logistic Planning},
    booktitle = {The Third NICaiA Workshop on Nature Inspired Computation and Its Applications (NICaiA'12)},
    editor = {Xin Yao},
    address = {Birmingham, UK: University of Birmingham, Computer Science Building},
    year = {2012},
    month = {April 16--17, },
    url = {http://www.it-weise.de/documents/files/W2012RFLP.pdf},
    abstract = {A presentation discussing two case studies on non-trivial representations in logistic planning scenarios: 1) a non-standard search and solution space for real-world vehicle routing (VRP) for multi-modal, container-based transport with intelligent search operations. 2) a developmental approach to the Capacitated Arc Routing Problem (CARP) in which the genotypes are heuristic functions evolved with GP and translated to full schedules via a developmental/iterative genotype-phenotype mapping (GPM).},
    sortkey = {0798914representationsforlogisticplanning},
    }
  • Jelena Jovanović, Raymond Chiong, and Thomas Weise. Social Networking, Teaching, and Learning: Introduction to Special Section on Social Networking, Teaching, and Learning (SNTL). Interdisciplinary Journal of Information, Knowledge, and Management (IJIKM), 7:39-43, April 13, 2012.
    [PDF] [Bibtex]
    @article{JCW2012SNTALITSSOSNTAL,
    author = {Jelena Jovanovi{\'{c}} and Raymond Chiong and Thomas Weise},
    title = {Social Networking, Teaching, and Learning: Introduction to Special Section on Social Networking, Teaching, and Learning (SNTL)},
    publisher = {Santa Rosa, CA, USA: Informing Science Institute (ISI)},
    journal = {Interdisciplinary Journal of Information, Knowledge, and Management (IJIKM)},
    volume = {7},
    pages = {39--43},
    year = {2012},
    month = {April 13, },
    url = {http://www.ijikm.org/Volume7/IJIKMv7p039-043Editorial572.pdf},
    abstract = {Today{\textquoteright}s students and educators live in the world of Facebook, Twitter, Wikipedia and YouTube. These and many other social networking and social media applications are part of the so-called Social Web (i.e., Web 2.0), best characterised by the notions of social interaction, content sharing, and collective intelligence. In addition, today{\textquoteright}s students, often referred to as digital natives (Prensky, 2001), have spent most of their time on computers, game consoles, digital music players, video cameras, cell phones, as well as the Web itself. Being used to constant engagement and multitasking in their day-to-day activities, students need a high level of social and creative en-gagement in learning. Traditional teaching approaches favouring passive content consumption, therefore, are no longer applicable and have to be substituted, or at least complemented, with highly interactive learning processes.},
    eiid = {20122415119200},
    socbus = {2-s2.0-84862023478},
    inspec = {13270468},
    sortkey = {0798911socialnetworkingteachingand},
    }
  • [DOI] Thomas Weise and Ke Tang. Evolving Distributed Algorithms with Genetic Programming. IEEE Transactions on Evolutionary Computation (IEEE-EC), 16(2):242-265, April 2012. Received “CIS Publication Spotlight“ in the August 2012 issue of the IEEE Computational Intelligence Magazine (CIM).
    [PDF] [Bibtex]
    @article{WT2011EVDAWGP,
    author = {Thomas Weise and Ke Tang},
    title = {Evolving Distributed Algorithms with Genetic Programming},
    publisher = {Washington, DC, USA: IEEE Computer Society},
    journal = {IEEE Transactions on Evolutionary Computation (IEEE-EC)},
    number = {2},
    volume = {16},
    pages = {242--265},
    year = {2012},
    month = {April},
    url = {http://www.it-weise.de/documents/files/WT2011EVDAWGP.pdf},
    doi = {10.1109/TEVC.2011.2112666},
    note = {Received ``CIS Publication Spotlight`` in the August 2012 issue of the IEEE Computational Intelligence Magazine (CIM).},
    abstract = {In this article, we evaluate the applicability of Genetic Programming (GP) for the evolution of distributed algorithms. We carry out a large-scale experimental study in which we tackle three well-known problems from distributed computing with six different program representations. For this purpose, we first define a simulation environment in which phenomena such as asynchronous computation at changing speed and messages taking over each other, i.e., out-of-order message delivery, occur with high probability. Second, we define extensions and adaptations of established GP approaches (such as treebased and Linear Genetic Programming) in order to make them suitable for representing distributed algorithms. Third, we introduce novel rule-based Genetic Programming methods designed especially with the characteristic difficulties of evolving algorithms (such as epistasis) in mind. Based on our extensive experimental study of these approaches, we conclude that GP is indeed a viable method for evolving non-trivial, deterministic, non-approximative distributed algorithms. Furthermore, one of the two rule-based approaches is shown to exhibit superior performance in most of the tasks and thus can be considered as an interesting idea also for other problem domains.},
    eiid = {20121614951654 and IP51643605},
    sciids = {922IH},
    sciwos = {WOS:000302540100006},
    socbus = {6026925},
    sortkey = {0798897evolvingdistributedalgorithmswith},
    }

2011

  • [DOI] Yu Wang, Bin Li, Thomas Weise, Jianyu Wang, Bo Yuan, and Qiongjie Tian. Self-Adaptive Learning Based Particle Swarm Optimization. Information Sciences — Informatics and Computer Science Intelligent Systems Applications: An International Journal, 181(20):4515-4538, October 15, 2011.
    [Bibtex]
    @article{WLWWYT2010SALBPSO,
    author = {Yu Wang and Bin Li and Thomas Weise and Jianyu Wang and Bo Yuan and Qiongjie Tian},
    title = {Self-Adaptive Learning Based Particle Swarm Optimization},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Information Sciences {--} Informatics and Computer Science Intelligent Systems Applications: An International Journal},
    number = {20},
    volume = {181},
    pages = {4515--4538},
    year = {2011},
    month = {October 15, },
    doi = {10.1016/j.ins.2010.07.013},
    abstract = {Particle swarm optimization (PSO) is a population-based stochastic search technique for solving optimization problems over continuous space, which has been proven to be efficient and effective in wide applications in scientific and engineering domains. However, the universality of current PSO variants, i.e., their ability to achieve good performance on a variety of different fitness landscapes, is still unsatisfying. For many practical problems, where the fitness landscapes are usually unknown, employing a trial-and-error scheme to search for the most suitable PSO variant is computationally expensive. Therefore, it is necessary to develop a more adaptive and robust PSO version to provide users a black-box tool for various application problems. In this paper, we propose a self-adaptive learning based PSO (SLPSO) to make up the above demerits. SLPSO simultaneously adopts four PSO based search strategies. A probability model is used to describe the probability of a strategy being used to update a particle. The model is self-adaptively improved according to the strategies{\textquoteright} ability of generating better quality solutions in the past generations. In order to evaluate the performance of SLPSO, we compare it with eight state-of-the-art PSO variants on 26 numerical optimization problems with different characteristics such as uni-modality, multi-modality, rotation, ill-condition, mis-scale and noise. The experimental results clearly verify the advantages of SLPSO. Moreover, a practical engineering problem, the economic load dispatch problem of power systems (ELD), is used to further evaluate SLPSO. Compared with the previous effective ELD evolutionary algorithms, SLPSO can update the best solution records.},
    eiid = {20113014172389 and IP51031102},
    sciids = {802ZG},
    sciwos = {WOS:000293548900010},
    sortkey = {0798714selfadaptivelearningbasedparticle},
    }
  • Raymond Chiong, Thomas Weise, and Zbigniew Michalewicz. Variants of Evolutionary Algorithms for Real-World Applications — Preface. In Raymond Chiong, Thomas Weise, and Zbigniew Michalewicz, editors, Variants of Evolutionary Algorithms for Real-World Applications, pages I–XIV. Berlin/Heidelberg: Springer-Verlag, 2011.
    [Bibtex]
    @incollection{CWM2011VOEAFRWAP,
    author = {Raymond Chiong and Thomas Weise and Zbigniew Michalewicz},
    title = {Variants of Evolutionary Algorithms for Real-World Applications {--} Preface},
    booktitle = {Variants of Evolutionary Algorithms for Real-World Applications},
    editor = {Raymond Chiong and Thomas Weise and Zbigniew Michalewicz},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    pages = {I--XIV},
    year = {2011},
    abstract = {Started as a mere academic curiosity, Evolutionary Algorithms (EAs) first came into sight back in the 1960s. However, it was not until the 1980s that the research on EAs became less theoretical and more practical. As a manifestation of population-based, stochastic search algorithms that mimic natural evolution, EAs use genetic operators such as crossover and mutation for the search process to generate new solutions through a repeated application of variation and selection.{\newline}Due to their ability to find excellent solutions for conventionally hard and dynamic problems within acceptable time, EAs have attracted interest from many researchers and practitioners in recent years. The general-purpose, black-box character of EAs makes them suitable for a wide range of realworld applications. Standard EAs such as Genetic Algorithms (GAs) and Genetic Programming (GP) are becoming more and more accepted in the industry and commercial sectors. With the dramatic increase in computational power today, an incredible diversification of new application areas of these techniques can be observed. At the same time, variants and other classes of evolutionary optimisation methods such as Differential Evolution, Estimation of Distribution Algorithms, Co-evolutionary Algorithms and Multi-Objective Evolutionary Algorithms (MOEAs) have been developed.{\newline}When applications or systems utilising EAs reach the production stage, off-the-shelf versions of these methods are typically replaced by dedicated algorithm variants. These specialised EAs often use tailored reproduction operators, search spaces differing significantly from the well-known binary or tree-based encodings, non-trivial genotype-phenotype mappings, or are hybridised with other optimisation algorithms. This book aims to promote the practitioner{\textquoteright}s view on EAs by giving a comprehensive discussion of how EAs can be adapted to the requirements of various applications in the real-world domains. It comprises 14 chapters, which can be categorised into the following four sections:{\newline}{\textbullet} Section I: Introduction{\newline}{\textbullet} Section II: Planning {\&} Scheduling{\newline}{\textbullet} Section III: Engineering{\newline}{\textbullet} Section IV: Data Collection, Retrieval {\&} Mining{\newline}The first section contains only one single chapter {--} the introductory chapter. In this chapter, Blum et al. re-visit the fundamental question of {``}what is an EA?{''} in an attempt to clearly define the scope of this book. In this regard, they systematically explore and discuss both the traditional and the modern views on this question by relating it to other areas in the field. That is, apart from discussing the main characteristics of conventional EAs they also extend their discussion to Memetic Algorithms (MAs) and the Swarm Intelligence algorithms. It appears that establishing semantic borders between the different algorithm families is never easy, nor necessarily useful. In this book, however, the focus will be on the traditional set of EAs like GAs, GP, and their variants.{\newline}The second section of the book deals with planning and scheduling problems. Planning and scheduling activities are among the most important tasks in Business and Industry. Once orders are placed by a customer, it is necessary to schedule the purchase of raw materials and to decide which machines are going to be used in order to create the ordered product in the desired quality. Often, multiple different client requests need to be facilitated at the same time and the goal is to satisfy all of them in a timely and cost-effective manner. However, it is not only the production steps that need to be scheduled. In fact, the whole behaviour of a supply chain as well as the work assignments for employees can be subject to planning. This section contains six chapters, with different groups of researchers presenting efficient EA approaches to a variety of real-world planning and scheduling problems.{\newline}The first chapter in this section by Mohais et al. introduces a tailor-made EA for the process of bottling wine in a mass-production environment. Timevarying (dynamic) constraints are the focus of this chapter. That is, scheduling for job shop problems rarely starts with a blank sheet of paper. Instead, some production processes will already be in progress. Hence, there is typically a set of scheduled operations that are fixed and cannot be modified by optimisation, yet will influence the efficiency and feasibility of new plans. Mohais et al. successfully approach the wine bottling problem with their tailor-made evolutionary method.{\newline}Following which, Toledo et al. present a similar real-world problem for soft-drink manufacturing plants known as the synchronised and integrated two-level lot sizing and scheduling problem. Here, the first production level has tanks storing the soft drink flavours and the second level corresponds to the bottling lines. The problem involves capacity limits, different costs and production times depending on the raw materials involved as well as the inventory costs. In order to derive production schedules with low associated costs in this scenario, Toledo et al. propose the use of an MA. This algorithm has a population structured as tree of clusters. It uses either Threshold Accepting or Tabu Search as local search, and utilises different operators. These variants have shown to outperform both the GA and a Relax approach based on some real-world data sets. In particular, the Tabu Search variant has turned out to be very efficient and robust.{\newline}The third chapter of the section by L{\"{a}}ssig et al. considers simulation-based optimisation of hub-and-spoke inventory systems and multi-location inventory systems with lateral transshipments. Such systems are very common in the industry, but it is extremely challenging to find the optimal order and transshipment policies for them in an analytical way. L{\"{a}}ssig et al. therefore suggest a simulation-based evolutionary approach, where the utility of rules is estimated by simulating the behaviour of the system applying them. This simulation process is used to compute the fitness of the policies. L{\"{a}}ssig et al. show that Threshold Accepting, Particle Swarm Optimisation, and especially GAs can effectively tackle the resulting optimisation problems.{\newline}Subsequently, Schellenberg et al. present a fuzzy-evolutionary approach for optimising the behaviour of a multi-echelon supply chain network of an Australian ASX Top 50 company. They use an EA for synthesising fuzzy rules for each link of the supply chain in order to satisfy all demands while adhering to system constraints (such as silo capacity limits which must not be exceeded due to overproduction further down the chain). Their experimental studies show that the evolution of behaviour rules that can issue commands based on the current situation is much more efficient than trying to generate complete plans scheduling each single supply and production event.{\newline}The following chapter by Dasgupta et al. provides a new solution to the task-based sailor assignment problem faced by the US Navy. That is, a sailor in active duty is usually reassigned to a different job around every three years. Here, the goal is to pick new jobs for the sailors currently scheduled for reassignment in a way that is most satisfying for them as well as the commanders. In the work presented by Dasgupta et al., these assignments have been broken further down to different tasks for different timeslots per sailor. For this purpose, Dasgupta et al. use a parallel implementation of a hybrid MOEA which combines the NSGA-II and some intelligent search operations. The experimental results show that the proposed solution is promising. In the final chapter of the section, Ma and Zhang discuss how a production planning process can be optimised with a GA using the example of CNC-based work{\newline}piece construction. A customisable job shop environment is presented, which can easily be adapted by the users. The optimisation approach then simultaneously selects the right machines, tools, commands for the tools, and operation sequences to manufacture a desired product. The applied GA minimises a compound of the machine costs, the tool costs and the machine, setup, and tool change cost. It is embedded into a commercial computer-aided design system and its utility is demonstrated through a case study. The work of Ma and Zhang leads us to the third section of this book, addressing another crucial division of any industrial company: R {\&} D (Research and Development) and Engineering. In this area, EA-based approaches again have shown huge potential for supporting the human operators in creating novel and more efficient products. However, there are two challenges. On one hand, the evaluation of an engineering design usually involves complex simulations and hence, takes quite a long time to complete. This decreases the utility of common EAs that often require numerous fitness evaluations. On the other hand, many engineering problems have a high-dimensional search space, i.e., they involve many decision variables. In this section, three chapters showcase how these challenges can be overcome and how EAs are able to deliver excellent solutions for hard, real-world engineering problems. In mechanical design problems, the goal is to find structures with specific physical properties. The Finite Element Method (FEM) can for example be used to assess the robustness of composite beams, trusses, airplane wings, and piezoelectric actuators. If such structures are to be optimised, as is the case in the chapter presented by Davarynejad et al., the FEM represents an indispensable tool for assessing the utility of the possible designs. However, each of its invocations requires a great amount of runtime and thus slows down the optimisation process considerably. To this end, Davarynejad et al. propose an adaptive fuzzy fitness granulation approach {--} a method which allows approximating the fitness of new designs based on previously tested ones. The proposed approach is shown to be able to reduce the amount of FEM invocations and speed up the optimisation process for these engineering problems significantly.{\newline}In the next chapter, Turan and Cui introduce a hybrid evolutionary approach for ship stability design, with a particular focus on roll on/roll off passenger ships. Since the evaluation of each ship design costs much runtime, the MOEA (i.e., NSGA-II) utilised by Turan and Cui is hybridised with Q-learning to guide the search directions. The proposed approach provides reasonably good results, where Turan and Cui are able to discover ship designs that represent significant improvements from the original design. The chapter by Rempis and Pasemann presents a new evolutionary method, which they called the Interactively Constrained Neuro-Evolution (ICONE) approach. ICONE uses an EA for synthesising the walking behaviour of humanoid robots. While bio-inspired neural control techniques have been highly promising for robot control, in the case when many sensor inputs have to be processed and many actuators need to be controlled the search space size may increase rapidly. Rempis and Pasemann therefore propose the use of both domain knowledge and restrictions of the possible network structures in their approach. As the name suggests, ICONE is interactive, thus allows the experimenter to bias the search towards the desired structures. This leads to excellent results in the walking-behaviour synthesis experiments.{\newline}The final section of the book concerns data collection, retrieval, and mining. The gathering, storage, retrieval and analysis of data is yet another essential area not just in the industry but also the public sectors, or even military. Database systems are the backbone of virtually every enterprise computing environment. The extraction of information from data such as images has many important applications, e.g., in medicine. The ideal coverage of an area with mobile sensors in order to gather data can be indispensible for, e.g., disaster recovery operations. This section covers four chapters dealing with this line of real-world applications from diverse fields.{\newline}A common means to reduce cost in the civil construction industry is to stabilise soil by mixing lime, cement, asphalt or any combination of these chemicals into it. The resulting changes in soil features such as strength, porosity, and permeability can then ease road constructions and foundation. In the chapter presented by Alavi et al., a Linear GP (LGP) approach is used to estimate the properties of stabilised soil. GP evolves program-like structures, and its linear version represents programs as a sequential list of instructions. Alavi et al. apply LGP in its original (purely evolutionary) version as well as a version hybridised with Simulated Annealing. Their experimental studies confirm that the accuracy of the proposed approach is satisfactory. The next chapter by Bilotta et al. discusses the segmentation of MRI images for (multiple sclerosis) lesion detection and lesion tissue volume estimation. In their work, Bilotta et al. present an innovative approach based on Cellular Neural Networks (CNNs), which they synthesise with a GA. This way, CNNs can be generated for both 2D and 3D lesion detection, which provides new perspectives for diagnostics and is a stark improvement compared to the currently used manual lesion delineation approach. Databases are among the most important elements of all enterprise software architectures. Most of them can be queried by using Structured Query Language (SQL). Skyline extends SQL by allowing queries for trade-off curves concerning two or more attributes over datasets, similar to Pareto frontiers. Before executing such a query, it is typically optimised via equivalence transformations for the purpose of minimising its runtime. In the penultimate chapter of this section (also of this book), Goncalves et al. introduce an alternative approach for Skyline Query Optimisation based on an EA. They show that the variants of their proposed approach are able to outperform the commonly-used dynamic programming, especially as the number of tables increases.{\newline}Distributing the nodes of Mobile Ad-hoc Networks (MANETs) as uniformly as possible over a given terrain is an important problem across a variety of real-world applications, ranging from those for civil to military purposes. The final chapter by Sahin et al. shows how a Force-based GA (FGA) can provide the node executing it with movement instructions which accomplish this objective. Here, one instance of the FGA is executed on each node of the MANET, and only local knowledge obtained from within the limited sensor and communication range of a node is utilised. The simulation experiments confirm that the FGA can be an effective mechanism for deploying mobile nodes with restrained communication capabilities in MANETs operating in unknown areas. To sum up, we would like to extend our gratitude to all the authors for their excellent contributions to this book. We also wish to thank all the reviewers involved in the review process for their constructive and useful review comments. Without their help, this book project could not have been satisfactorily completed. A special note of thanks goes to Dr. Thomas Ditzinger (Engineering Senior Editor, Springer-Verlag) and Ms Heather King (Engineering Editorial, Springer-Verlag) for their editorial assistance and professional support. Finally, we hope that readers would enjoy reading this book as much as we have enjoyed putting it together!{\newline}June 2011 Raymond Chiong{\newline}Thomas Weise{\newline}Zbigniew Michalewicz},
    sortkey = {0798696variantsofevolutionaryalgorithms},
    }
  • [DOI] Raymond Chiong, Thomas Weise, and Zbigniew Michalewicz, editors. Variants of Evolutionary Algorithms for Real-World Applications. Berlin/Heidelberg: Springer-Verlag, 2011.
    [PDF] [Bibtex]
    @book{CWM2011VOEAFRWA,
    title = {Variants of Evolutionary Algorithms for Real-World Applications},
    editor = {Raymond Chiong and Thomas Weise and Zbigniew Michalewicz},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    year = {2011},
    url = {http://books.google.de/books?id=B2ONePP40MEC},
    doi = {10.1007/978-3-642-23424-8},
    abstract = {Evolutionary Algorithms (EAs) are population-based, stochastic search algorithms that mimic natural evolution. Due to their ability to find excellent solutions for conventionally hard and dynamic problems within acceptable time, EAs have attracted interest from many researchers and practitioners in recent years. This book ``Variants of Evolutionary Algorithms for Real-World Applications`` aims to promote the practitioner{\textquoteright}s view on EAs by providing a comprehensive discussion of how EAs can be adapted to the requirements of various applications in the real-world domains. It comprises 14 chapters, including an introductory chapter re-visiting the fundamental question of what an EA is and other chapters addressing a range of real-world problems such as production process planning, inventory system and supply chain network optimisation, task-based jobs assignment, planning for CNC-based work piece construction, mechanical/ship design tasks that involve runtimeintense simulations, data mining for the prediction of soil properties, automated tissue classification for MRI images, and database query optimisation, among others. These chapters demonstrate how different types of problems can be successfully solved using variants of EAs and how the solution approaches are constructed, in a way that can be understood and reproduced with little prior knowledge on optimisation.},
    isbn = {978-3-642-23423-1 and 978-3-642-23424-8},
    googleBookID = {B2ONePP40MEC},
    sortkey = {0798696variantsofevolutionaryalgorithms},
    }
  • [DOI] Christian Blum, Raymond Chiong, Maurice Clerc, Kenneth Alan De Jong, Zbigniew Michalewicz, Ferrante Neri, and Thomas Weise. Evolutionary Optimization. In Raymond Chiong, Thomas Weise, and Zbigniew Michalewicz, editors, Variants of Evolutionary Algorithms for Real-World Applications, chapter 1, pages 1-29. Berlin/Heidelberg: Springer-Verlag, 2011.
    [PDF] [Bibtex]
    @incollection{BCCDJMNW2011EO,
    author = {Christian Blum and Raymond Chiong and Maurice Clerc and Kenneth Alan {De Jong} and Zbigniew Michalewicz and Ferrante Neri and Thomas Weise},
    title = {Evolutionary Optimization},
    booktitle = {Variants of Evolutionary Algorithms for Real-World Applications},
    editor = {Raymond Chiong and Thomas Weise and Zbigniew Michalewicz},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    chapter = {1},
    pages = {1--29},
    year = {2011},
    url = {http://www.it-weise.de/documents/files/BCCDJMNW2011EO.pdf},
    doi = {10.1007/978-3-642-23424-8_1},
    abstract = {The emergence of different metaheuristics and their new variants in recent years has made the definition of the term Evolutionary Algorithms unclear. Originally, it was coined to put a group of stochastic search algorithms that mimic natural evolution together. While some people would still see it as a specific term devoted to this group of algorithms, including Genetic Algorithms, Genetic Programming, Evolution Strategies, Evolutionary Programming, and to a lesser extent Differential Evolution and Estimation of Distribution Algorithms, many others would regard ``Evolutionary Algorithms`` as a general term describing population-based search methods that involve some form of randomness and selection. In this chapter, we re-visit the fundamental question of ``what is an Evolutionary Algorithm?`` not only from the traditional viewpoint but also the wider, more modern perspectives relating it to other areas of Evolutionary Computation. To do so, apart from discussing the main characteristics of this family of algorithms we also look at Memetic Algorithms and the Swarm Intelligence algorithms. Fromour discussion, we see that establishing semantic borders between these algorithm families is not always easy, nor necessarily useful. It is anticipated that they will further converge as the research from these areas cross-fertilizes each other.},
    sortkey = {0798696evolutionaryoptimization},
    }
  • [DOI] Xiannian Fan, Ke Tang, and Thomas Weise. Margin-Based Over-Sampling Method for Learning From Imbalanced Datasets. In Joshua (Zhexue) Huang, Longbing Cao, and Jaideep Srivastava, editors, Proceedings of the 15th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Part II (PAKDD’11), volume 6635 of Lecture Notes in Computer Science (LNCS), pages 309-320, Shenzhen, Guangdong, China, May 24–27, 2011. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [Bibtex]
    @inproceedings{FTW2011MBAOOSFIL,
    author = {Xiannian Fan and Ke Tang and Thomas Weise},
    title = {Margin-Based Over-Sampling Method for Learning From Imbalanced Datasets},
    booktitle = {Proceedings of the 15th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Part II (PAKDD'11)},
    editor = {Joshua (Zhexue) Huang and Longbing Cao and Jaideep Srivastava},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Shenzhen, Guangdong, China},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {6635},
    pages = {309--320},
    year = {2011},
    month = {May 24--27, },
    url = {http://www.it-weise.de/documents/files/FTW2011MBAOOSFIL.pdf},
    doi = {10.1007/978-3-642-20847-8_26},
    abstract = {Learning from imbalanced datasets has drawn more and more attentions in both theoretical and practical aspects. Over-sampling is a popular and simple method for imbalanced learning. In this paper, we show that there is an inherently potential risk associated with the over-sampling algorithms in terms of the large margin principle. Then we propose a new synthetic over sampling method, named Margin-guided Synthetic Over-sampling (MSYN), to reduce this risk. The MSYN improves learning with respect to the data distributions guided by the margin-based rule. Empirical study verities the proposed analysis.},
    eiid = {20112314036487},
    sciids = {BCX89},
    sciwos = {WOS:000311907700026},
    sortkey = {0798558marginbasedoversamplingmethodfor},
    }
  • Thomas Weise. Applications of Evolutionary Algorithms. May 12, 2011. Invited presentation.
    [PDF] [Bibtex]
    @misc{W2011AOEA,
    author = {Thomas Weise},
    title = {Applications of Evolutionary Algorithms},
    address = {Jiujiang, Jiangxi, China: Jiujiang University, School of Information Science and Technology},
    year = {2011},
    month = {May 12, },
    url = {http://www.it-weise.de/documents/files/W2011AOEA.pdf},
    note = {Invited presentation.},
    sortkey = {0798546applicationsofevolutionaryalgorithms},
    }
  • [DOI] Mingxu Wan, Thomas Weise, and Ke Tang. Novel Loop Structures and the Evolution of Mathematical Algorithms. In Sara Silva, James A. Foster, Miguel Nicolau, Penousal Machado, and Mario Giacobini, editors, Proceedings of the 14th European Conference on Genetic Programming (EuroGP’11), volume 6621/2011 of Lecture Notes in Computer Science (LNCS), pages 49-60, Torino, Italy, April 27–29, 2011. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WWT2011NLSATEOMA,
    author = {Mingxu Wan and Thomas Weise and Ke Tang},
    title = {Novel Loop Structures and the Evolution of Mathematical Algorithms},
    booktitle = {Proceedings of the 14th European Conference on Genetic Programming (EuroGP'11)},
    editor = {Sara Silva and James A. Foster and Miguel Nicolau and Penousal Machado and Mario Giacobini},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Torino, Italy},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {6621/2011},
    pages = {49--60},
    year = {2011},
    month = {April 27--29, },
    url = {http://www.it-weise.de/documents/files/WWT2011NLSATEOMA.pdf},
    slides = {http://www.it-weise.de/documents/files/WWT2011NLSATEOMA_slides.pdf},
    doi = {10.1007/978-3-642-20407-4_5},
    abstract = {In this paper, we analyze the capability of Genetic Programming (GP) to synthesize non-trivial, non-approximative, and deterministic mathematical algorithms with integer-valued results. Such algorithms usually involve loop structures. We raise the question which representation for loops would be most efficient. We define five tree-based program representations which realize the concept of loops in different ways, including two novel methods which use the convergence of variable values as implicit stopping criteria. Based on experiments on four problems under three fitness functions (error sum, hit rate, constant 1) we find that GP can statistically significantly outperform random walks. Still, evolving said algorithms seems to be hard for GP and the success rates are not high. Furthermore, we found that none of the program representations could consistently outperform the others, but the two novel methods with indirect stopping criteria are utilized to a much higher degree than the other three loop instructions.},
    eiid = {20111913976760},
    sciids = {BZK01},
    sciwos = {WOS:000301802700005},
    sortkey = {0798528novelloopstructuresand},
    }
  • [DOI] Thomas Weise, Stefan Niemczyk, Raymond Chiong, and Mingxu Wan. A Framework for Multi-Model EDAs with Model Recombination. In Proceedings of the 4th European Event on Bio-Inspired Algorithms for Continuous Parameter Optimisation (EvoNUM’11), Applications of Evolutionary Computation — Proceedings of EvoApplications 2011: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Part 1 (EvoAPPLICATIONS’11), volume 6624 of Lecture Notes in Computer Science (LNCS), pages 304-313, Torino, Italy, April 27–29, 2011. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WNCW2011AFFMMEWMR,
    author = {Thomas Weise and Stefan Niemczyk and Raymond Chiong and Mingxu Wan},
    title = {A Framework for Multi-Model EDAs with Model Recombination},
    booktitle = {Proceedings of the 4th European Event on Bio-Inspired Algorithms for Continuous Parameter Optimisation (EvoNUM'11), Applications of Evolutionary Computation {--} Proceedings of EvoApplications 2011: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Part 1 (EvoAPPLICATIONS'11)},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Torino, Italy},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {6624},
    pages = {304--313},
    year = {2011},
    month = {April 27--29, },
    url = {http://www.it-weise.de/documents/files/WNCW2011AFFMMEWMR.pdf},
    slides = {http://www.it-weise.de/documents/files/WNCW2011AFFMMEWMR_slides.pdf},
    doi = {10.1007/978-3-642-20525-5_31},
    abstract = {Estimation of Distribution Algorithms (EDAs) are evolutionary optimization methods that build models which estimate the distribution of promising regions in the search space. Conventional EDAs use only one single model at a time. One way to efficiently explore multiple areas of the search space is to use multiple models in parallel. In this paper, we present a general framework for both single- and multi-model EDAs. We propose to use clustering to divide the selected individuals into different groups which are then utilized to build separate models. For the multi-model case, we introduce the concept of model recombination. This novel framework has great generality, encompassing the traditional Evolutionary Algorithm and the EDA as its extreme cases. We instantiate our framework in form of a real-valued algorithm and apply this algorithm to some well-known benchmark functions. Numerical results show that both single- and multi-model EDAs have their own strengths and weaknesses and that the multi-model EDA is able to prevent premature convergence.},
    eiid = {20112013980645},
    sciwos = {WOS:000302387400031},
    sortkey = {0798528aframeworkformultimodel},
    }
  • [DOI] Thomas Weise and Raymond Chiong. A Novel Extremal Optimization Algorithm for the Template Design Problem. International Journal of Organizational and Collective Intelligence (IJOCI), 2(2):1-17, April–June 2011.
    [Bibtex]
    @article{WR2010ANEOAFTTDP,
    author = {Thomas Weise and Raymond Chiong},
    title = {A Novel Extremal Optimization Algorithm for the Template Design Problem},
    publisher = {New York, NY, USA: Idea Group Publishing (Idea Group Inc., IGI Global)},
    journal = {International Journal of Organizational and Collective Intelligence (IJOCI)},
    number = {2},
    volume = {2},
    pages = {1--17},
    year = {2011},
    month = {April--June},
    doi = {10.4018/joci.2011040101},
    abstract = {This paper presents a novel algorithm based on extremal dynamics for tackling the template design problem, a constrained optimization problem originated from the printing industry. The template design problem involves printing several variations of a design onto one or more stencil sheets, where the aims are to minimize the number of stencils as well as the overproduction of prints of a particular design. We introduce several search operators to be used in conjunction with the proposed algorithm. Different combinations of these search operators are tested via extensive numerical experiments. The solutions found indicate that our algorithm is indeed a feasible approach for template design optimization. In particular, hybridizing it with a deterministic local search has proven to be very effective.},
    sortkey = {0798500anovelextremaloptimization},
    }
  • Thomas Weise. Illustration of Statistical Test Results for Experiment Evaluation. Technical Report, Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL), March 2, 2011.
    [PDF] [Bibtex]
    @techreport{W2011IOSTRFEE,
    author = {Thomas Weise},
    title = {Illustration of Statistical Test Results for Experiment Evaluation},
    publisher = {Germany: it-weise.de (self-published)},
    institution = {Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL)},
    year = {2011},
    month = {March 2, },
    url = {http://www.it-weise.de/documents/files/W2011IOSTRFEE.pdf},
    abstract = {In this reference document, I provide some notes on how I (personally) think that the results of statistical tests involving \ensuremath{N>2} processes could be represented in a compact and easy-to-read way. The proposed method is a directed graph acyclic graph (DAG), which is based on the fact that the outcomes of tests always are at least a strict partial order which can be visualized as DAG.},
    sortkey = {0798470illustrationofstatisticaltest},
    }
  • [DOI] Raymond Chiong and Thomas Weise. Editorial: Special Issue on Modern Search Heuristics and Applications. Evolutionary Intelligence, 4(1):1-2, January 19, 2011.
    [PDF] [Bibtex]
    @article{CW2011SIOMSHAA,
    author = {Raymond Chiong and Thomas Weise},
    title = {Editorial: Special Issue on Modern Search Heuristics and Applications},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    journal = {Evolutionary Intelligence},
    number = {1},
    volume = {4},
    pages = {1--2},
    year = {2011},
    month = {January 19, },
    url = {http://www.it-weise.de/documents/files/CW2011SIOMSHAA.pdf},
    doi = {10.1007/s12065-011-0050-7},
    eiid = {20111013720552 and IP51239219},
    sortkey = {0798421editorialspecialissueon},
    }
  • [DOI] Pu Wang, Thomas Weise, and Raymond Chiong. Novel Evolutionary Algorithms for Supervised Classification Problems: An Experimental Study. Evolutionary Intelligence, 4(1):3-16, January 12, 2011.
    [PDF] [Bibtex]
    @article{WWC2011NEAFSCPAES,
    author = {Pu Wang and Thomas Weise and Raymond Chiong},
    title = {Novel Evolutionary Algorithms for Supervised Classification Problems: An Experimental Study},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    journal = {Evolutionary Intelligence},
    number = {1},
    volume = {4},
    pages = {3--16},
    year = {2011},
    month = {January 12, },
    url = {http://www.it-weise.de/documents/files/WWC2011NEAFSCPAES.pdf},
    doi = {10.1007/s12065-010-0047-7},
    abstract = {Evolutionary Algorithms (EAs) are population-based, stochastic search algorithms that mimic natural evolution. Over the years, EAs have been successfully applied to many classification problems. In this paper, we present three novel evolutionary approaches and analyze their performances for synthesizing classifiers with EAs in supervised data mining scenarios. The first approach is based on encoding rule sets with bit string genomes, while the second one utilizes Genetic Programming (GP) to create decision trees with arbitrary expressions attached to the nodes. The novelty of these two approaches lies in the use of solutions on the Pareto front as an ensemble. The third approach, EDDIE-101, is also based on GP but uses a new, advanced fitness measure and some novel genetic operators. We compare these approaches to a number of well-known data mining methods, including C4.5 and Random-Forest, and show that the performances of our evolved classifiers can be very competitive as far as the solution quality is concerned. In addition, the proposed approaches work well across a wide range of configurations, and EDDIE-101 particularly has been highly efficient. To further evaluate the flexibility of EDDIE-101 across different problem domains, we also test it on some real financial datasets for finding investment opportunities and compare the results with those obtained using other classifiers. Numerical experiments confirm that EDDIE-101 can be successfully extended to financial forecasting.},
    eiid = {20111013720553 and IP51227209},
    sortkey = {0798414novelevolutionaryalgorithmsfor},
    }
  • [DOI] Yingxu Wang, Bernard Widrow, Bo Zhang, Witold Kinsner, Kenji Sugawara, Fuchun Sun, Jianhua Lu, Thomas Weise, and Du Zhang. Perspectives on the Field of Cognitive Informatics and Its Future Development. The International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 5(1):1-17, January–March 2011.
    [PDF] [Bibtex]
    @article{WWZKSSLWZ2011POTFOCIAIFD,
    author = {Yingxu Wang and Bernard Widrow and Bo Zhang and Witold Kinsner and Kenji Sugawara and Fuchun Sun and Jianhua Lu and Thomas Weise and Du Zhang},
    title = {Perspectives on the Field of Cognitive Informatics and Its Future Development},
    publisher = {New York, NY, USA: Idea Group Publishing (Idea Group Inc., IGI Global)},
    journal = {The International Journal of Cognitive Informatics and Natural Intelligence (IJCINI)},
    number = {1},
    volume = {5},
    pages = {1--17},
    year = {2011},
    month = {January--March},
    url = {http://www.it-weise.de/documents/files/W2010CCAEC.pdf},
    doi = {10.4018/jcini.2011010101},
    abstract = {The contemporary wonder of sciences and engineering has recently refocused on the beginning point of them: how the brain processes internal and external information autonomously and cognitively rather than imperatively as those of conventional computers. Cognitive Informatics (CI) is a transdisciplinary enquiry of computer science, information sciences, cognitive science, and intelligence science that investigates into the internal information processing mechanisms and processes of the brain and natural intelligence, as well as their engineering applications in cognitive computing. This paper reports a set of eight position statements presented in the plenary panel of IEEE ICCI{\textquoteright}10 on Cognitive Informatics and Its Future Development contributed from invited panelists who are part of the world{\textquoteright}s renowned researchers and scholars in the field of cognitive informatics and cognitive computing.},
    eiid = {20114014384631},
    inspec = {12451742},
    sortkey = {0798401perspectivesonthefield},
    }

2010

  • [DOI] Brian M. Blake, Thomas Weise, and Steffen Bleul. WSC-2010: Web Services Composition and Evaluation. In Proceedings of the IEEE International Conference on Service-Oriented Computing and Applications (SOCA’10), pages 1-4, Perth, WA, Australia, December 13–15, 2010. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{BWB2010W2WSCAE,
    author = {M. Brian Blake and Thomas Weise and Steffen Bleul},
    title = {WSC-2010: Web Services Composition and Evaluation},
    booktitle = {Proceedings of the IEEE International Conference on Service-Oriented Computing and Applications (SOCA'10)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Perth, WA, Australia},
    pages = {1--4},
    year = {2010},
    month = {December 13--15, },
    url = {http://www.it-weise.de/documents/files/BWB2010W2WSCAE.pdf},
    doi = {10.1109/SOCA.2010.5707190},
    abstract = {The Web Services Challenge (WSC) is a forum where academic and industry researchers can share experiences of developing tools that automate the integration of web services. In the sixth year (i.e. WSC-10) of the Web Services Challenge, software platforms will extend their solutions to the several composition challenges. Again this year, requests and results will be transmitted within SOAP messages. Semantics will be represented as ontologies written in OWL, services will be represented in WSDL, and service orchestrations will be represented in WSBPEL. Nonfunctional properties (Quality of Service) of a service will be represented using WSLA format.},
    eiid = {20111113747701},
    sortkey = {0798381wsc2010webservicescomposition},
    }
  • [DOI] Xin Yu, Thomas Weise, Ke Tang, and Steffen Bleul. QoS-aware Semantic Web Service Composition for SOAs. In Proceedings of the IEEE International Conference on Service-Oriented Computing and Applications (SOCA’10), Perth, WA, Australia, December 13–15, 2010. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [Bibtex]
    @inproceedings{XWTB2010QASWSCFS,
    author = {Xin Yu and Thomas Weise and Ke Tang and Steffen Bleul},
    title = {QoS-aware Semantic Web Service Composition for SOAs},
    booktitle = {Proceedings of the IEEE International Conference on Service-Oriented Computing and Applications (SOCA'10)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Perth, WA, Australia},
    year = {2010},
    month = {December 13--15, },
    doi = {10.1109/SOCA.2010.5707192},
    abstract = {QoS-aware semantic web service composition concerns finding services from a repository to accomplish a specified task while meeting the Quality of Service (QoS) demands. The composition task is defined in form of a composition request which contains a set of available input parameters and wanted output parameters. If the input parameters given in the request are provided, the services of this set can be executed. Concepts from an ontology describing their semantics are passed to the composition engine. The composer works on a repository of services which posses QoS features. The parameters of these services are semantically annotated in the same way as the parameters in the request. The composer then finds a set of services fulfilling the request. In this paper, we introduce our improved composition system with which we will take part in the Web Service Challenge 2010.},
    eiid = {20111113747703},
    inspec = {11795104},
    sortkey = {0798381qosawaresemanticwebservice},
    }
  • [DOI] Wenxiang Chen, Thomas Weise, Zhenyu Yang, and Ke Tang. Large-Scale Global Optimization Using Cooperative Coevolution with Variable Interaction Learning. In Robert Schaefer, Carlos Cotta, Joanna Ko l, and Günter Rudolph, editors, Proceedings of the 11th International Conference on Parallel Problem Solving From Nature, Part 2 (PPSN’10-2), volume 6239 of Lecture Notes in Computer Science (LNCS), pages 300-309, Kraków, Poland: AGH University of Science and Technology, September 11–15, 2010. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [PPT] [Bibtex]
    @inproceedings{CWYT2010LSGOUCCWVIL,
    author = {Wenxiang Chen and Thomas Weise and Zhenyu Yang and Ke Tang},
    title = {Large-Scale Global Optimization Using Cooperative Coevolution with Variable Interaction Learning},
    booktitle = {Proceedings of the 11th International Conference on Parallel Problem Solving From Nature, Part 2 (PPSN'10-2)},
    editor = {Robert Schaefer and Carlos Cotta and Joanna Ko{\l}odziej and G{\"{u}}nter Rudolph},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Krak{\'{o}}w, Poland: AGH University of Science and Technology},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {6239},
    pages = {300--309},
    year = {2010},
    month = {September 11--15, },
    url = {http://www.it-weise.de/documents/files/CWYT2010LSGOUCCWVIL.pdf},
    slides = {http://mail.ustc.edu.cn/~chenwx/slides2010PPSN.pdf},
    poster = {http://mail.ustc.edu.cn/~chenwx/ppsn2010Poster.pdf},
    doi = {10.1007/978-3-642-15871-1_31},
    abstract = {In recent years, Cooperative Coevolution (CC) was proposed as a promising framework for tackling high-dimensional optimization problems. The main idea of CC-based algorithms is to discover which decision variables, i.e, dimensions, of the search space interact. Non-interacting variables can be optimized as separate problems of lower dimensionality. Interacting variables must be grouped together and optimized jointly. Early research in this area started with simple attempts such as one-dimension based and splitting-in-half methods. Later, more efficient algorithms with new grouping strategies, such as DECCG and MLCC, were proposed. However, those grouping strategies still cannot sufficiently adapt to different group sizes. In this paper, we propose a new CC framework named Cooperative Coevolution with Variable Interaction Learning (CCVIL), which initially considers all variables as independent and puts each of them into a separate group. Iteratively, it discovers their relations and merges the groups accordingly. The efficiency of the newly proposed framework is evaluated on the set of large-scale optimization benchmarks.},
    eiid = {20104513369063},
    sciids = {BTC53},
    sciwos = {WOS:000286453000031},
    sortkey = {0798280largescaleglobaloptimizationusing},
    }
  • [DOI] Pu Wang, Edward P. K. Tsang, Thomas Weise, Ke Tang, and Xin Yao. Using GP to Evolve Decision Rules for Classification in Financial Data Sets. In Fuchun Sun, Yingxu Wang, Jianhua Lu, Bo Zhang, Witold Kinsner, and Lotfi A. Zadeh, editors, Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI’10), pages 722-727, Beijing, China: Tsinghua University, July 7–9, 2010. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WTWTY2010UGTEDRFCIFDS,
    author = {Pu Wang and Edward P. K. Tsang and Thomas Weise and Ke Tang and Xin Yao},
    title = {Using GP to Evolve Decision Rules for Classification in Financial Data Sets},
    booktitle = {Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI'10)},
    editor = {Fuchun Sun and Yingxu Wang and Jianhua Lu and Bo Zhang and Witold Kinsner and Lotfi A. Zadeh},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Tsinghua University},
    pages = {722--727},
    year = {2010},
    month = {July 7--9, },
    url = {http://www.it-weise.de/documents/files/WTWTY2010UGPTEDRFCIFDS.pdf},
    slides = {http://www.it-weise.de/documents/files/WTWTY2010UGPTEDRFCIFDS_slides.pdf},
    doi = {10.1109/COGINF.2010.5599820},
    abstract = {Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic Programming process itself is still very inefficient and that further improvements are necessary if we want this application of GP to become successful.},
    eiid = {20105013469298},
    inspec = {11579674},
    sortkey = {0798210usinggptoevolve},
    }
  • [DOI] Yingxu Wang, Bernard Widrow, Bo Zhang, Witold Kinsner, Kenji Sugawara, Fuchun Sun, Thomas Weise, Yixin Zhong, and Du Zhang. Perspectives on Cognitive Informatics and Its Future Development: Summary of Plenary Panel II of IEEE ICCI’10. In Fuchun Sun, Yingxu Wang, Jianhua Lu, Bo Zhang, Witold Kinsner, and Lotfi A. Zadeh, editors, Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI’10), pages 17-25, Beijing, China: Tsinghua University, July 7–9, 2010. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{WWZKSSWZZ2010POCIAIFDSOPPIIOII,
    author = {Yingxu Wang and Bernard Widrow and Bo Zhang and Witold Kinsner and Kenji Sugawara and Fuchun Sun and Thomas Weise and Yixin Zhong and Du Zhang},
    title = {Perspectives on Cognitive Informatics and Its Future Development: Summary of Plenary Panel II of IEEE ICCI'10},
    booktitle = {Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI'10)},
    editor = {Fuchun Sun and Yingxu Wang and Jianhua Lu and Bo Zhang and Witold Kinsner and Lotfi A. Zadeh},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Tsinghua University},
    pages = {17--25},
    year = {2010},
    month = {July 7--9, },
    url = {http://www.it-weise.de/documents/files/WWZKSSWZZ2010POCIAIFDSOPPIIOII.pdf},
    doi = {10.1109/COGINF.2010.5599693},
    abstract = {The contemporary wonder of sciences and engineering has recently refocused on the beginning point of them: how the brain processes internal and external information autonomously and cognitively rather than imperatively as those of conventional computers. Cognitive Informatics (CI) is a transdisciplinary enquiry of computer science, information sciences, cognitive science, and intelligence science that investigates into the internal information processing mechanisms and processes of the brain and natural intelligence, as well as their engineering applications in cognitive computing. This paper reports a set of 9 position statements presented in the plenary panel of ICCI'10 on Cognitive Informatics and Its Future Development contributed from invited panelists who are part of the world's renowned researchers and scholars in the field of cognitive informatics and cognitive computing.},
    eiid = {20105013469178},
    sortkey = {0798210perspectivesoncognitiveinformatics},
    }
  • [DOI] Thomas Weise and Raymond Chiong. Evolutionary Data Mining Approaches for Rule-based and Tree-based Classifiers. In Fuchun Sun, Yingxu Wang, Jianhua Lu, Bo Zhang, Witold Kinsner, and Lotfi A. Zadeh, editors, Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI’10), pages 696-703, Beijing, China: Tsinghua University, July 7–9, 2010. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WC2010EDMAFRBATBC,
    author = {Thomas Weise and Raymond Chiong},
    title = {Evolutionary Data Mining Approaches for Rule-based and Tree-based Classifiers},
    booktitle = {Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI'10)},
    editor = {Fuchun Sun and Yingxu Wang and Jianhua Lu and Bo Zhang and Witold Kinsner and Lotfi A. Zadeh},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Beijing, China: Tsinghua University},
    pages = {696--703},
    year = {2010},
    month = {July 7--9, },
    url = {http://www.it-weise.de/documents/files/WC2010EDMAFRBATBC.pdf},
    slides = {http://www.it-weise.de/documents/files/WC2010EDMAFRBATBC_slides.pdf},
    doi = {10.1109/COGINF.2010.5599821},
    abstract = {Data mining is an important process, with applications found in many business, science and industrial problems. While a wide variety of algorithms have already been proposed in the literature for classification tasks in large data sets, and the majority of them have been proven to be very effective, not all of them are flexible and easily extensible. In this paper, we introduce two new approaches for synthesizing classifiers with Evolutionary Algorithms (EAs) in supervised data mining scenarios. The first method is based on encoding rule sets with bit string genomes and the second one utilizes Genetic Programming to create decision trees with arbitrary expressions attached to the nodes. Comparisons with some sophisticated standard approaches, such as C4.5 and Random-Forest, show that the performance of the evolved classifiers can be very competitive. We further demonstrate that both proposed approaches work well across different configurations of the EAs.},
    eiid = {20105013469299},
    inspec = {11579675},
    sortkey = {0798210evolutionarydataminingapproaches},
    }
  • [DOI] Thomas Weise, Li Niu, and Ke Tang. AOAB — Automated Optimization Algorithm Benchmarking. In Black Box Optimization Benchmarking (BBOB’10), Companion Publication of the Genetic and Evolutionary Computation Conference (GECCO’10 Companion), pages 1479-1486, Portland, OR, USA: Portland Marriott Downtown Waterfront Hotel, July 7, 2010. New York, NY, USA: ACM Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WNT2010AOABAOAB,
    author = {Thomas Weise and Li Niu and Ke Tang},
    title = {AOAB {--} Automated Optimization Algorithm Benchmarking},
    booktitle = {Black Box Optimization Benchmarking (BBOB'10), Companion Publication of the Genetic and Evolutionary Computation Conference (GECCO'10 Companion)},
    publisher = {New York, NY, USA: ACM Press},
    address = {Portland, OR, USA: Portland Marriott Downtown Waterfront Hotel},
    pages = {1479--1486},
    year = {2010},
    month = {July 7, },
    url = {http://www.it-weise.de/documents/files/WNT2010AOABAOAB.pdf},
    slides = {http://www.it-weise.de/documents/files/WNT2010AOABAOAB_slides.pdf},
    doi = {10.1145/1830761.1830763},
    abstract = {In this paper we present AOAB, the Automated Optimization Algorithm Benchmarking system. AOAB can be used to automatically conduct experiments with numerical optimization algorithms by applying them to different benchmarks with different parameter settings. Based on the results, AOAB can automatically perform comparisons between different algorithms and settings. It can aid the researcher to identify trends for good parameter settings and to find which algorithms are suitable for which type of problem.{\newline}We introduce the system structure of AOAB (the server and the graphical client interface), define the way in which optimizers and benchmark functions can be implemented for the use in AOAB, and conduct an illustrative example experiment with our system: a comparison between Random Search and two Hill Climbers.},
    eiid = {20103513190754},
    sciids = {BGA53},
    sciwos = {WOS:000322071400001},
    sortkey = {0798210aoabautomatedoptimization},
    }
  • [DOI] Yu Wang, Bin Li, and Thomas Weise. Estimation of Distribution and Differential Evolution Cooperation for Large Scale Economic Load Dispatch Optimization of Power Systems. Information Sciences — Informatics and Computer Science Intelligent Systems Applications: An International Journal, 180(12):2405-2420, June 2010.
    [PDF] [Bibtex]
    @article{WLW2010EODADECFLSELDOOPS,
    author = {Yu Wang and Bin Li and Thomas Weise},
    title = {Estimation of Distribution and Differential Evolution Cooperation for Large Scale Economic Load Dispatch Optimization of Power Systems},
    publisher = {Essex, UK: Elsevier Science Publishers B.V.},
    journal = {Information Sciences {--} Informatics and Computer Science Intelligent Systems Applications: An International Journal},
    number = {12},
    volume = {180},
    pages = {2405--2420},
    year = {2010},
    month = {June},
    url = {http://www.it-weise.de/documents/files/WLW2010EODADECFLSELDOOPS.pdf},
    doi = {10.1016/j.ins.2010.02.015},
    abstract = {Economic Load Dispatch (ELD) is an important and difficult optimization problem in power system planning. This article aims at addressing two practically important issues related to ELD optimization: (1) analyzing the ELD problem from the perspective of evolutionary optimization; (2) developing effective algorithms for ELD problems of large scale. The first issue is addressed by investigating the fitness landscape of ELD problems with the purpose of estimating the expected performance of different approaches. To address the second issue, a new algorithm named ''Estimation of Distribution and Differential Evolution Cooperation'' (ED-DE) is proposed, which is a serial hybrid of two effective evolutionary computation (EC) techniques: estimation of distribution and differential evolution. The advantages of ED-DE over the previous ELD optimization algorithms are experimentally testified on ELD problems with the number of generators scaling from 10 to 160. The best solution records of classical 13 and 40-generator ELD problems with valve points, and the best solution records of 10, 20, 40, 80 and 160-generator ELD problems with both valve points and multiple fuels are updated in this work. To further evaluate the efficiency and effectiveness of ED-DE, we also compare it with other state-of-the-art evolutionary algorithms (EAs) on typical function optimization tasks.},
    eiid = {20101412821019},
    sciids = {593PM},
    sciwos = {WOS:000277471400005},
    sortkey = {0798169estimationofdistributionand},
    }
  • Stefan Niemczyk and Thomas Weise. A General Framework for Multi-Model Estimation of Distribution Algorithms. Technical Report, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, March 10, 2010.
    [PDF] [PPT] [Bibtex]
    @techreport{NW2010AGFFMMEODA,
    author = {Stefan Niemczyk and Thomas Weise},
    title = {A General Framework for Multi-Model Estimation of Distribution Algorithms},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2010},
    month = {March 10, },
    url = {http://www.it-weise.de/documents/files/NW2010AGFFMMEODA.pdf},
    slides = {http://www.it-weise.de/documents/files/NW2010AGFFMMEODA_slides.pdf},
    abstract = {This technical report introduces an extension for Estimation of Distribution Algorithms (EDAs). EDAs are evolutionary optimization methods that try to build models which estimate the distribution of promising regions in the search space. Traditional EDAs use only one single model at a time. However, a single (univariate) model can only represent a single area of the search space. After the algorithm has decided for one region of the search space, the probability that the algorithm can leave this area is very small and explore different parts of the search space are thus rarely investigated. Such an EDA will not sample new individuals in the outside from the learned model.{\newline}One way to explore multiple areas of the search space is to use multiple models. Our proposed multi-model EDA uses clustering to group similar individuals. For each such group, one model is created. Additional, we introduce a model recombination operator which uses these models to create additional ones.{\newline}The main idea of our approach is to prevent premature convergence by using multiple models. We suppose that, if multiple areas are explored at the same time, the chance to find the area in the search space which contains the global optimum is higher. By crossing different models, the algorithm gets an additional degree of freedom. By choosing a recom- bination good operator, we assume that a higher degree of adaptation to the optimization problem can be reached.{\newline}The multi-model EDA can be seen as a general algorithm model which unites the idea of traditional Genetic Algorithms (GAs) and the EDA. Indeed, these two methods can be considered as its extreme cases: If each individual is treated as one single model, our algo- rithm becomes a GA. If all individual are used to construct one single model, the algorithm becomes a regular EDA.},
    sortkey = {0798081ageneralframeworkfor},
    }
  • Ke Tang, Xiaodong Li, Ponnuthurai Nagaratnam Suganthan, Zhenyu Yang, and Thomas Weise. Benchmark Functions for the CEC’2010 Special Session and Competition on Large-Scale Global Optimization. Technical Report, Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL), January 8, 2010.
    [PDF] [PPT] [Bibtex]
    @techreport{TLSYW2010BFFTC2SSACOLSGO,
    author = {Ke Tang and Xiaodong Li and Ponnuthurai Nagaratnam Suganthan and Zhenyu Yang and Thomas Weise},
    title = {Benchmark Functions for the CEC'2010 Special Session and Competition on Large-Scale Global Optimization},
    institution = {Hefei, Anhui, China: University of Science and Technology of China (USTC), School of Computer Science and Technology, Nature Inspired Computation and Applications Laboratory (NICAL)},
    year = {2010},
    month = {January 8, },
    url = {http://www.it-weise.de/documents/files/TLSYW2009BFFTCSSACOLSGO.pdf},
    slides = {http://www.it-weise.de/documents/files/TLSYW2009BFFTCSSACOLSGO_slides.pdf},
    abstract = {In the past decades, different kinds of metaheuristic optimization algorithms [1, 2] have been developed; Simulated Annealing (SA) [3, 4], Evolutionary Algorithms (EAs) [5-7], Differential Evolution (DE) [8, 9], Particle Swarm Optimization (PSO) [10, 11], Ant Colony Optimization (ACO) [12, 13], and Estimation of Distribution Algorithms (EDAs) [14, 15] are just a few of them. These algorithms have shown excellent search abilities but often lose their efficacy when applied to large and complex problems, e.g., problem instances with high dimensions, such as those with more than one hundred decision variables. Many optimization methods suffer from the ``curse of dimensionality`` [16, 17], which implies that their performance deteriorates quickly as the dimensionality of the search space increases. The reasons for this phenomenon appear to be two-fold. First, the solution space of a problem often increases exponentially with the problem dimension [16, 17] and more efficient search strategies are required to explore all promising regions within a given time budget. Second, also the characteristics of a problem may change with the scale. Rosenbrock{\textquoteright}s function [18] (see also Section 2.6), for instance, is unimodal for two dimension but becomes multimodal for higher ones [19]. Because of such a worsening of the features of an optimization problem resulting from an increase in scale, a previously successful search strategy may no longer be capable of finding the optimal solution. Historically, scaling EAs to large-scale problems has attracted much interest, including both theoretical and practical studies. The earliest practical approach might be parallelizing an existing EA [20-22]. Later, cooperative coevolution appeared as another promising method [23, 24]. However, existing works on this topic are often limited to test problems used in individual studies and a systematic evaluation platform is still not available in literature for comparing the scalability of different EAs. This report aims to contribute to solving this problem. In particular, we provide a suite of benchmark functions for large-scale numerical optimization.},
    sortkey = {0798013benchmarkfunctionsforthe},
    }

2009

  • [DOI] Raymond Chiong, Thomas Weise, and Bee Theng Lau. Template Design using Extremal Optimization with Multiple Search Operators. In Nanna Suryana Herman, Siti Mariyam Shamsuddin, and Ajith Abraham, editors, International Conference on SOft Computing and PAttern Recognition (SoCPaR’09), pages 202-207, Malacca, Malaysia: Melaka International Trade Centre (MITC), December 4–7, 2009. Piscataway, NJ, USA: IEEE (Institute of Electrical and Electronics Engineers).
    [PDF] [PPT] [Bibtex]
    @inproceedings{CW2009TDUEOWMSO,
    author = {Raymond Chiong and Thomas Weise and Bee Theng Lau},
    title = {Template Design using Extremal Optimization with Multiple Search Operators},
    booktitle = {International Conference on SOft Computing and PAttern Recognition (SoCPaR'09)},
    editor = {Nanna Suryana Herman and Siti Mariyam Shamsuddin and Ajith Abraham},
    publisher = {Piscataway, NJ, USA: IEEE (Institute of Electrical and Electronics Engineers)},
    address = {Malacca, Malaysia: Melaka International Trade Centre (MITC)},
    pages = {202--207},
    year = {2009},
    month = {December 4--7, },
    url = {http://www.it-weise.de/documents/files/CWL2009TDUEOWMSO.pdf},
    slides = {http://www.it-weise.de/documents/files/CWL2009TDUEOWMSO_pres.pdf},
    doi = {10.1109/SoCPaR.2009.49},
    abstract = {The template design problem is a constrained optimization problem originated from the printing industry. It involves printing several variations of a design onto one or more stencil sheets, where the aims are to minimize the number of stencils as well as the overproduction of prints of a particular design. Over the years, exact solution methods have been used to solve the problem. These methods could be useful for small to moderate-sized problem instances. However, when the problem instances are huge, the search space may easily grow too large for the systematic approaches. To date, no meta-heuristic or soft computing techniques have been used for this problem. In this paper, we propose the use of Extremal Optimization (EO) with multiple search operators for solving the template design problem. Different combinations of the search operators are tested via extensive numerical experiments. The results show that EO is indeed a feasible approach for template design optimization. The hybridization of EO with a deterministic local search has proven to be particularly effective.},
    eiid = {20101012758280},
    sciids = {BOP29},
    sciwos = {WOS:000277207700035},
    inspec = {11050930},
    sortkey = {0797975templatedesignusingextremal},
    }
  • [DOI] Thomas Weise, Alexander Podlich, and Christian Gorldt. Solving Real-World Vehicle Routing Problems with Evolutionary Algorithms. In Raymond Chiong and Sandeep Dhakal, editors, Natural Intelligence for Scheduling, Planning and Packing Problems, volume 250 of Studies in Computational Intelligence, chapter 2, pages 29-53. Berlin/Heidelberg: Springer-Verlag, October 2009.
    [PDF] [Bibtex]
    @incollection{WPG2009SRWVRPWEA,
    author = {Thomas Weise and Alexander Podlich and Christian Gorldt},
    title = {Solving Real-World Vehicle Routing Problems with Evolutionary Algorithms},
    booktitle = {Natural Intelligence for Scheduling, Planning and Packing Problems},
    editor = {Raymond Chiong and Sandeep Dhakal},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    series = {Studies in Computational Intelligence},
    volume = {250},
    chapter = {2},
    pages = {29--53},
    year = {2009},
    month = {October},
    url = {http://www.it-weise.de/documents/files/WPG2009SRWVRPWEA.pdf},
    doi = {10.1007/978-3-642-04039-9_2},
    abstract = {In this chapter, we present the freight transportation planning component of the in.west project. This system uses an Evolutionary Algorithm with intelligent search operations in order to achieve a high utilization of resources and a minimization of the distance travelled by freight carriers in real-world scenarios. We test our planner rigorously with real-world data and obtain substantial improvements when compared to the original freight plans. Additionally, different settings for the Evolutionary Algorithm are studied with further experiments and their utility is verified with statistical tests.},
    sortkey = {0797904solvingrealworldvehiclerouting},
    }
  • [DOI] Thomas Weise and Raymond Chiong. Evolutionary Approaches and Their Applications to Distributed Systems. In Raymond Chiong, editor, Intelligent Systems for Automated Learning and Adaptation: Emerging Trends and Applications, chapter 6, pages 114-149. Hershey, PA, USA: Information Science Reference, September 2009.
    [Bibtex]
    @incollection{WC2009EAATATDS,
    author = {Thomas Weise and Raymond Chiong},
    title = {Evolutionary Approaches and Their Applications to Distributed Systems},
    booktitle = {Intelligent Systems for Automated Learning and Adaptation: Emerging Trends and Applications},
    editor = {Raymond Chiong},
    publisher = {Hershey, PA, USA: Information Science Reference},
    chapter = {6},
    pages = {114--149},
    year = {2009},
    month = {September},
    doi = {10.4018/978-1-60566-798-0.ch006},
    abstract = {The ubiquitous presence of distributed systems has drastically changed the way the world interacts, and impacted not only the economics and governance but also the society at large. It is therefore important for the architecture and infrastructure within the distributed environment to be continuously renewed in order to cope with the rapid changes driven by the innovative technologies. However, many problems in distributed computing are either of dynamic nature, large scale, NP complete, or a combination of any of these. In most cases, exact solutions are hardly found. As a result, a number of intelligent nature-inspired algorithms have been used recently, as these algorithms are capable of achieving good quality solutions in reasonable computational time. Among all the nature-inspired algorithms, evolutionary algorithms are considerably the most extensively applied ones. This chapter presents a systematic review of evolutionary algorithms employed to solve various problems related to distributed systems. The review is aimed at providing an insight of evolutionary approaches, in particular genetic algorithms and genetic programming, in solving problems in five different areas of network optimization: network topology, routing, protocol synthesis, network security, and parameter settings and configuration. Some interesting applications from these areas will be discussed in detail with the use of illustrative examples.},
    sortkey = {0797871evolutionaryapproachesandtheir},
    }
  • [DOI] Srividya Kona, Ajay Bansal, Brian M. Blake, Steffen Bleul, and Thomas Weise. WSC-2009: A Quality of Service-Oriented Web Services Challenge. In Birgit Hofreiter, editor, Proceedings of the 11th IEEE Conference on Commerce and Enterprise Computing (CEC’09), pages 487-490, Vienna, Austria: Vienna University of Technology, July 20–23, 2009. Piscataway, NJ, USA: IEEE Computer Society and Red Hook, NY, USA: Curran Associates, Inc..
    [PDF] [Bibtex]
    @inproceedings{KBBBW2009W2AQOSOWSC,
    author = {Srividya Kona and Ajay Bansal and M. Brian Blake and Steffen Bleul and Thomas Weise},
    title = {WSC-2009: A Quality of Service-Oriented Web Services Challenge},
    booktitle = {Proceedings of the 11th IEEE Conference on Commerce and Enterprise Computing (CEC'09)},
    editor = {Birgit Hofreiter},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society and Red Hook, NY, USA: Curran Associates, Inc.},
    address = {Vienna, Austria: Vienna University of Technology},
    pages = {487--490},
    year = {2009},
    month = {July 20--23, },
    url = {http://www.it-weise.de/documents/files/KBBSW2009WAQOSOWSC.pdf},
    doi = {10.1109/CEC.2009.80},
    abstract = {With the growing acceptance of service-oriented computing, an emerging area of research is the investigation of technologies that will enable the discovery and composition of web services. The Web Services Challenge (WSC) is a forum where academic and industry researchers can share experiences of developing tools that automate the integration of web services. In the fifth year (i.e. WSC-09) of the Web Services Challenge, software platforms will address several new composition challenges. Requests and results will be transmitted within SOAP messages. Semantics will be represented as ontologies written in OWL, services will be represented in WSDL, and service orchestrations will be represented in WSBPEL. In addition, non-functional properties (Quality of Service) of a service will be represented using WSLA format.},
    eiid = {20094712467206},
    inspec = {10839134},
    sortkey = {0797826wsc2009aqualityof},
    }
  • [DOI] Thomas Weise and Michael Zapf. Evolving Distributed Algorithms with Genetic Programming: Election. In Lihong Xu, Erik D. Goodman, and Yongsheng Ding, editors, Proceedings of the First ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC’09), pages 577-584, Shanghai, China: Hua-Ting Hotel {&} Towers, June 12–14, 2009. New York, NY, USA: ACM Press.
    [PDF] [Bibtex]
    @inproceedings{WZ2009EDAWGPE,
    author = {Thomas Weise and Michael Zapf},
    title = {Evolving Distributed Algorithms with Genetic Programming: Election},
    booktitle = {Proceedings of the First ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC'09)},
    editor = {Lihong Xu and Erik D. Goodman and Yongsheng Ding},
    publisher = {New York, NY, USA: ACM Press},
    address = {Shanghai, China: Hua-Ting Hotel {\&} Towers},
    pages = {577--584},
    year = {2009},
    month = {June 12--14, },
    url = {http://www.it-weise.de/documents/files/WZ2009EDAWGPE.pdf},
    doi = {10.1145/1543834.1543913},
    abstract = {In this paper, we present a detailed analysis of the application of Genetic Programming to the evolution of distributed algorithms. This research field has many facets which make it especially difficult. These aspects are discussed and countermeasures are provided. Six different Genetic Programming approaches (SGP, eSGP, LGP, RBGP, eRBGP, and Fraglets) are applied to the election problem as case study utilizing these countermeasures. The results of the experiments are nalyzed statistically and discussed thoroughly.},
    eiid = {20093012219539},
    sciids = {BRC96},
    sciwos = {WOS:000282382900079},
    sortkey = {0797785evolvingdistributedalgorithmswith},
    }
  • [DOI] Diana Elena Comes, Steffen Bleul, Thomas Weise, and Kurt Geihs. A Flexible Approach for Business Processes Monitoring. In Twittie Senivongse and Gina Oliveira, editors, 9th IFIP WG 6.1 International Conference on Distributed Applications and Interoperable Systems (DAIS’09), volume 5523/2009 of Lecture Notes in Computer Science (LNCS), pages 116-128, Lisbon, Portugal, June 9–11, 2009. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{CBWG2009AFAFBPM,
    author = {Diana Elena Comes and Steffen Bleul and Thomas Weise and Kurt Geihs},
    title = {A Flexible Approach for Business Processes Monitoring},
    booktitle = {9th IFIP WG 6.1 International Conference on Distributed Applications and Interoperable Systems (DAIS'09)},
    editor = {Twittie Senivongse and Gina Oliveira},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Lisbon, Portugal},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {5523/2009},
    pages = {116--128},
    year = {2009},
    month = {June 9--11, },
    url = {http://www.it-weise.de/documents/files/CBTG2009AFAFBPM.pdf},
    slides = {http://www.it-weise.de/documents/files/CBTG2009AFAFBPM_pres.pdf},
    doi = {10.1007/978-3-642-02164-0_9},
    abstract = {Business processes and their implementation as Web Service Compositions are not only dependent on Web Services and partners all over the Internet, but also on their failsafe execution. Service providers have to obligate their services to perform according to negotiated Quality of Service (QoS) parameters. For example, response time and throughput are important parameters to achieve fast and efficient services. Overloaded or failing services may compromise the reliability and execution of whole enterprise processes.{\newline}In this paper we introduce a flexible monitoring approach for the measurement of QoS in BPEL (Business Process Execution Language) processes. We propose a generic algorithm for QoS aggregation in BPEL processes. The novel generic aggregation algorithm applies customized aggregation functions for QoS dimensions. Furthermore, we present a BPEL monitoring system which supports ad-hoc sensor deployment and efficient runtime and offline data aggregation not only for whole process descriptions but also sections inside service processes.},
    eiid = {20093412265790},
    sciids = {BKH10},
    sciwos = {WOS:000268061500009},
    sortkey = {0797782aflexibleapproachfor},
    }
  • Thomas Weise, Alexander Podlich, Manfred Menze, and Christian Gorldt. Optimierte Güterverkehrsplanung mit Evolutionären Algorithmen. Industrie Management — Zeitschrift für industrielle Geschäftsprozesse, 10(3):37-40, June 2, 2009.
    [PDF] [Bibtex]
    @article{WPRGG2009OGMEA,
    author = {Thomas Weise and Alexander Podlich and Manfred Menze and Christian Gorldt},
    title = {Optimierte G{\"{u}}terverkehrsplanung mit Evolution{\"{a}}ren Algorithmen},
    publisher = {Berlin, Germany: GITO mbH {--} Verlag f{\"{u}}r Industrielle Informationstechnik und Organisation},
    journal = {Industrie Management {--} Zeitschrift f{\"{u}}r industrielle Gesch{\"{a}}ftsprozesse},
    number = {3},
    volume = {10},
    pages = {37--40},
    year = {2009},
    month = {June 2, },
    url = {http://www.logistics.de/logistik/branchen.nsf/D4FF2D93CA69B47FC12575CF004870C8/$File/gueterverkehrsplanung\_optimierung\_algorithmen\_weise\_podlich\_menze\_gorldt\_gitopdf.pdf},
    abstract = {In diesem Beitrag wird ein Ansatz der Frachttransportplanung mithilfe von evolution{\"{a}}ren Algorithmen vorgestellt. Ziel ist es, eine Entscheidungsunterst{\"{u}}tzung im Bereich der Transportplanung zu schaffen um die Disponenten bei der t{\"{a}}glichen Planung zu unterst{\"{u}}tzen. Ein wichtiges Zielkriterium ist dabei m{\"{o}}glichst umweltschonende Transporte zu disponieren, um so z.B. die Transportleistung (km) zu minimieren. Der in diesem Beitrag vorgestellte Prototyp wurde mit realen Daten der DHL auf die Eignung in der Transportplanung getestet. Die Ergebnisse der Berechnung werden dabei mit den realen Frachtpl{\"{a}}nen verglichen. Weiterhin werden unterschiedliche Einstellungen f{\"{u}}r den evolution{\"{a}}ren Algorithmus experimentell untersucht und deren Nutzbarkeit durch statistische Tests verifiziert.},
    sortkey = {0797775optimiertegterverkehrsplanungmitevolutionren},
    }
  • Thomas Weise. Evolving Distributed Algorithms with Genetic Programming. PhD thesis, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, May 4, 2009. Won the Dissertation Award of The Association of German Engineers (Verein Deutscher Ingenieure, VDI).
    [PDF] [PPT] [Bibtex]
    @phdthesis{W2009DISS,
    author = {Thomas Weise},
    title = {Evolving Distributed Algorithms with Genetic Programming},
    school = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2009},
    month = {May 4, },
    url = {http://www.it-weise.de/documents/files/W2009DISS.pdf},
    slides = {http://www.it-weise.de/documents/files/W2009DISS_slides.pdf},
    note = {Won the Dissertation Award of The Association of German Engineers (Verein Deutscher Ingenieure, VDI).},
    abstract = {Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility.{\newline}Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions.{\newline}The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior.{\newline}In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers.{\newline}Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.},
    committeeMember = {Kurt Geihs and Christian F. Tschudin and Birgit {Vogel-Heuser} and Albert Z{\"{u}}ndorf},
    supervisor = {Kurt Geihs},
    urn = {urn:nbn:de:hebis:34-2009051127217},
    sortkey = {0797744evolvingdistributedalgorithmswith},
    }
  • [DOI] Thomas Weise, Michael Zapf, Raymond Chiong, and Antonio Jesús Nebro Urbaneja. Why is optimization difficult?. In Raymond Chiong, editor, Nature-Inspired Algorithms for Optimisation, volume 193/2009 of Studies in Computational Intelligence, chapter 1, pages 1-50. Berlin/Heidelberg: Springer-Verlag, April 30, 2009.
    [PDF] [Bibtex]
    @incollection{WZCN2009WIOD,
    author = {Thomas Weise and Michael Zapf and Raymond Chiong and Antonio Jes{\'{u}}s {Nebro Urbaneja}},
    title = {Why is optimization difficult?},
    booktitle = {Nature-Inspired Algorithms for Optimisation},
    editor = {Raymond Chiong},
    publisher = {Berlin/Heidelberg: Springer-Verlag},
    series = {Studies in Computational Intelligence},
    volume = {193/2009},
    chapter = {1},
    pages = {1--50},
    year = {2009},
    month = {April 30, },
    url = {http://www.it-weise.de/documents/files/WZCN2009WIOD.pdf},
    doi = {10.1007/978-3-642-00267-0_1},
    abstract = {This chapter aims to address some of the fundamental issues that are often encountered in optimization problems, making them difficult to solve. These issues include premature convergence, ruggedness, causality, deceptiveness, neutrality, epistasis, robustness, overfitting, oversimplification, multi-objectivity, dynamic fitness, the No Free Lunch Theorem, etc. We explain why these issues make optimization problems hard to solve and present some possible countermeasures for dealing with them. By doing this, we hope to help both practitioners and fellow researchers to create more efficient optimization applications and novel algorithms.},
    sortkey = {0797737whyisoptimizationdifficult},
    }
  • [DOI] Thomas Weise, Alexander Podlich, Kai Reinhard, Christian Gorldt, and Kurt Geihs. Evolutionary Freight Transportation Planning. In Mario Giacobini, Penousal Machado, Anthony Brabazon, Jon McCormack, Stefano Cagnoni, Michael O’Neill, Gianni A. Di Caro, Ferrante Neri, Anikó Ekárt, Mike Preuß, Anna Isabel Esparcia-Alcázar, Franz Rothlauf, Muddassar Farooq, Ernesto Tarantino, Andreas Fink, and Shengxiang Yang, editors, Applications of Evolutionary Computing — Proceedings of EvoWorkshops 2009: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG (EvoWorkshops’09), volume 5484/2009 of Lecture Notes in Computer Science (LNCS), pages 768-777, Tübingen, Germany: Eberhard-Karls-Universität Tübingen, Fakultät für Informations- und Kognitionswissenschaften, April 15–17, 2009. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WPRGG2009EFTP,
    author = {Thomas Weise and Alexander Podlich and Kai Reinhard and Christian Gorldt and Kurt Geihs},
    title = {Evolutionary Freight Transportation Planning},
    booktitle = {Applications of Evolutionary Computing {--} Proceedings of EvoWorkshops 2009: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG (EvoWorkshops'09)},
    editor = {Mario Giacobini and Penousal Machado and Anthony Brabazon and Jon McCormack and Stefano Cagnoni and Michael {O'Neill} and Gianni A. {Di Caro} and Ferrante Neri and Anik{\'{o}} Ek{\'{a}}rt and Mike Preu{\ss} and Anna Isabel {Esparcia-Alc{\'{a}}zar} and Franz Rothlauf and Muddassar Farooq and Ernesto Tarantino and Andreas Fink and Shengxiang Yang},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {T{\"{u}}bingen, Germany: Eberhard-Karls-Universit{\"{a}}t T{\"{u}}bingen, Fakult{\"{a}}t f{\"{u}}r Informations- und Kognitionswissenschaften},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {5484/2009},
    pages = {768--777},
    year = {2009},
    month = {April 15--17, },
    url = {http://www.it-weise.de/documents/files/WPRGG2009EFTP.pdf},
    slides = {http://www.it-weise.de/documents/files/WPRGG2009EFTP_pres.pdf},
    doi = {10.1007/978-3-642-01129-0_87},
    abstract = {In this paper, we present the freight transportation planning component of the INWEST project. This system utilizes an evolutionary algorithm with intelligent search operations in order to achieve a high utilization of resources and a minimization of the distance travelled by freight carriers in real-world scenarios. We test our planner rigorously with real-world data and obtain substantial improvements when compared to the original freight plans. Additionally, different settings for the evolutionary algorithm are studied with further experiments and their utility is verified with statistical tests.},
    eiid = {20093012218527},
    sciids = {BJH22},
    sciwos = {WOS:000265786800087},
    sortkey = {0797722evolutionaryfreighttransportationplanning},
    }
  • Alexander Podlich, Thomas Weise, Manfred Menze, and Christian Gorldt. Intelligente Wechselbrückensteuerung für die Logistik von Morgen. In Michael Wagner, Dieter Hogrefe, Kurt Geihs, and Klaus David, editors, First Workshop on Global Sensor Networks (GSN’09), volume 17, pages 1-10, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, March 6, 2009. Potsdam, Germany: European Association of Software Science and Technology (EASST; Universität Potsdam, Institute for Informatics).
    [PDF] [PPT] [Bibtex]
    @inproceedings{PWMG2009IWFDLVM,
    author = {Alexander Podlich and Thomas Weise and Manfred Menze and Christian Gorldt},
    title = {Intelligente Wechselbr{\"{u}}ckensteuerung f{\"{u}}r die Logistik von Morgen},
    booktitle = {First Workshop on Global Sensor Networks (GSN'09)},
    editor = {Michael Wagner and Dieter Hogrefe and Kurt Geihs and Klaus David},
    publisher = {Potsdam, Germany: European Association of Software Science and Technology (EASST; Universit{\"{a}}t Potsdam, Institute for Informatics)},
    address = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    volume = {17},
    pages = {1--10},
    year = {2009},
    month = {March 6, },
    url = {http://eceasst.cs.tu-berlin.de/index.php/eceasst/article/viewFile/205/207},
    slides = {http://www.it-weise.de/documents/files/PWMG2009IWFDLVM_pres.pdf},
    abstract = {Die Logistik ist einer der wichtigsten Zweige der Volkswirtschaft. Die effiziente Gestaltung der in sie involvierten Prozesse ist daher, gerade angesichts des zu erwartenden R{\"{u}}ckgangs der {\"{O}}lf{\"{o}}rdermenge sowie des bekannterma{\ss}en sch{\"{a}}dlichen Einflusses von CO2 auf das Klima, von hoher Wichtigkeit. Dennoch gibt es auf diesem Bereich viele bisher nur unzureichend gel{\"{o}}ste Probleme. In diesem Beitrag wird das Inwest-System vorgestellt, das sowohl eine praktische Transportplanung als auch ein Informationssystem, welche alle an der Transportkette beteiligte Nutzer und Komponenten verbindet, zur Verf{\"{u}}gung stellt.},
    sortkey = {0797680intelligentewechselbrckensteuerungfrdie},
    }
  • Steffen Bleul, Thomas Weise, and Kurt Geihs. The Web Service Challenge — A Review on Semantic Web Service Composition. In Michael Wagner, Dieter Hogrefe, Kurt Geihs, and Klaus David, editors, Service-Oriented Computing (SOC’2009), volume 17. Potsdam, Germany: European Association of Software Science and Technology (EASST; Universität Potsdam, Institute for Informatics), March 5, 2009. Collocated with KiVS{\textquoteright}09
    [PDF] [PPT] [Bibtex]
    @inproceedings{BWG2009TWSCAROSWSC,
    author = {Steffen Bleul and Thomas Weise and Kurt Geihs},
    title = {The Web Service Challenge {--} A Review on Semantic Web Service Composition},
    booktitle = {Service-Oriented Computing (SOC'2009)},
    editor = {Michael Wagner and Dieter Hogrefe and Kurt Geihs and Klaus David},
    publisher = {Potsdam, Germany: European Association of Software Science and Technology (EASST; Universit{\"{a}}t Potsdam, Institute for Informatics)},
    volume = {17},
    year = {2009},
    month = {March 5, },
    url = {http://eceasst.cs.tu-berlin.de/index.php/eceasst/article/viewFile/207/191},
    slides = {http://www.it-weise.de/documents/files/BWG2009TWSCAROSWSC_pres.pdf},
    note = {Collocated with KiVS{\textquoteright}09},
    abstract = {Every year, contesters submit contributions to the Web Service Challenge (WSC) in order to determine which service composition system is the most efficient one. In this challenge, semantic composition tasks must be solved and the results delivered by the composers are checked for correctness. The time needed for the composition process is another important competition criterion.{\newline}After we had participated with great success in the 2006 and 2007 WSC, we were asked to manage the Web Service Challenge 2008. In this paper, we present the challenge task, the challenge rules, the document format used, and the results of this competition. We provide a summary over the past challenges and give first previews on the future developments planned for the Web Service Challenges to come.},
    sortkey = {0797679thewebservicechallenge},
    }
  • [DOI] Thomas Weise, Michael Zapf, Mohammad Ullah Khan, and Kurt Geihs. Combining Genetic Programming and Model-Driven Development. International Journal of Computational Intelligence and Applications (IJCIA), 8(1):37-52, March 2009.
    [PDF] [Bibtex]
    @article{WZKG2009DGPFz,
    author = {Thomas Weise and Michael Zapf and Mohammad Ullah Khan and Kurt Geihs},
    title = {Combining Genetic Programming and Model-Driven Development},
    publisher = {Singapore: World Scientific Publishing Co. and London, UK: Imperial College Press Co.},
    journal = {International Journal of Computational Intelligence and Applications (IJCIA)},
    number = {1},
    volume = {8},
    pages = {37--52},
    year = {2009},
    month = {March},
    url = {http://www.it-weise.de/documents/files/WZKG2009DGPFz.pdf},
    doi = {10.1142/S1469026809002436},
    abstract = {Genetic Programming is known to provide good solutions for many problems like the evolution of network protocols and distributed algorithms. In most cases it is a hardwired module of a design framework assisting the engineer in optimizing specific aspects in system development. In this article we show how the utility of Genetic Programming can be increased remarkably by isolating it as a component and integrating it into the model-driven software development process. Our Genetic Programming framework produces XMI-encoded UML models that can easily be loaded into widely available modeling tools, which in turn offer code generation as well as additional analysis and test capabilities. We use the evolution of a distributed election algorithm as an example to illustrate how Genetic Programming can be combined with model-driven development.},
    eiid = {20092012083173},
    inspec = {11039030},
    sortkey = {0797673combininggeneticprogrammingand},
    }
  • Alexander Podlich. Intelligente Planung und Optimierung des Güterverkehrs auf Straße und Schiene mit Evolutionären Algorithmen. Master’s thesis, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, February 2009.
    [Bibtex]
    @mastersthesis{P2008IPUODGASUSMEA,
    author = {Alexander Podlich},
    title = {Intelligente Planung und Optimierung des G{\"{u}}terverkehrs auf Stra{\ss}e und Schiene mit Evolution{\"{a}}ren Algorithmen},
    school = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2009},
    month = {February},
    abstract = {Mit dem stark anwachsenden G{\"{u}}terverkehr, der sich einerseits durch den intensiven Warenaustausch innerhalb der erweiterten Europ{\"{a}}ischen Union, andererseits durch den zunehmenden globalen Handel ergibt, w{\"{a}}chst der Bedarf an intelligenten L{\"{o}}sungen f{\"{u}}r strategische Planung und betriebliche Disposition innerhalb der Logistik. Gleichzeitig sollen Kapazit{\"{a}}ten und Reserven aller Verkehrstr{\"{a}}ger effizienter genutzt werden, um einen staufreien, CO2-sparenden und zuverl{\"{a}}ssigen G{\"{u}}terverkehr zu erm{\"{o}}glichen.{\newline}Nach Angaben des Bundesministerium f{\"{u}}r Wirtschaft und Technologie (BMWi) wird die G{\"{u}}terverkehrsleistung von 2005 bis 2030 um 69{\%}, bis 2050 um 110{\%} ansteigen. Rund 70{\%} der Verkehrsleistungen entf{\"{a}}llt dabei auf Kraftfahrzeuge und 27{\%} auf Bahn und Binnenschiffe.{\newline}Allein auf deutschen Stra{\ss}en legen mehr als 54 Millionen in der Bundesrepublik gemeldete Kraftfahrzeuge pro Jahr etwa 528 Milliarden Kilometer zur{\"{u}}ck. Das entspricht etwa der 3500-fachen mittleren Entfernung zwischen Sonne und Erde. Es k{\"{o}}nnten theoretisch noch weitaus mehr sein, st{\"{u}}nden Teile dieser Fahrzeuge hierzulande nicht allj{\"{a}}hrlich 4,7 Milliarden Stunden lang still, im Stau. Das sind rund 57 Stunden je Einwohner und Jahr. In anderen L{\"{a}}ndern ist es nicht besser: 4000 Kilometer Stau belasten z. B. Europas Autobahnen t{\"{a}}glich. Das entspricht einem Zehntel der Gesamtl{\"{a}}nge des Autobahnnetzes.{\newline}Um dieser j{\"{a}}hrlich steigenden Verkehrszunahme und den daraus entstehenden Anforderungen gerecht zu werden und die allgemeine Mobilit{\"{a}}t, insbesondere im G{\"{u}}terverkehr, zu sichern, werden sich in naher Zukunft die Methoden der Verkehrssteuerung in St{\"{a}}dten, auf Landstra{\ss}en und Autobahnen ver{\"{a}}ndern m{\"{u}}ssen.{\newline}In der Literatur wird die Planung und Optimierung von logistischen Vorg{\"{a}}ngen haupts{\"{a}}chlich als ein rein {\"{o}}konomisches Problem betrachtet. Ein bestimmter Warenbedarf soll in einer bestimmten Menge in einem vorgegebenen Zeitfenster an einen bestimmten Ort geliefert werden. Dabei gilt die Pr{\"{a}}misse, dass die daf{\"{u}}r anfallenden Kosten minimiert werden sollen. Diese k{\"{o}}nnen durch sehr viele Faktoren entstehen und umfassen viele Aspekte. So verursacht jede Lieferung Lohnkosten f{\"{u}}r den Fahrer, Kosten f{\"{u}}r den Treibstoff und f{\"{u}}hrt zu Wertminderung an den Transportmitteln. Weitere Kosten entstehen, wen z. B. eine Ware gelagert und nicht sofort ausgeliefert wird oder wenn Wartezeiten auftreten und Transportmittel nicht ausgelastet sind.{\newline}Neben den {\"{o}}konomischen Faktoren flie{\ss}en mittlerweile aber auch die {\"{o}}kologischen Aspekte in die Logistik ein. Das wachsende Umweltbewusstsein und die Ergebnisse neuer Studien zum Klimawandel r{\"{u}}cken die volkswirtschaftlichen Kosten in den Vordergrund, die bisher gr{\"{o}}{\ss}tenteils unbeachtet blieben. Der durch den G{\"{u}}terverkehr verursachte Verbrauch von Ressourcen und die Belastung der Umwelt gewinnen in Politik, {\"{O}}ffentlichkeit und Industrie mehr und mehr an Bedeutung. Daraus resultiert zunehmend der Ruf nach einer kostensparenden, nachhaltigen und umweltschonenden Logistik.{\newline}An dieser Stelle setzt die vorliegende Diplomarbeit an. Mit Hilfe von evolution{\"{a}}ren Algorithmen wird eine Transportplanung und Ad-Hoc-Optimierung realisiert, um den G{\"{u}}tertransport- bzw. das G{\"{u}}terverkehrsaufkommen auf Stra{\ss}e und Schiene zu minimieren. Durch diese Transportplanung- und Optimierung wird neben dem {\"{o}}kologischen Aspekt, n{\"{a}}mlich der Minimierung des CO2-Aussto{\ss}es, gezeigt, wie auch {\"{o}}konomische Faktoren einbezogen werden k{\"{o}}nnen, um das Erreichen beider Ziele zu erm{\"{o}}glichen. So kann z. B. neben der CO2-einsparenden Routenoptimierung u. a. auch ein kosteng{\"{u}}nstigerer Warentransport intermodal gestaltet werden, indem sowohl die Bef{\"{o}}rderungsmittel auf der Stra{\ss}e als auch auf Schienen kombiniert benutzt werden.{\newline}Diese Diplomarbeit ist im Rahmen des vom BMWi gef{\"{o}}rderten Forschungsprojekts in.west (Intelligente Wechselbr{\"{u}}ckensteuerung) entstanden, welches in Zusammenarbeit mit der Deutschen Post im Januar 2008 gestartet wurde. Weitere Projektpartner sowie Mitwirkende dieses Forschungsprojekts sind in der Tabelle dargestellt. Hintergrund des F{\"{o}}rderungsprojekts ist das eben geschilderte enorme Optimierungspotential im Bereich der Logistik. Die forschungsleitende Hypothese ist die Reduzierung des Transport- bzw. Verkehrsaufkommens um 10{\%}. Eine gleichzeitige Optimierung der Auslastung sowie eine Steigerung der Termintreue wird weiterhin angestrebt.{\newline}Im Rahmen des in.west-Projekts soll ein satellitengest{\"{u}}tztes Ortungssystem und eine softwarebasierte intelligente Steuerung eine Verfolgbarkeit der logistischen Prozesse in Echtzeit erm{\"{o}}glichen. So sollen Abweichungen vom System selbstst{\"{a}}ndig erkannt werden, um auf diese schnell und sinnvoll reagieren zu k{\"{o}}nnen. Den methodischen Kern und den Schwerpunkt dieser Arbeit bildet die Kombination dieser zwei Aspekte. Dazu wird ein Ansatz vorgestellt, wie eine intelligente Steuerung auf heuristischer Entscheidungsbasis unter den verschiedenen Nebenbedingungen zu einem, im Bezug auf vorher definierten Zielfunktionen, optimalen Ergebnis f{\"{u}}hren kann.{\newline}Die in dieser Arbeit vorgestellte intelligente Steuerung bildet eine zentrale Aufgabe im in.west-Projekt und erm{\"{o}}glicht einerseits eine Transportplanung f{\"{u}}r einen kompletten Zeitraum und realisiert andererseits, unter Zuhilfenahme eines satellitengest{\"{u}}tzten Ortungssystems, eine Ad-Hoc-Optimierung, die Disponenten oder andere Experten in unvorhersehbaren Ereignissen wie Stau oder Unfall unterst{\"{u}}tzt und z. B. einen optimalen Tourenplan zur Laufzeit errechnet. In beiden Anwendungsf{\"{a}}llen k{\"{o}}nnen durch eine verbesserte Transportplanung- und Optimierung die {\"{o}}kologischen und {\"{o}}konomischen Transportkosten gesenkt werden},
    advisor = {Thomas Weise and Christian Gorldt and Manfred Menze},
    committeeMember = {Kurt Geihs and Bernd {Scholz-Reiter}},
    sortkey = {0797640intelligenteplanungundoptimierung},
    }
  • Michael Zapf and Thomas Weise. Applicability of Emergence Engineering to Distributed Systems Scenarios. Kasseler Informatikschriften (KIS) 2008, 5, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, January 9, 2009.
    [PDF] [Bibtex]
    @techreport{ZW2009AOEETDS,
    author = {Michael Zapf and Thomas Weise},
    title = {Applicability of Emergence Engineering to Distributed Systems Scenarios},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik},
    type = {Kasseler Informatikschriften (KIS)},
    number = {2008, 5},
    year = {2009},
    month = {January 9, },
    url = {http://nbn-resolving.org/resolver?identifier=urn:nbn:de:hebis:34-2009010925609&verb=full},
    abstract = {Genetic Programming can be effectively used to create emergent behavior for a group of autonomous agents. In the process we call Offline Emergence Engineering, the behavior is at first bred in a Genetic Programming environment and then deployed to the agents in the real environment. In this article we shortly describe our approach, introduce an extended behavioral rule syntax, and discuss the impact of the expressiveness of the behavioral description to the generation success, using two scenarios in comparison: the election problem and the distributed critical section problem. We evaluate the results, formulating criteria for the applicability of our approach.},
    urn = {urn:nbn:de:hebis:34-2009010925609},
    sortkey = {0797617applicabilityofemergenceengineering},
    }
  • Raymond Chiong and Thomas Weise. Global Optimisation and Mobile Learning. Learning Technology — LTTF Newsletter, 11(1-2):26-28, January–April 2009.
    [PDF] [Bibtex]
    @article{CW2009GOAML,
    author = {Raymond Chiong and Thomas Weise},
    title = {Global Optimisation and Mobile Learning},
    publisher = {Technical Committee on Learning Technology},
    journal = {Learning Technology {--} LTTF Newsletter},
    number = {1-2},
    volume = {11},
    pages = {26--28},
    year = {2009},
    month = {January--April},
    url = {http://www.it-weise.de/documents/files/CW2009GOAML.pdf},
    abstract = {1 Introduction{\newline}Mobile devices, such as cellular phones and Personal Digital Assistants (PDA), have become part and parcel of our everyday life. These mobile technologies and their wide adoption in the society are influencing not only the way we live, but also the way we learn, the way we work, and the way we socialise. According to [1], there are estimated to be more than 1.5 billion mobile phones in the world today. The rapid advancement of these portable technologies is also changing the way educational institutions work. It has opened up new possibilities for extending learning opportunities to all social-economic levels and a completely new dimension to the progress in education and training known as mobile learning. Through mobile learning, educational and training programs that were once delivered only through a face-to-face setting or networked computers can now be done almost anywhere, anytime.{\newline}2 Global Optimisation{\newline}Global optimisation, on the other hand, is a branch of applied mathematics and numerical analysis that focuses on finding the best possible solutions based on a set of criteria expressed as mathematical functions, commonly known as objective functions [2]. Global optimisation approaches can generally be divided into two types: deterministic and stochastic. The most successful example of the deterministic type is perhaps the Branch and Bound1 methods, but they are not so attractive anymore in recent years due to the large and dynamic problem spaces that need to be tackled in today{\textquoteright}s real-world problems. A more appealing choice is therefore the stochastic solvers, such as Genetic Algorithms, Particle Swarm Optimisation, Ant Colony Optimisation, and so on. These methods are mostly inspired in part by nature and natural systems. For an overview of some popular nature-inspired methods and their practical applications, see [3]. So, what does global optimisation have to do with mobile learning? An undeniable fact is that all of us desire optimal outcomes. Very often we tend to find various alternatives in order to maximise our gain by minimising the cost we need to bear. Likewise, various aspects of the mobile learning environment need to be optimised so that the mobile learners can take full advantage of it. Global optimisation methods have been widely used in many e-learning activities. For example, very recently an e-learning decision support framework based on a set of soft computing techniques is introduced in [4] with the aim to improve e-learning experience. This framework can discover an e-learning system{\textquoteright}s usage patterns and contribute to alleviating instructors{\textquoteright} workload. The identification of students{\textquoteright} learning behaviour allows instructors to predict the performance of their students and pinpoint weaker students for personalised feedback. Besides that, we see the use of Genetic Algorithms for providing intelligent assessment services in an e-learning environment [5] and for classifying students in order to predict their final grade based on features extracted from log data in a web-based educational system [6], the use of Ant Colony Optimisation for the pedagogic {\{}(1) A general optimisation algorithm that systematically enumerates all candidate solutions and discards fruitless candidates by using upper and lower estimated bounds of the quantity of solutions being optimised.{\}} material of an online teaching website for high school students [7-8] and for sequencing of elearning activities [9], as well as the use of Particle Swarm Optimisation for arranging a set of learning resources in order to present them in a personalised way to the learners [10]. Note that these examples are by no means a comprehensive list, but a snapshot of some interesting works that applied global optimisation methods to e-learning over the last couple of years.{\newline}3 Examples of Global Optimisation in Mobile Learning{\newline}While substantial works have been done on e-learning with global optimisation, its applications to mobile learning are still rare. Lately, an adaptive testing system for supporting versatile educational assessment has been presented [11]. In this work, the authors integrate computer based test with mobile learning for both formative assessment and self-assessment. Students are assessed through a process that uses item response theory, a well-founded psychometric theory. The problem with the use of item response theory is that a large item bank is indispensable to a test, yet when the system has a large item bank, the test item selection becomes a very tedious job. To solve the problem, Particle Swarm Optimisation method is used to speed up the searching and selection process. Furthermore, for controlling the test item exposure, an item exposure mechanism is combined with Particle Swarm Optimisation to prevent the same test item from appearing twice. When a test item was responded or an adaptive test was finished by a student, this system applies maximum likelihood estimation as an underlying psychometric theory to estimate the student{\textquoteright}s ability and give immediate feedback by showing the results to the student. Apart from Particle Swarm Optimisation, an improved Genetic Algorithm with association rules has been proposed in [12] to analyse the vast amount of learners{\textquoteright} profile data in a webbased mobile-learning system. The authors show that interesting relationships can be found with this method within minimal execution time. If fully developed, it is able to create an efficient mobile-learning system that understands its learners.{\newline}4 Concluding Remarks{\newline}Although brief, these works demonstrate the potential of global optimisation in mobile learning. Genetic Algorithms have been applied extensively in mobile robots with huge success (see [13, 14]). Similarly, swarm intelligence and other global optimisation methods have contributed greatly to the field of telecommunications and distributed systems (see [15, 16]). It is therefore just a matter of time before these methods are adopted extensively in mobile learning.{\newline}References{\newline}[1] Attewell, J. (2005). Mobile Technologies and Learning: A Technology Update and m-Learning Project Summary. Technology Enhanced Learning Research Centre, Learning and Skills Development Agency. London: Learning and Skills Development Agency.{\newline}[2] Weise, T. (2009). Global Optimization Algorithms - Theory and Application. Online e-book under GNU Free Documentation License, available at http://www.it-weise.de/projects/book.pdf{\newline}[3] Chiong, R., Neri, F., {\&} McKay, R. I. (2009). Nature that Breeds Solutions. In R. Chiong (Ed.), Nature-Inspired Informatics for Intelligent Applications and Knowledge Discovery: Implications in Business, Science and Engineering (Chapter 1). Hershey, PA: Information Science Reference.{\newline}[4] Castro, F., Nebot, {\`{A}}, {\&} Mugica, F. (2008). A Soft Computing Decision Support Framework to Improve the e-Learning Experience. Proceedings of the 2008 Spring Simulation Multiconference, Modeling {\&} Simulation in Education (pp. 781-788). San Diego, CA: The Society for Computer Simulation, International.{\newline}[5] Alexakos, C. E., Giotopoulos, K. C., Thermogianni, E. J., Beligiannis, G. N., {\&} Likothanassis, S. D. (2006). Integrating E-learning Environments with Computational Intelligence Assessment Agents. Proceedings of World Academy of Science, Engineering and Technology, 13, 233-238.{\newline}[6] Minaei-Bidgoli, B., {\&} Punch, W. F. (2003). Using Genetic Algorithms for Data Mining Optimization in an Educational Web-based System. Lecture Notes in Computer Science, 2724, 2252-2263.{\newline}[7] Semet, Y., Lutton, E., {\&} Collet, P. (2003). Ant Colony Optimisation for e-Learning: Observing the Emergence of Pedagogical Suggestions. Proceedings of the IEEE Swarm Intelligence Symposium (pp. 46-52). Piscataway, NJ: IEEE Press.{\newline}[8] Semet, Y., Yamo{\newline}nt, Y., Biojout, R., Luton, E., {\&} Collet, P. (2003). Artificial Ant Colonies and e-Learning: An Optimisation of Pedagogical Paths. Proceedings of the 10th International Conference on Human-Computer Interaction (pp. 1031-1035). Mahwah, NJ: Lawrence Erlbaum Associates.{\newline}[9] Guti{\'{e}}rrez, S., Valigiani, G., Collet, P., {\&} Kloos, C. D. (2008). Adaptation of the ACO Heuristic for Sequencing Learning Activities. Proceedings of the European Conference on Technology Enhanced Learning (http://ceur-ws.org/Vol-280/p15.pdf), Crete, Greece.{\newline}[10] de Marcos, L., Mart{\'{\i}}nez, J. J., Gutierrez, J. A. (2008). Swarm Intelligence in e-Learning: A Learning Object Sequencing Agent based on Competencies. Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation (pp. 17-24). New York, NY: ACM Press.{\newline}[11] Huang, Y. M., Lin, Y. T., {\&} Cheng, S. C. (2009). An Adaptive Testing System for Supporting Versatile Educational Assessment. Computers {\&} Education, 52, 53-67.{\newline}[12] Zheng, S. J., Xiong, S. J., Huang, Y., {\&} Wu, S. X. (2008). Using Methods of Association Rules Mining Optimization in Web-Based Mobile-Learning System. Proceedings of the International Symposium on Electronic Commerce and Security (pp. 967-970). Washington, DC: IEEE Computer Society.{\newline}[13] Floreano, D., {\&} Mondada, F. (1996). Evolution of Homing Navigation in a Real Mobile Robot. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 26(3), 396-407.{\newline}[14] Kubota, N., Morioka, T., Kojima, F., {\&} Fukuda, T. (2001). Learning of Mobile Robots using Perception-based Genetic Algorithm. Measurement, 29(3), 237-248.{\newline}[15] Nesmachnow, S., Cancela, H., {\&} Alba, E. (2009). Nature-Inspired Informatics for Telecommunication Network Design. In R. Chiong (Ed.), Nature-Inspired Informatics for Intelligent Applications and Knowledge Discovery: Implications in Business, Science and Engineering (Chapter 14). Hershey, PA: Information Science Reference.{\newline}[16] Weise, T., {\&} Chiong, R. (2009). Evolutionary Approaches and their Applications to Distributed Systems. In R. Chiong (Ed.), Intelligent Systems for Automated Learning and Adaptation: Emerging Trends and Applications (Chapter 6). Hershey, PA: Information Science Reference.},
    sortkey = {0797607globaloptimisationandmobile},
    }
  • Thomas Weise. Global Optimization Algorithms — Theory and Application. Germany: it-weise.de (self-published), 2009.
    [PDF] [Bibtex]
    @book{WGOEB,
    author = {Thomas Weise},
    title = {Global Optimization Algorithms {--} Theory and Application},
    publisher = {Germany: it-weise.de (self-published)},
    year = {2009},
    url = {http://www.it-weise.de/projects/book.pdf},
    sortkey = {0797573globaloptimizationalgorithms},
    }

2008

  • Thomas Weise. Internal Cooperation/Brainstorming Session Presentation — Evolving Distributed Algorithms with Genetic Programming. December 15, 2008.
    [PPT] [Bibtex]
    @misc{W2008BSWVH,
    author = {Thomas Weise},
    title = {Internal Cooperation/Brainstorming Session Presentation {--} Evolving Distributed Algorithms with Genetic Programming},
    publisher = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2008},
    month = {December 15, },
    slides = {http://www.it-weise.de/documents/files/W2008BSWVH.pdf},
    sortkey = {0797589internalcooperationbrainstormingsessionpresentation},
    }
  • Christian Voigtmann. Integration Evolutionärer Klassifikatoren in Weka. Master’s thesis Bachelor’s Thesis, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, October 26, 2008.
    [Bibtex]
    @mastersthesis{V2008IEIW,
    author = {Christian Voigtmann},
    title = {Integration Evolution{\"{a}}rer Klassifikatoren in Weka},
    school = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    type = {Bachelor's Thesis},
    year = {2008},
    month = {October 26, },
    abstract = {Im Rahmen zweier Projektarbeiten haben zwei Kommilitonen und ich in den Jahren 2007 und 2008 erfolgreich am Data-Mining-Cup1 (DMC) Wettbewerb teilgenommen. Der DMC ist der gr{\"{o}}{\ss}te Wettbewerb im Bereich des Data-Minings und wird einmal im Jahr von der Firma Prudsys AG2 und der Technischen Universit{\"{a}}t Chemnitz veranstaltet. In den letzten beiden Jahren wurden jeweils Aufgaben aus dem Bereich des {\"{u}}berwachten Lernens gestellt. Um diese Aufgabenstellung zu l{\"{o}}sen, haben wir uns in den beiden Jahren g{\"{a}}ngiger Klassifikatoren aus demWeka Framework bedient und eigene Klassifikatoren unter Verwendung von evolution{\"{a}}ren Algorithmen gez{\"{u}}chtet. Die von uns gez{\"{u}}chteten Ans{\"{a}}tze waren in beiden Jahren die L{\"{o}}sungen, die im Vergleich zu allen anderen von uns eingereichten L{\"{o}}sungen die besten Platzierungen erreichten. 2007 erreichten wir Platz 23 von 248 eingereichen L{\"{o}}sungen und 2008 haben wir Platz 93 von 212 eingereichten L{\"{o}}sungen erzielt. Neben der Vorverarbeitung der Daten f{\"{u}}r deren Verst{\"{a}}ndnis stellte die Erzeugung und Anpassung der evolution{\"{a}}ren Ans{\"{a}}tze auf die jeweilige zu l{\"{o}}sende Aufgabenstellung die zeitaufwendigste T{\"{a}}tigkeit dar. Um nachfolgenden Gruppen, die am DMC teilnehmen m{\"{o}}chten bzw. allen anderen Interessierten aus der Data-Mininig-Community, die zeitintensive Adaptierung der evolution{\"{a}}ren Ans{\"{a}}tze an neue Datens{\"{a}}tze zu ersparen, entstand die Idee, die in den Wettbewerben erprobten Ans{\"{a}}tze zu verallgemeinern und in das Weka Framework zu integrieren. Die Verallgemeinerung der Ans{\"{a}}tze soll gew{\"{a}}hrleisten, dass m{\"{o}}glichst viele unterschiedliche Datens{\"{a}}tze aus dem Bereich des {\"{u}}berwachten Lernens verarbeitet werden k{\"{o}}nnen. Des Weiteren soll durch die Integration der Ans{\"{a}}tze in das Weka Framework sichergestellt werden, dass deren Parametrisierung m{\"{o}}glichst {\"{u}}berschaubar und einfach zu Hand haben ist. Mein pers{\"{o}}nliches Ziel ist es, die integrierten evolution{\"{a}}ren Ans{\"{a}}tze bei der n{\"{a}}chsten Teilnahme am DMC 2009 zu verwenden und mit ihnen ein m{\"{o}}glichst gutes Ergebnis zu erzielen. Das Ziel dieser Arbeit ist es, die zwei im Zuge des Data-Mining-Cups 2007 und 2008 entwickelten evolution{\"{a}}ren Ans{\"{a}}tze der Allgemeinheit zur Verf{\"{u}}gung zu stellen, indem diese in das bekannte Weka Framework integriert werden. Dabei sollen diese beiden Ans{\"{a}}tze wie alle standardm{\"{a}}{\ss}ig in Weka integrierten Klassifikatoren {\"{u}}ber das Men{\"{u}} f{\"{u}}r die Klassifikatoren ausw{\"{a}}hlbar und parametrierbar sein.Weiter soll gew{\"{a}}hrleistet sein, dass beide Ans{\"{a}}tze alle g{\"{a}}ngigen Optionen der Weka Data-Mining Software, wie das Erzeugen und das Laden von Modellen, sowie die Klassifizierung von Holdoutdatens {\"{a}}tzen und die Ausgabe des Klassifizierungsergebnisses innerhalb des Frameworks unterst{\"{u}}tzen. Einen wichtigen Punkt stellt die {\"{U}}berarbeitung der beiden Ans{\"{a}}tze hinsichtlich ihrer Generalit{\"{a}}t dar, damit m{\"{o}}glichst viele unterschiedliche Datens{\"{a}}tze verarbeitet werden k{\"{o}}nnen. Im zweiten Kapitel wird auf den Begriff des Data-Minings eingegangen und ein Beispieldatensatz aus dem Data-Mining vorgestellt. Au{\ss}erdem werden evolution{\"{a}}re Algorithmen allgemein besprochen und es wird auf verwandte Verfahren wie Learning Classifier Systems und Entscheidungsb{\"{a}}ume eingegangen. Das dritte Kapitel besch{\"{a}}ftigt sich mit den verwendeten Werkzeugen, die f{\"{u}}r die Bearbeitung der Aufgabenstellung herangezogen wurden. Im darauf folgenden Kapitel werden verwandte Arbeiten vorgestellt. Das f{\"{u}}nfte Kapitel stellt die beiden in das Weka Framework zu integrierenden evolution{\"{a}}ren Ans{\"{a}}tze ausf{\"{u}}hrlich vor, deren Implementierung anschlie{\ss}end in Kapitel sechs besprochen wird. Im Kapitel Experimente werden die integrierten Ans{\"{a}}tze auf bekannte Data-Mining Datens{\"{a}}tze angewandt und deren Ergebnisse mit etablierten Klassifikatoren verglichen und statistisch ausgewertet. Zum Schluss der Arbeit werden die erzielten Ergebnisse besprochen und es wird ein Ausblick {\"{u}}ber noch ausstehende Arbeiten gegeben.},
    advisor = {Thomas Weise},
    committeeMember = {Kurt Geihs and Heinrich Werner},
    sortkey = {0797534integrationevolutionrerklassifikatorenin},
    }
  • [DOI] Philipp Andreas Baer, Thomas Weise, and Kurt Geihs. Geminga: Service Discovery for Mobile Robotics. In Proceedings of The Third International Conference on Systems and Networks Communications (ICSNC’08), pages 167-172, Sliema, Malta: Palace Hotel, October 26–31, 2008. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [Bibtex]
    @inproceedings{BWG2008GSDFMR,
    author = {Philipp Andreas Baer and Thomas Weise and Kurt Geihs},
    title = {Geminga: Service Discovery for Mobile Robotics},
    booktitle = {Proceedings of The Third International Conference on Systems and Networks Communications (ICSNC'08)},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Sliema, Malta: Palace Hotel},
    pages = {167--172},
    year = {2008},
    month = {October 26--31, },
    url = {http://www.it-weise.de/documents/files/BWG2008GSDFMR.pdf},
    doi = {10.1109/ICSNC.2008.29},
    abstract = {Communication infrastructures of highly distributed software architectures are often complex to configure and costly to manage. Dynamics in the environment leading to a need for self-adaptation will further complicate maintenance. For this purpose we introduce Geminga, a service discovery approach for application in ad hoc networks and self-configuration of communication infrastructures. Tailored to unreliability in communication, it bridges the gap between traditional application domains of distributed architectures and groups of mobile robots. The applicability of Geminga is shown by adapting it to a software framework for autonomous soccer robots.},
    eiid = {20090211848280},
    sortkey = {0797534gemingaservicediscoveryfor},
    }
  • [DOI] Ajay Bansal, Brian M. Blake, Srividya Kona, Steffen Bleul, Thomas Weise, and Michael C. Jäger. WSC-08: Continuing the Web Services Challenge. In Proceedings of IEEE Joint Conference on E-Commerce Technology (10th CEC) and Enterprise Computing, E-Commerce and E-Services (5th EEE) (CEC/EEE’08), pages 351-354, Washington, DC, USA, July 21–24, 2008. Piscataway, NJ, USA: IEEE Computer Society.
    [PDF] [PPT] [Bibtex]
    @inproceedings{BBKBWJ2008WSC08CTWSC,
    author = {Ajay Bansal and M. Brian Blake and Srividya Kona and Steffen Bleul and Thomas Weise and Michael C. J{\"{a}}ger},
    title = {WSC-08: Continuing the Web Services Challenge},
    booktitle = {Proceedings of IEEE Joint Conference on E-Commerce Technology (10th CEC) and Enterprise Computing, E-Commerce and E-Services (5th EEE) (CEC/EEE'08)},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Washington, DC, USA},
    pages = {351--354},
    year = {2008},
    month = {July 21--24, },
    url = {http://www.it-weise.de/documents/files/BBKBWJ2008WSC08CTWSC.pdf},
    poster = {http://www.it-weise.de/documents/files/BBKBWJ2008WSC08CTWSC_flyer.pdf},
    doi = {10.1109/CECandEEE.2008.146},
    abstract = {The capabilities of organizations can be openly exposed, easily searched and discovered, and made readily-accessible to humans and particularly to machines, using service-oriented computing approaches. Artificial intelligence and software engineering researchers alike are tantalized by the promise of ubiquitously discovering and incorporating services into their own business processes (i.e. composition and orchestration). With growing acceptance of service-oriented computing, an emerging area of research is the investigation of technologies that will enable the discovery and composition of web services. The Web Services Challenge (WSC) is a forum where academic and industry researchers can share experiences of developing tools that automate the integration of Web services. In the fourth year (i.e. WSC-08) of the Web Services Challenge, software platforms will address several new composition challenges. Requests and results will be transmitted within SOAP messages. In addition, semantics will be represented as ontologies written in OWL, services will be represented in WSDL, and service orchestrations will be represented in WS-BPEL.},
    eiid = {20091512027446},
    sciids = {BJF01},
    sciwos = {WOS:000265327500048},
    inspec = {10475109},
    sortkey = {0797430wsc08continuingtheweb},
    }
  • [DOI] Thomas Weise, Steffen Bleul, Marc Kirchhoff, and Kurt Geihs. Semantic Web Service Composition for Service-Oriented Architectures. In Proceedings of IEEE Joint Conference on E-Commerce Technology (10th CEC) and Enterprise Computing, E-Commerce and E-Services (5th EEE) (CEC/EEE’08), pages 355-358, Washington, DC, USA, July 21–24, 2008. Piscataway, NJ, USA: IEEE Computer Society.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WBKG2008SWSCFSOA,
    author = {Thomas Weise and Steffen Bleul and Marc Kirchhoff and Kurt Geihs},
    title = {Semantic Web Service Composition for Service-Oriented Architectures},
    booktitle = {Proceedings of IEEE Joint Conference on E-Commerce Technology (10th CEC) and Enterprise Computing, E-Commerce and E-Services (5th EEE) (CEC/EEE'08)},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Washington, DC, USA},
    pages = {355--358},
    year = {2008},
    month = {July 21--24, },
    url = {http://www.it-weise.de/documents/files/WBKG2008SWSCFSOA.pdf},
    slides = {http://www.it-weise.de/documents/files/WBKG2008SWSCFSOA_slides.pdf},
    doi = {10.1109/CECandEEE.2008.148},
    abstract = {Semantic web service composition is about finding services from a repository that are able to accomplish a specified task. The task is defined in a form of a composition request which contains a set of available input parameters and a set of wanted output parameters. Instead of the parameter values, concepts from an ontology describing their semantics are passed to the composition engine. The composer works on a repository of services. The parameters of these services are semantically annotated in the same way as the parameters in the request. The composer then finds a set of services fulfilling the request - the composition. If the input parameters given in the request are provided, the services of this set can be executed and will finally produce the wanted output parameters. In this paper, we introduce our new, improved composition system with which we will take part in the Web Service Challenge 2008.},
    eiid = {20091512027447},
    sciids = {BJF01},
    sciwos = {WOS:000265327500049},
    inspec = {10475110},
    sortkey = {0797430semanticwebservicecomposition},
    }
  • [DOI] Thomas Weise, Stefan Niemczyk, Hendrik Skubch, Roland Reichle, and Kurt Geihs. A Tunable Model for Multi-Objective, Epistatic, Rugged, and Neutral Fitness Landscapes. In Maarten Keijzer, Giuliano Antoniol, Clare Bates Congdon, Kalyanmoy Deb, Benjamin Doerr, Nikolaus Hansen, John H. Holmes, Gregory S. Hornby, Daniel Howard, James Kennedy, Sanjeev P. Kumar, Fernando G. Lobo, Julian Francis Miller, Jason H. Moore, Frank Neumann, Martin Pelikan, Jordan B. Pollack, Kumara Sastry, Kenneth Owen Stanley, Adrian Stoica, El-Ghazali, and Ingo Wegener, editors, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO’08), pages 795-802, Atlanta, GA, USA: Renaissance Atlanta Hotel Downtown, July 12–16, 2008. New York, NY, USA: ACM Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WNSRG2008ATMFMOERANFL,
    author = {Thomas Weise and Stefan Niemczyk and Hendrik Skubch and Roland Reichle and Kurt Geihs},
    title = {A Tunable Model for Multi-Objective, Epistatic, Rugged, and Neutral Fitness Landscapes},
    booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'08)},
    editor = {Maarten Keijzer and Giuliano Antoniol and Clare Bates Congdon and Kalyanmoy Deb and Benjamin Doerr and Nikolaus Hansen and John H. Holmes and Gregory S. Hornby and Daniel Howard and James Kennedy and Sanjeev P. Kumar and Fernando G. Lobo and Julian Francis Miller and Jason H. Moore and Frank Neumann and Martin Pelikan and Jordan B. Pollack and Kumara Sastry and Kenneth Owen Stanley and Adrian Stoica and {El-Ghazali} Talbi and Ingo Wegener},
    publisher = {New York, NY, USA: ACM Press},
    address = {Atlanta, GA, USA: Renaissance Atlanta Hotel Downtown},
    pages = {795--802},
    year = {2008},
    month = {July 12--16, },
    url = {http://www.it-weise.de/documents/files/WNSRG2008GECCO.pdf},
    slides = {http://www.it-weise.de/documents/files/WNSRG2008GECCO_slides.pdf},
    doi = {10.1145/1389095.1389252},
    abstract = {The fitness landscape of a problem is the relation between the solution candidates and their reproduction probability. In order to understand optimization problems, it is essential to also understand the features of fitness landscapes and their interaction. In this paper we introduce a model problem that allows us to investigate many characteristics of fitness landscapes. Specifically noise, affinity for overfitting, neutrality, epistasis, multi-objectivity, and ruggedness can be independently added, removed, and fine-tuned. With this model, we contribute a useful tool for assessing optimization algorithms and parameter settings.},
    eiid = {20085111786051},
    sortkey = {0797421atunablemodelfor},
    }
  • [DOI] Thomas Weise, Steffen Bleul, Diana Elena Comes, and Kurt Geihs. Different Approaches to Semantic Web Service Composition. In Abdelhamid Mellouk, Jun Bi, Guadalupe Ortiz, Kak Wah (Dickson) Chiu, and Manuela Popescu, editors, Proceedings of The Third International Conference on Internet and Web Applications and Services (ICIW’08), pages 90-96, Athens, Greece, June 8–13, 2008. Los Alamitos, CA, USA: IEEE Computer Society Press.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WBCG2008ICIW,
    author = {Thomas Weise and Steffen Bleul and Diana Elena Comes and Kurt Geihs},
    title = {Different Approaches to Semantic Web Service Composition},
    booktitle = {Proceedings of The Third International Conference on Internet and Web Applications and Services (ICIW'08)},
    editor = {Abdelhamid Mellouk and Jun Bi and Guadalupe Ortiz and Kak Wah (Dickson) Chiu and Manuela Popescu},
    publisher = {Los Alamitos, CA, USA: IEEE Computer Society Press},
    address = {Athens, Greece},
    pages = {90--96},
    year = {2008},
    month = {June 8--13, },
    url = {http://www.it-weise.de/documents/files/WBCG2008ICIW.pdf},
    slides = {http://www.it-weise.de/documents/files/WBCG2008ICIW_slides.pdf},
    doi = {10.1109/ICIW.2008.32},
    abstract = {Semantic web service composition is about finding services from a repository that are able to accomplish a specified task if executed. The task is defined in a form of a composition request which contains a set of available input parameters and a set of wanted output parameters. Instead of the parameter values, concepts from an ontology describing their semantics are passed to the composition engine. The parameters of the services in the repository the composer works on are semantically annotated in the same way as the parameters in the request. The composer then finds a sequence of services, called a composition. If the input parameters given in the request are provided, the services of this sequence can subsequently be executed and will finally produce the wanted output parameters. In this paper, three different approaches to semantic web service composition are formally defined and compared with each other: an uninformed search in form of an IDDFS algorithm, a greedy informed search based on heuristic functions, and a multi- objective genetic algorithm.},
    eiid = {20083711536637},
    sciids = {BRC96},
    sciwos = {WOS:000290504500016},
    inspec = {10067008},
    sortkey = {0797384differentapproachestosemantic},
    }
  • Stefan Niemczyk. Ein Modellproblem mit einstellbarer Schwierigkeit zur Evaluierung Evolutionärer Algorithmen. Master’s thesis, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, May 5, 2008.
    [PDF] [PPT] [Bibtex]
    @mastersthesis{N2008EMMESZEEA,
    author = {Stefan Niemczyk},
    title = {Ein Modellproblem mit einstellbarer Schwierigkeit zur Evaluierung Evolution{\"{a}}rer Algorithmen},
    school = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    pages = {75},
    year = {2008},
    month = {May 5, },
    url = {http://www.it-weise.de/documents/files/N2008MPMES.pdf},
    slides = {http://www.it-weise.de/documents/files/N2008MPMES_slides.pdf},
    abstract = {Das Thema dieser Arbeit ist die Erstellung eines Modellproblems, welches Neutralit{\"{a}}t, Epistase, Schroffheit, Multiobjektivit{\"{a}}t und {\"{U}}berspezialisierung beziehungsweise {\"{U}}bervereinfachung simulieren kann. Neben dem Testen von Verfahren und Einstellungen ist es m{\"{o}}glich, diese zu vergleichen und neue Erkenntnisse zu erlagen. Das Modell bietet zahlreiche Anwendungsm{\"{o}}glichkeiten. Als Ausgangspunkt f{\"{u}}r das Modell wurde die Suche nach einem Bitstring mit einer variablen L{\"{a}}nge verwendet. Diese Suche kann Schrittweise mit den bereits oben erw{\"{a}}hnten Eigenschaften erschwert werden. Dabei ist jede Schwierigkeit als eine Art Filter zu verstehen, der Einfluss auf gefundene L{\"{o}}sungen oder die Auswertung nimmt. Hierbei wurde darauf geachtet, dass alle Eigenschaften die Performanz des Modells nicht negativ beeinflussen. Es wurden zahlreiche Experimente durchgef{\"{u}}hrt um diese Filter einzeln und in Kombination zu testen und somit die Richtigkeit des Modells zu zeigen. Diese verliefen gro{\ss}teils wie erwartet. Die ben{\"{o}}tigte Zeit f{\"{u}}r die Testreihen blieb immer innerhalb eines akzeptablen Rahmens. Insgesamt wurde ein Modell geschaffen, mit dem alle der oben erw{\"{a}}hnten Eigenschaften simuliert werden k{\"{o}}nnen. Ein solches Modell existiert noch nicht, alle existierenden {\"{a}}hnlichen Ans{\"{a}}tze beinhalten immer nur eine Teilmenge der Eigenschaften.},
    advisor = {Thomas Weise},
    committeeMember = {Kurt Geihs and Albert Z{\"{u}}ndorf},
    sortkey = {0797348einmodellproblemmiteinstellbarer},
    }
  • [DOI] Thomas Weise, Michael Zapf, and Kurt Geihs. Evolving Proactive Aggregation Protocols. In Michael O’Neill, Leonardo Vanneschi, Steven Matt Gustafson, Anna Isabel Esparcia-Alcázar, Ivanoe de Falco, Antonio Della Cioppa, and Ernesto Tarantino, editors, Genetic Programming — Proceedings of the 11th European Conference on Genetic Programming (EuroGP’08), volume 4971/2008 of Lecture Notes in Computer Science (LNCS), pages 254-265, Naples, Italy, March 26–28, 2008. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [Bibtex]
    @inproceedings{WZG2008DGPFAEPAP,
    author = {Thomas Weise and Michael Zapf and Kurt Geihs},
    title = {Evolving Proactive Aggregation Protocols},
    booktitle = {Genetic Programming {--} Proceedings of the 11th European Conference on Genetic Programming (EuroGP'08)},
    editor = {Michael {O'Neill} and Leonardo Vanneschi and Steven Matt Gustafson and Anna Isabel {Esparcia-Alc{\'{a}}zar} and Ivanoe {de Falco} and Antonio {Della Cioppa} and Ernesto Tarantino},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Naples, Italy},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {4971/2008},
    pages = {254--265},
    year = {2008},
    month = {March 26--28, },
    url = {http://www.it-weise.de/documents/files/WZG2008DGPFa.pdf},
    doi = {10.1007/978-3-540-78671-9_22},
    abstract = {We present an approach for the automated synthesis of proactive aggregation protocols using Genetic Programming and discuss major decisions in modeling and simulating distributed aggregation protocols. We develop a genotype, which is an abstract specification form for aggregation protocols. Finally we show the evolution of a distributed average protocol under various conditions to demonstrate the utility of our approach},
    eiid = {20083011392084},
    sciids = {BHN52},
    sciwos = {WOS:000254506700022},
    sortkey = {0797303evolvingproactiveaggregationprotocols},
    }
  • Stephan Opfer, Stefan Triller, Stephan Scheuermann, Till Amma, Michael Blumenstein, and Ilhan Glogic. Proceedings of the 1st Kassel Student Workshop on Security in Distributed Systems (KaSWoSDS’08). Kasseler Informatikschriften (KIS) 2008, 1, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, February 13, 2008. Published on April 14, 2008.
    [PDF] [PPT] [PPT] [Bibtex]
    @techreport{PROC2008KASWOSDS,
    author = {Stephan Opfer and Stefan Triller and Stephan Scheuermann and Till Amma and Michael Blumenstein and Ilhan Glogic},
    title = {Proceedings of the 1st Kassel Student Workshop on Security in Distributed Systems (KaSWoSDS'08)},
    editor = {Thomas Weise and Philipp Andreas Baer},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik},
    type = {Kasseler Informatikschriften (KIS)},
    number = {2008, 1},
    year = {2008},
    month = {February 13, },
    url = {http://www.it-weise.de/documents/files/PROC2008KASWOSDS.pdf},
    slides = {http://www.it-weise.de/documents/files/WB2007SIVS_slides.pdf},
    poster = {http://www.it-weise.de/documents/files/WB2007SIVS_flyer.pdf},
    note = {Published on April 14, 2008.},
    abstract = {With this document, we provide a compilation of in-depth discussions on some of the most current security issues in distributed systems. The six contributions have been collected and presented at the 1st Kassel Student Workshop on Security in Distributed Systems (KaSWoSDS{\textquoteright}08). We are pleased to present a collection of papers not only shedding light on the theoretical aspects of their topics, but also being accompanied with elaborate practical examples. In Chapter 1, Stephan Opfer discusses Viruses, one of the oldest threats to system security. For years there has been an arms race between virus producers and anti-virus software providers, with no end in sight. Stefan Triller demonstrates how malicious code can be injected in a target process using a buffer overflow in Chapter 2. Websites usually store their data and user information in data bases. Like buffer overflows, the possibilities of performing SQL injection attacks targeting such data bases are left open by unwary programmers. Stephan Scheuermann gives us a deeper insight into the mechanisms behind such attacks in Chapter 3. Cross-site scripting (XSS) is a method to insert malicious code into websites viewed by other users. Michael Blumenstein explains this issue in Chapter 4. Code can be injected in other websites via XSS attacks in order to spy out data of internet users, spoofing subsumes all methods that directly involve taking on a false identity. In Chapter 5, Till Amma shows us different ways how this can be done and how it is prevented. Last but not least, cryptographic methods are used to encode confidential data in a way that even if it got in the wrong hands, the culprits cannot decode it. Over the centuries, many different ciphers have been developed, applied, and finally broken. Ilhan Glogic sketches this history in Chapter 6.},
    urn = {urn:nbn:de:hebis:34-2008041421155},
    sortkey = {0797257proceedingsofthe1st},
    }

2007

  • [DOI] Thomas Weise, Michael Zapf, and Kurt Geihs. Rule-based Genetic Programming. In Proceedings of the 2nd International Conference on Bio-Inspired Models of Network, Information, and Computing Systems (BIONETICS’07), pages 8-15, Budapest, Hungary: Radisson SAS Beke Hotel, December 10–13, 2007. Piscataway, NJ, USA: IEEE Computer Society.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WZG2007DGPFi,
    author = {Thomas Weise and Michael Zapf and Kurt Geihs},
    title = {Rule-based Genetic Programming},
    booktitle = {Proceedings of the 2nd International Conference on Bio-Inspired Models of Network, Information, and Computing Systems (BIONETICS'07)},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Budapest, Hungary: Radisson SAS Beke Hotel},
    pages = {8--15},
    year = {2007},
    month = {December 10--13, },
    url = {http://www.it-weise.de/documents/files/WZG2007RBGP.pdf},
    slides = {http://www.it-weise.de/documents/files/WZG2007RBGP_slides.pdf},
    doi = {10.1109/BIMNICS.2007.4610073},
    abstract = {In this paper we introduce a new approach for Genetic Programming, called rule-based Genetic Programming, or RBGP in short. A program evolved in the RBGP syntax is a list of rules. Each rule consists of two conditions, combined with a logical operator, and an action part. Such rules are independent from each other in terms of position (mostly) and cardinality (always). This reduces the epistasis drastically and hence, the genetic reproduction operations are much more likely to produce good results than in other Genetic Programming methodologies. In order to verify the utility of our idea, we apply RBGP to a hard problem in distributed systems. With it, we are able to obtain emergent algorithms for mutual exclusion at a distributed critical section.},
    eiid = {20084111632894},
    sciids = {BKM77},
    sciwos = {WOS:000268585800002},
    sortkey = {0797187rulebasedgeneticprogramming},
    }
  • Thomas Weise, Steffen Bleul, and Kurt Geihs. Web Service Composition Systems for the Web Service Challenge — A Detailed Review. Technical Report 2007, 7, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, November 19, 2007.
    [PDF] [Bibtex]
    @techreport{WBG2007WSCb,
    author = {Thomas Weise and Steffen Bleul and Kurt Geihs},
    title = {Web Service Composition Systems for the Web Service Challenge {--} A Detailed Review},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik},
    series = {Kasseler Informatikschriften (KIS)},
    number = {2007, 7},
    pages = {1--40},
    year = {2007},
    month = {November 19, },
    url = {http://www.it-weise.de/documents/files/WBG2007WSCb.pdf},
    urn = {urn:nbn:de:hebis:34-2007111919638},
    sortkey = {0797163webservicecompositionsystems},
    }
  • Thomas Weise, Stefan Achler, Martin Göb, Christian Voigtmann, and Michael Zapf. Evolving Classifiers — Evolutionary Algorithms in Data Mining. Kasseler Informatikschriften (KIS) 2007, 4, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, September 28, 2007.
    [PDF] [Bibtex]
    @techreport{WAGVZ2007DMC,
    author = {Thomas Weise and Stefan Achler and Martin G{\"{o}}b and Christian Voigtmann and Michael Zapf},
    title = {Evolving Classifiers {--} Evolutionary Algorithms in Data Mining},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik},
    type = {Kasseler Informatikschriften (KIS)},
    number = {2007, 4},
    pages = {1--20},
    year = {2007},
    month = {September 28, },
    url = {http://www.it-weise.de/documents/files/WAGVZ2007DMC.pdf},
    abstract = {Data mining means to summarize information from large amounts of raw data. It is one of the key technologies in many areas of economy, science, administration and the internet. In this report we introduce an approach for utilizing evolutionary algorithms to breed fuzzy classifier systems. This approach was exercised as part of a structured procedure by the students Achler, G{\"{o}}b, and Voigtmann as contribution to the 2006 Data-Mining-Cup contest, yielding encouragingly positive results.},
    urn = {urn:nbn:de:hebis:34-2007092819260},
    sortkey = {0797106evolvingclassifiersevolutionary},
    }
  • [DOI] Thomas Weise, Michael Zapf, Mohammad Ullah Khan, and Kurt Geihs. Genetic Programming meets Model-Driven Development. In Andreas König, Mario Köppen, Ajith Abraham, Christian Igel, and Nikola Kasabov, editors, Proceedings of the 7th International Conference on Hybrid Intelligent Systems (HIS’07), pages 332-335, Kaiserslautern, Germany: Fraunhofer Center FhG ITWM/FhG IESE, September 17–19, 2007. Piscataway, NJ, USA: IEEE Computer Society.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WZKG2007DGPFg,
    author = {Thomas Weise and Michael Zapf and Mohammad Ullah Khan and Kurt Geihs},
    title = {Genetic Programming meets Model-Driven Development},
    booktitle = {Proceedings of the 7th International Conference on Hybrid Intelligent Systems (HIS'07)},
    editor = {Andreas K{\"{o}}nig and Mario K{\"{o}}ppen and Ajith Abraham and Christian Igel and Nikola Kasabov},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Kaiserslautern, Germany: Fraunhofer Center FhG ITWM/FhG IESE},
    pages = {332--335},
    year = {2007},
    month = {September 17--19, },
    url = {http://www.it-weise.de/documents/files/WZKG2007DGPFg.pdf},
    poster = {http://www.it-weise.de/documents/files/WZKG2007DGPFg_poster.pdf},
    doi = {10.1109/HIS.2007.11},
    abstract = {Genetic programming is known to provide good solutions for many problems like the evolution of network protocols and distributed algorithms. In such cases it is most likely a hardwired module of a design framework that assists the engineer to optimize specific aspects of the system to be developed. It provides its results in a fixed format through an internal interface. In this paper we show how the utility of genetic programming can be increased remarkably by isolating it as a component and integrating it into the model-driven software development process. Our genetic programming framework produces XMI-encoded UML models that can easily be loaded into widely available modeling tools which in turn posses code generation as well as additional analysis and test capabilities. We use the evolution of a distributed election algorithm as an example to illustrate how genetic programming can be combined with model-driven development. This example clearly illustrates the advantages of our approach - the generation of source code in different programming languages.},
    eiid = {20082911386590},
    inspec = {9877168},
    sortkey = {0797095geneticprogrammingmeetsmodeldriven},
    }
  • Thomas Weise. SIGOA+DGPF: Evolutionary Computation and Genetic Programming for Distributed Computing. August 6, 2007.
    [PPT] [Bibtex]
    @misc{W2007DGPFe,
    author = {Thomas Weise},
    title = {SIGOA+DGPF: Evolutionary Computation and Genetic Programming for Distributed Computing},
    publisher = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2007},
    month = {August 6, },
    slides = {http://www.it-weise.de/documents/files/W2007DGPFe.pdf},
    abstract = {A presentation I gave for students interested in doing a project with me as their advisor. Includes an intro into Evolutionary Algorithms, a discussion of the Sigoa Optimization Framework's approach, and an insight into Genetic Programming for distributed systems.},
    sortkey = {0797051sigoadgpfevolutionarycomputationand},
    }
  • [DOI] Steffen Bleul, Thomas Weise, and Kurt Geihs. Making a Fast Semantic Service Composition System Faster. In Proceedings of IEEE Joint Conference on E-Commerce Technology (9th CEC) and Enterprise Computing, E-Commerce and E-Services (4th EEE) (CEC/EEE’07), pages 517-520, Tokyo, Japan: National Center of Sciences, July 23–26, 2007. Piscataway, NJ, USA: IEEE Computer Society. 2nd place in 2007 WSC.
    [PDF] [PPT] [Bibtex]
    @inproceedings{BWG2007WSC,
    author = {Steffen Bleul and Thomas Weise and Kurt Geihs},
    title = {Making a Fast Semantic Service Composition System Faster},
    booktitle = {Proceedings of IEEE Joint Conference on E-Commerce Technology (9th CEC) and Enterprise Computing, E-Commerce and E-Services (4th EEE) (CEC/EEE'07)},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Tokyo, Japan: National Center of Sciences},
    pages = {517--520},
    year = {2007},
    month = {July 23--26, },
    url = {http://www.it-weise.de/documents/files/BWG2007WSC.pdf},
    slides = {http://www.it-weise.de/documents/files/BWG2007WSC_slides.pdf},
    doi = {10.1109/CEC-EEE.2007.62},
    note = {2nd place in 2007 WSC.},
    abstract = {Service Oriented Architecture (SOA) is a flexible software design paradigm for enterprises. The workflows of a company are implemented as services which can be arranged, updated and managed at runtime without interfering with ongoing business. Service management aims at providing undisturbed access to services. Its efficiency strongly depends on a fast response time in the case of a failure. This is hard to achieve since the relations between applications and services require comprehensive knowledge and lack transparency for administrators. Self-organizing approaches promise a solution by automating service discovery. In this paper we present a service discovery system which enables service compositions from semantic descriptions stored in a knowledge base. Therefore, it utilizes multiple composition algorithms from which the most appropriate set is selected and applied according to the size of the knowledge base and the available processors. The functionality of our system is made available through a Web Service interface itself. It is thus applicable in self-organizing service management systems with any number of services and ontologies.},
    eiid = {20083511485208},
    sciids = {BGR20},
    sciwos = {WOS:000250044300070},
    inspec = {9868637},
    sortkey = {0797035makingafastsemantic},
    }
  • Thomas Weise, Michael Zapf, Mohammad Ullah Khan, and Kurt Geihs. Genetic Programming meets Model-Driven Development. Kasseler Informatikschriften (KIS) 2007, 2, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, July 2, 2007.
    [PDF] [Bibtex]
    @techreport{WZKG2007DGPFd,
    author = {Thomas Weise and Michael Zapf and Mohammad Ullah Khan and Kurt Geihs},
    title = {Genetic Programming meets Model-Driven Development},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik},
    type = {Kasseler Informatikschriften (KIS)},
    number = {2007, 2},
    pages = {1--8},
    year = {2007},
    month = {July 2, },
    url = {http://www.it-weise.de/documents/files/WZKG2007DGPFd.pdf},
    abstract = {Genetic programming is known to provide good solutions for many problems like the evolution of network protocols and distributed algorithms. In such cases it is most likely a hardwired module of a design framework that assists the engineer to optimize specific aspects of the system to be developed. It provides its results in a fixed format through an internal interface. In this paper we show how the utility of genetic programming can be increased remarkably by isolating it as a component and integrating it into the model-driven software development process. Our genetic programming framework produces XMI-encoded UML models that can easily be loaded into widely available modeling tools which in turn posses code generation as well as additional analysis and test capabilities. We use the evolution of a distributed election algorithm as an example to illustrate how genetic programming can be combined with model-driven development. This example clearly illustrates the advantages of our approach - the generation of source code in different programming languages.},
    urn = {urn:nbn:de:hebis:34-2007070218786},
    sortkey = {0797014geneticprogrammingmeetsmodeldriven},
    }
  • [DOI] Thomas Weise, Kurt Geihs, and Philipp Andreas Baer. Genetic Programming for Proactive Aggregation Protocols. In Bart l, Andrzej Dzieliński, Marcin Iwanowski, and Bernardete Ribeiro, editors, Proceedings of the 8th International Conference on Adaptive and Natural Computing Algorithms, Part I (ICANNGA’07), volume 4431/2007 of Lecture Notes in Computer Science (LNCS), pages 167-173, Warsaw, Poland: Warsaw University, April 11–17, 2007. Berlin, Germany: Springer-Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WGB2007DGPFb,
    author = {Thomas Weise and Kurt Geihs and Philipp Andreas Baer},
    title = {Genetic Programming for Proactive Aggregation Protocols},
    booktitle = {Proceedings of the 8th International Conference on Adaptive and Natural Computing Algorithms, Part I (ICANNGA'07)},
    editor = {Bart{\l}omiej Beliczy{\'{n}}ski and Andrzej Dzieli{\'{n}}ski and Marcin Iwanowski and Bernardete Ribeiro},
    publisher = {Berlin, Germany: Springer-Verlag GmbH},
    address = {Warsaw, Poland: Warsaw University},
    series = {Lecture Notes in Computer Science (LNCS)},
    volume = {4431/2007},
    pages = {167--173},
    year = {2007},
    month = {April 11--17, },
    url = {http://www.it-weise.de/documents/files/W2007DGPFb.pdf},
    slides = {http://www.it-weise.de/documents/files/W2007DGPFb_slides.pdf},
    doi = {10.1007/978-3-540-71618-1_19},
    abstract = {We present an approach for automated generation of proactive aggregation protocols using Genetic Programming. First a short introduction into aggregation and proactive protocols is given. We then show how proactive aggregation protocols can be specified abstractly. To be able to use Genetic Programming to derive such protocol specifications, we describe a simulation based fitness assignment method. We have applied our approach successfully to the derivation of aggregation protocols. Experimental results are presented that were obtained using our own Distributed Genetic Programming Framework. The results are very encouraging and demonstrate clearly the utility of our approach.},
    eiid = {20080311022959},
    sciids = {BGC96},
    sciwos = {WOS:000246097200019},
    sortkey = {0796924geneticprogrammingforproactive},
    }
  • [DOI] Philipp Andreas Baer, Roland Reichle, Michael Zapf, Thomas Weise, and Kurt Geihs. A Generative Approach to the Development of Autonomous Robot Software. In Theodore Allan Bapty, Michael G. Hinchey, and Roy Sterritt, editors, Proceedings of 4th IEEE Workshop on Engineering of Autonomic and Autonomous Systems (EASe’07), Tucson, AZ, USA, March 26–29, 2007. Washington, DC, USA: IEEE Computer Society.
    [PDF] [PPT] [Bibtex]
    @inproceedings{BRZWG2007AR,
    author = {Philipp Andreas Baer and Roland Reichle and Michael Zapf and Thomas Weise and Kurt Geihs},
    title = {A Generative Approach to the Development of Autonomous Robot Software},
    booktitle = {Proceedings of 4th IEEE Workshop on Engineering of Autonomic and Autonomous Systems (EASe'07)},
    editor = {Theodore Allan Bapty and Michael G. Hinchey and Roy Sterritt},
    publisher = {Washington, DC, USA: IEEE Computer Society},
    address = {Tucson, AZ, USA},
    year = {2007},
    month = {March 26--29, },
    url = {http://www.it-weise.de/documents/files/BRZWG2007AR.pdf},
    slides = {http://www.it-weise.de/documents/files/BRZWG2007AR_slides.pdf},
    doi = {10.1109/EASE.2007.2},
    abstract = {The integration of new or existing software components into established architectures and the ability to deal with heterogeneity are key requirements for middleware and development frameworks for robotic systems. This paper presents SPICA, a software development framework for communication infrastructures of autonomous mobile robots. Utilizing the model-driven software development paradigm, communication and data flow can be defined on an abstract level. For this purpose, domain-specific languages and tools are provided that allow specification and generation of module communication infrastructures for communication between modules along with primitives for data management. The high-level platform-independent specifications are automatically transformed into low-level platform and programming language-specific source code. We illustrate the applicability of our approach with an elaborate example describing the design of a soccer robot architecture that has proven its strength during RoboCup 2006. Our experiences have revealed that SPICA is advantageous for prototyping as well as for building high performance systems.},
    eiid = {20073510787475},
    sciids = {BGD54},
    sciwos = {WOS:000246173800005},
    sortkey = {0796906agenerativeapproachto},
    }

2006

  • Thomas Weise and Kurt Geihs. DGPF — An Adaptable Framework for Distributed Multi-Objective Search Algorithms Applied to the Genetic Programming of Sensor Networks. In Bogdan Filipič and Jurij Šilc, editors, Proceedings of the Second International Conference on Bioinspired Optimization Methods and their Applications (BIOMA’06), Informacijska Družba (Information Society), pages 157-166, Ljubljana, Slovenia: Jožef Stefan International Postgraduate School, October 9–10, 2006. Ljubljana, Slovenia: Jožef Stefan Institute.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WG2006DGPFc,
    author = {Thomas Weise and Kurt Geihs},
    title = {DGPF {--} An Adaptable Framework for Distributed Multi-Objective Search Algorithms Applied to the Genetic Programming of Sensor Networks},
    booktitle = {Proceedings of the Second International Conference on Bioinspired Optimization Methods and their Applications (BIOMA'06)},
    editor = {Bogdan Filipi{\v{c}} and Jurij {\v{S}}ilc},
    publisher = {Ljubljana, Slovenia: Jo{\v{z}}ef Stefan Institute},
    address = {Ljubljana, Slovenia: Jo{\v{z}}ef Stefan International Postgraduate School},
    series = {Informacijska Dru{\v{z}}ba (Information Society)},
    pages = {157--166},
    year = {2006},
    month = {October 9--10, },
    url = {http://www.it-weise.de/documents/files/WG2006DGPFc.pdf},
    slides = {http://www.it-weise.de/documents/files/WG2006DGPFc_slides.pdf},
    abstract = {We present DGPF, a framework providing multi-objective, auto-adaptive search algorithms with a focus on Genetic Programming. We first introduce a Common Search API, suitable to explore arbitrary problem spaces with different search algorithms. Using our implementation of Genetic Algorithms as an example, we elaborate on the distribution utilities of the framework which enable local, Master/Slave, Peer-To-Peer, and P2P/MS hybrid distributed search execution. We also discuss how heterogeneous searches consisting of multiple, cooperative search algorithms can be constructed. Sensor networks are distributed systems of nodes with scarce resources. We demonstrate how Genetic Programming based on our framework can be applied to create algorithms for sensor nodes that use these resources very efficiently.},
    sortkey = {0796723dgpfanadaptable},
    }
  • Thomas Weise and Kurt Geihs. Genetic Programming Techniques for Sensor Networks. In Pedro José Marrón, editor, 5. GI/ITG KuVS Fachgespräch “Drahtlose Sensornetze”, volume 2006/07, pages 21-25. Stuttgart, Germany: Universität Stuttgart, Fakultät 5: Informatik, Elektrotechnik und Informationstechnik, Institut für Parallele und Verteilte Systeme (IPVS), July 17–18, 2006.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WG2006DGPFb,
    author = {Thomas Weise and Kurt Geihs},
    title = {Genetic Programming Techniques for Sensor Networks},
    booktitle = {5. GI/ITG KuVS Fachgespr{\"{a}}ch {``}Drahtlose Sensornetze{''}},
    editor = {Pedro Jos{\'{e}} Marr{\'{o}}n},
    publisher = {Stuttgart, Germany: Universit{\"{a}}t Stuttgart, Fakult{\"{a}}t 5: Informatik, Elektrotechnik und Informationstechnik, Institut f{\"{u}}r Parallele und Verteilte Systeme (IPVS)},
    volume = {2006/07},
    pages = {21--25},
    year = {2006},
    month = {July 17--18, },
    url = {http://www.it-weise.de/documents/files/WG2006DGPFb.pdf},
    slides = {http://www.it-weise.de/documents/files/WG2006DGPFb_slides.pdf},
    abstract = {In this paper we present an approach to automated program code generation for sensor nodes and other small devices. Using Genetic Programming, we are able to discover algorithms that solve certain problems. Furthermore, non-functional properties like code size, memory usage, and communication frequency can be optimized using multiobjective search techniques. The evolution of algorithms requires program testing, which we perform using a customized simulation environment for sensor networks. The simulation model takes into account characteristic features of sensor nodes, such as unreliable communication and resource constraints. An application example is presented that demonstrates the feasibility of our approach and its potential to create robust and adaptive code for sensor network applications.},
    urn = {urn:nbn:de:bsz:93-opus-28388},
    sortkey = {0796632geneticprogrammingtechniquesfor},
    }
  • Steffen Bleul, Thomas Weise, and Kurt Geihs. An Ontology for Quality-Aware Service Discovery. International Journal of Computer Systems Science and Engineering (CSSE), 21(4):227-234, July 2006. Special issue on {“}Engineering Design and Composition of Service-Oriented Applications{”}
    [PDF] [Bibtex]
    @article{BWG2006QASD,
    author = {Steffen Bleul and Thomas Weise and Kurt Geihs},
    title = {An Ontology for Quality-Aware Service Discovery},
    publisher = {Leicester, UK: CRL Publishing Limited},
    journal = {International Journal of Computer Systems Science and Engineering (CSSE)},
    number = {4},
    volume = {21},
    pages = {227--234},
    year = {2006},
    month = {July},
    url = {http://www.it-weise.de/documents/files/BWG2006QASD.pdf},
    note = {Special issue on {``}Engineering Design and Composition of Service-Oriented Applications{''}},
    abstract = {The fast emergence and acceptance of service oriented architectures leads to fast development of extensional technologies like service delivery, discovery and composition. As main effort is being spent on automatic discovery and composition, current solutions do not reflect real world scenarios sufficiently. Services are offered by different vendors with different quality levels and prices. Large service oriented architectures with dynamic service compositions are not able to adapt without manual inspection of service quality and negotiation of service contracts. We propose an ontology for modelling Quality of Services (QoS) and Service- Level-Agreements (SLA). A semantic approach should bridge the gap of different terminology, languages and metrics making Service-Level offers and requests agent understandable and automatic quality-aware discovery possible.},
    eiid = {20064410208380},
    sciids = {095XP},
    sortkey = {0796614anontologyforqualityaware},
    }
  • [DOI] Steffen Bleul, Thomas Weise, and Kurt Geihs. Large-Scale Service Composition in Semantic Service Discovery. In Andreas Wombacher, Christian Huemer, and Markus Stolze, editors, Proceedings of 2006 IEEE Joint Conference on E-Commerce Technology and Enterprise Computing, E-Commerce and E-Services (CEC/EEE’06), pages 427-429, Millbrae, CA, USA: Westin San Francisco Airport, June 26–29, 2006. Piscataway, NJ, USA: IEEE Computer Society. 1st place in 2006 WSC.
    [PDF] [PPT] [Bibtex]
    @inproceedings{BWG2006WSC,
    author = {Steffen Bleul and Thomas Weise and Kurt Geihs},
    title = {Large-Scale Service Composition in Semantic Service Discovery},
    booktitle = {Proceedings of 2006 IEEE Joint Conference on E-Commerce Technology and Enterprise Computing, E-Commerce and E-Services (CEC/EEE'06)},
    editor = {Andreas Wombacher and Christian Huemer and Markus Stolze},
    publisher = {Piscataway, NJ, USA: IEEE Computer Society},
    address = {Millbrae, CA, USA: Westin San Francisco Airport},
    pages = {427--429},
    year = {2006},
    month = {June 26--29, },
    url = {http://www.it-weise.de/documents/files/BWG2006WSC.pdf},
    slides = {http://www.it-weise.de/documents/files/BWG2006WSC_slides.pdf},
    doi = {10.1109/CEC-EEE.2006.59},
    note = {1st place in 2006 WSC.},
    abstract = {Self-Healing and self-optimizing service based applications are important steps towards the self-organizing ServiceOriented Architectures (SOA). Self-Organizing SOAs replace services by functional equivalent services in the case of faults or in respect of quality of service. These features depend on automatic service discovery which provides service alternatives. We enter the WSC{\textquoteright}06 contest to present a semantic service discovery system for large sets of services. A recursive algorithm builds service compositions by adding services in each iteration. The search works backwards, since we add services that produce a certain output regardless of its input parameters. A valid service composition produces a set of queried output parameters and input parameters necessary for the composed services. The algorithm is improved by using efficient data structures in our service composition system.},
    eiid = {20070110350633},
    inspec = {9189339},
    sortkey = {0796608largescaleservicecompositionin},
    }
  • Thomas Weise. Genetic Programming for Sensor Networks. Technical Report, Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group, January 2006.
    [PDF] [Bibtex]
    @techreport{W2006DGPFa,
    author = {Thomas Weise},
    title = {Genetic Programming for Sensor Networks},
    institution = {Kassel, Hesse, Germany: University of Kassel, Fachbereich 16: Elektrotechnik/Informatik, Distributed Systems Group},
    year = {2006},
    month = {January},
    url = {http://www.it-weise.de/documents/files/W2006DGPFa.pdf},
    abstract = {DGPF Home: http://dgpf.sourceforge.net/{\verb=\=} In this paper we present an approach to automated program code generation for sensor nodes and other small devices using Genetic Programming. We give a short introduction to Genetic Algorithms. Our new Distributed Genetic Programming Framework facilitates the development of sensor network applications. Genetic evolution of programs requires program testing. Therefore we use a simulation environment for distributed systems of sensor nodes. The simulation model takes into account characteristic features of sensor nodes, such as unreliable communication and resource constraints. Two application examples are presented that demonstrate the feasibility of our approach and its potential to create robust and adaptive code for sensor network applications.},
    sortkey = {0796416geneticprogrammingforsensor},
    }

2005

  • Steffen Bleul and Thomas Weise. An Ontology for Quality-Aware Service Discovery. In Christian Zirpins, Guadalupe Ortiz, Winfried Lamersdorf, and Wolfgang Emmerich, editors, First International Workshop on Engineering Service Compositions (WESC’05), volume RC23821 of IBM Research Report, Amsterdam, The Netherlands, December 12, 2005.
    [PDF] [PPT] [Bibtex]
    @inproceedings{BW2005QASD,
    author = {Steffen Bleul and Thomas Weise},
    title = {An Ontology for Quality-Aware Service Discovery},
    booktitle = {First International Workshop on Engineering Service Compositions (WESC'05)},
    editor = {Christian Zirpins and Guadalupe Ortiz and Winfried Lamersdorf and Wolfgang Emmerich},
    institution = {Yorktown Heights, NY, USA: IBM Research Division},
    address = {Amsterdam, The Netherlands},
    series = {IBM Research Report},
    volume = {RC23821},
    year = {2005},
    month = {December 12, },
    url = {http://www.it-weise.de/documents/files/BW2005QASD.pdf},
    slides = {http://fresco-www.informatik.uni-hamburg.de/wesc05/slides/wesc05_1-5_bleul.pdf},
    abstract = {The fast emergence and acceptance of service oriented architectures leads to fast development of extensional technologies like service delivery, discovery and composition. As main effort is being spent on automatic discovery and composition, current solutions do not reflect real world scenarios sufficiently. Services are offered by different vendors with different quality levels and prices. Large service oriented architectures with dynamic service compositions are not able to adapt without manual inspection of service quality and negotiation of service contracts. We propose an ontology for modelling Quality of Services (QoS) and Service- Level-Agreements (SLA). A semantic approach should bridge the gap of different terminology, languages and metrics making Service-Level offers and requests agent understandable and automatic quality-aware discovery possible.},
    sortkey = {0796395anontologyforqualityaware},
    }
  • Elke Wällnitz and Thomas Weise. Ein plattformunabhängiger XML-Editor für die Erstellung und Verwaltung von E-Learning-Inhalten. In Ulrike Lucke, Kristin Nölting, and Djamshid Tavangarian, editors, Workshop Proceedings DeLFI 2005 und GMW05 [Die 3. e-Learning Fachtagung Informatik + Gesellschaft für Medien in der Wissenschaft], pages 83-92, Rostock, Germany, September 13–16, 2005. Berlin, Germany: Logos Verlag Berlin {–} Verlag für wissenschaftliche Publikationen.
    [Bibtex]
    @inproceedings{WW2005EPUXEFDEUVVELI,
    author = {Elke W{\"{a}}llnitz and Thomas Weise},
    title = {Ein plattformunabh{\"{a}}ngiger XML-Editor f{\"{u}}r die Erstellung und Verwaltung von E-Learning-Inhalten},
    booktitle = {Workshop Proceedings DeLFI 2005 und GMW05 [Die 3. e-Learning Fachtagung Informatik + Gesellschaft f{\"{u}}r Medien in der Wissenschaft]},
    editor = {Ulrike Lucke and Kristin N{\"{o}}lting and Djamshid Tavangarian},
    publisher = {Berlin, Germany: Logos Verlag Berlin {--} Verlag f{\"{u}}r wissenschaftliche Publikationen},
    address = {Rostock, Germany},
    pages = {83--92},
    year = {2005},
    month = {September 13--16, },
    abstract = {Der Beitrag stellt einen in Java programmierten allgemeinen XML- Editor vor, der den Dialekt KML (Knowledge Management Language) der im Rahmen des Verbundprojektes Wissenswerkstatt Rechensysteme entwickelten Markup-Language <ML>3 nutzt. Dieser WYSIWYG-Editor besteht aus zwei Teilen. Zum ersten ist es mo{\"{a}}glich, XML-Dateien {--} ohne detaillierte Kenntnisse zum Dialekt {--} komfortabel zu erstellen und zu modifizieren (Inhaltsteil). Damit kann ein zentraler Wissenspool fu{\"{a}}r E-Learning-Module auf der Basis von XML geschaffen werden. Der zweite Teil (Didaktik) ermo{\"{a}}glicht es per Drag und Drop aus dem Inhaltspool beliebige E-Learning-Kursmaterialien zusammen zu stellen und mit entsprechenden Schaltfl{\"{a}}chen die gew{\"{u}}nschten Ausgabeformate (Web- Dokumente, Skripte und Folien) unter Beachtung didaktischer Kriterien (Zielgruppe, Anforderungsniveau, didaktische Struktur) zu erzeugen. Ziel des Beitrages ist es, den Prototyp des Editors einer breiten O{\"{a}}ffentlichkeit zur Nutzung zug{\"{a}}nglich zu machen, aber auch Interessenten fu{\"{a}}r die Weiterentwicklung des Open-Source-Projektes zu gewinnen. Die Implementierung jedes beliebigen XML-Dialektes u{\"{a}}ber Programmierung eines Plugins macht den WYSIWYG-Editor universell einsetzbar.},
    sortkey = {0796297einplattformunabhngigerxmleditorfr},
    }
  • Elke Wällnitz and Thomas Weise. Platform-independent KML Editor for Creating E-Learning Modules based on XML. In Piet Kommers and Griff Richards, editors, Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA’05), pages 4700-4704, Montréal, QC, Canada: Le Centre Sheraton Hotel Montréal, June 27, 2005. Chesapeake, VA, USA: Association for the Advancement of Computing in Education (AACE).
    [PDF] [PPT] [Bibtex]
    @inproceedings{WW2005KMLb,
    author = {Elke W{\"{a}}llnitz and Thomas Weise},
    title = {Platform-independent KML Editor for Creating E-Learning Modules based on XML},
    booktitle = {Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA'05)},
    editor = {Piet Kommers and Griff Richards},
    publisher = {Chesapeake, VA, USA: Association for the Advancement of Computing in Education (AACE)},
    address = {Montr{\'{e}}al, QC, Canada: Le Centre Sheraton Hotel Montr{\'{e}}al},
    pages = {4700--4704},
    year = {2005},
    month = {June 27, },
    url = {http://www.it-weise.de/documents/files/WW2005KMLb.pdf},
    slides = {http://www.it-weise.de/documents/files/WW2005KMLb_slides.pdf},
    abstract = {The chair of Operating Systems of Chemnitz University of Technology participated in a joint project ``Knowledge Workshop Computing Systems``. As a result, twelve universities across Germany created a total of 145 e-learning modules for the subject of Technical Computer Science. Experiences from this project ``in terms of creation of modules based on XML as well as from use in presence teaching at schools`` initiated a second project creating a WYSIWIG editor which also allowed teachers creating learning modules who are not skilled in using XML directly. Experiences from the first project were published in [3]. This paper presents the WYSIWIG editor KML which has been implemented in Java. The editor uses a special markup language named 3.The paper presents experiences from using this editor for creating e-learning content in schools, colleges and professional schools in the Federal State of Saxony in Germany.},
    sortkey = {0796212platformindependentkmleditorfor},
    }
  • Volker Fickert, Winfried Kalfa, and Thomas Weise. Framework for Distributed Simulation and Measuring of Complex Relations of Operating System Components. In Piet Kommers and Griff Richards, editors, Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA’05), pages 3865-3870, Montréal, QC, Canada: Le Centre Sheraton Hotel Montréal, June 27, 2005. Chesapeake, VA, USA: Association for the Advancement of Computing in Education (AACE).
    [PDF] [PPT] [Bibtex]
    @inproceedings{FKW2005OSF,
    author = {Volker Fickert and Winfried Kalfa and Thomas Weise},
    title = {Framework for Distributed Simulation and Measuring of Complex Relations of Operating System Components},
    booktitle = {Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA'05)},
    editor = {Piet Kommers and Griff Richards},
    publisher = {Chesapeake, VA, USA: Association for the Advancement of Computing in Education (AACE)},
    address = {Montr{\'{e}}al, QC, Canada: Le Centre Sheraton Hotel Montr{\'{e}}al},
    pages = {3865--3870},
    year = {2005},
    month = {June 27, },
    url = {http://www.it-weise.de/documents/files/FKW2005OSF.pdf},
    slides = {http://www.it-weise.de/documents/files/FKW2005OSF_slides.pdf},
    abstract = {Collecting experience with the help of experiments makes it much easier to understand complex relations. But with modern computing systems it is hardly possible to get a direct insight into internal processes. A current project for the simulation and realization of measuring of processes in operating systems is presented in my lecture. Its main point is the visualization of such processes. Because of that distributed applications which simulate different components of an operating system or which, with the help of appropriate drivers, are able to carry out measurements on real machines were drawn up with JAVA. During the simulation and measurements learners can influence parameters of different components and experience their effects directly. Thus in teaching operating systems it will be possible to illustrate processes which are difficult to understand and to influence complex relations immediately. The software and more information about this work can be found here.},
    sortkey = {0796212frameworkfordistributedsimulation},
    }
  • Thomas Weise. Entwicklung eines WYSIWYG Editors für das Erstellen von Lehrmaterial im XML Format. In Informatiktage’05, Sankt Augustin, Nordrhein Westfalen, Germany: Schloss Birlinghoven, April 8, 2005. Bonn, North Rhine-Westphalia, Germany: Gesellschaft für Informatik e.V. (GI).
    [PDF] [PPT] [Bibtex]
    @inproceedings{W2005KML,
    author = {Thomas Weise},
    title = {Entwicklung eines WYSIWYG Editors f{\"{u}}r das Erstellen von Lehrmaterial im XML Format},
    booktitle = {Informatiktage'05},
    publisher = {Bonn, North Rhine-Westphalia, Germany: Gesellschaft f{\"{u}}r Informatik e.V. (GI)},
    address = {Sankt Augustin, Nordrhein Westfalen, Germany: Schloss Birlinghoven},
    year = {2005},
    month = {April 8, },
    url = {http://www.it-weise.de/documents/files/W2005KML.pdf},
    slides = {http://www.it-weise.de/documents/files/W2005KML_slides.pdf},
    abstract = {In der Arbeit wird ein WYSIWYG-Editor zum Erstellen von Lehrmaterial f{\"{u}}r das E-Learning vorgestellt. Es wird ein auf XML basierendes Speicherformat genutzt. Dieses erm{\"{o}}glicht das Auszeichnen der Texte mit semantischen Markierungen, das Anbinden von Multimedia-Objekten und Simulationen. Das erstelle Lehrmaterial kann nach didaktischen Gesichtspunkten umgeordnet und in andere Formate wie XHTML und PDF konvertiert werden.},
    sortkey = {0796127entwicklungeineswysiwygeditors},
    }
  • Thomas Weise. Entwicklung eines WYSIWYG Editors für das Erstellen von Lehrmaterial im XML Format. Master’s thesis, Chemnitz, Sachsen, Germany: Chemnitz University of Technology, Faculty of Computer Science, Operating Systems Group, April 5, 2005.
    [PDF] [PPT] [Bibtex]
    @mastersthesis{W2005MT,
    author = {Thomas Weise},
    title = {Entwicklung eines WYSIWYG Editors f{\"{u}}r das Erstellen von Lehrmaterial im XML Format},
    school = {Chemnitz, Sachsen, Germany: Chemnitz University of Technology, Faculty of Computer Science, Operating Systems Group},
    year = {2005},
    month = {April 5, },
    url = {http://www.it-weise.de/documents/files/W2005MT.pdf},
    slides = {http://www.it-weise.de/documents/files/W2005MT_slides.pdf},
    abstract = {Die vorliegende Arbeit beschreibt den Entwurf, die Entwicklung und die Anpassung eines XML-WYSIWYG-Editors f{\"{u}}r die Verwendung in der Lehre. Der praktische Teil der Arbeit hat einen Editor zum Ergebnis, welcher den XML-Dialekt KML implementiert, mit dessen Hilfe ML3-formattiertes Lehrmaterial erstellt werden kann. Der Entwurf des Editors ist jedoch besonders auf Erweiterbarkeit und Wartbarkeit gewichtet. Dadurch wird der erstellte Editor f{\"{u}}r beliebige XML-Dialekte mit geringem Aufwand anpassbar.},
    advisor = {Winfried Kalfa and Elke W{\"{a}}llnitz},
    sortkey = {0796124entwicklungeineswysiwygeditors},
    }
  • Elke Wällnitz and Thomas Weise. Der plattformunabhängige KML-Editor als Werkzeug zur Entwicklung von E-Learning-Modulen auf der Basis von XML. In Klaus Fellbaum, editor, Tagungsband zum 3. Workshop über die Grundfragen multimedialen Lehrens und Lernens (GML2’05), pages 215-224, Cottbus, Brandenburg, Germany: Brandenburgische Technische Universität (BTU) Cottbus, March 7–9, 2005. Aachen, North Rhine-Westphalia, Germany: Shaker Verlag GmbH.
    [PDF] [PPT] [Bibtex]
    @inproceedings{WW2005KMLa,
    author = {Elke W{\"{a}}llnitz and Thomas Weise},
    title = {Der plattformunabh{\"{a}}ngige KML-Editor als Werkzeug zur Entwicklung von E-Learning-Modulen auf der Basis von XML},
    booktitle = {Tagungsband zum 3. Workshop {\"{u}}ber die Grundfragen multimedialen Lehrens und Lernens (GML2'05)},
    editor = {Klaus Fellbaum},
    publisher = {Aachen, North Rhine-Westphalia, Germany: Shaker Verlag GmbH},
    address = {Cottbus, Brandenburg, Germany: Brandenburgische Technische Universit{\"{a}}t (BTU) Cottbus},
    pages = {215--224},
    year = {2005},
    month = {March 7--9, },
    url = {http://www.it-weise.de/documents/files/WW2005KMLa.pdf},
    slides = {http://www.it-weise.de/documents/files/WW2005KMLa_slides.pdf},
    abstract = {Der Lehrstuhl Betriebssysteme der TU Chemnitz beteiligte sich an dem vom Bundesministerium f{\"{u}}r Bildung und Forschung gef{\"{o}}rderten Verbundprojekt {``}Wissenswerkstatt Rechensysteme{''}. Die im Rahmen dieses Projektes gewonnenen und zum GML\ensuremath{^3}-Workshop im Jahr 2004 vorgestellten Erfahrungen - sowohl hinsichtlich der Erstellung der Module auf der Basis von XML-Dokumenten als auch des die Pr{\"{a}}senzlehre begleitenden Einsatzes - initiierten ein neues Projekt mit dem Ziel der Entwicklung eines WYSIWYG-Editors, mit dessen Hilfe auch informatisch nicht {``}vorbelastete{''} Lehrkr{\"{a}}fte ebenso wie Informatiker die Inhalte f{\"{u}}r E-Learning-Module effizient und komfortabel erfassen und mit entsprechenden Schaltfl{\"{a}}chen die gew{\"{u}}nschten Ausgabeformate (Web-Dokumente, Skripte und Folien) unter Beachtung didaktischer Kriterien (Zielgruppe, Anforderungsniveau, didaktische Struktur) erzeugen k{\"{o}}nnen. Der Vortrag stellt diesen in Java programmierten und damit universell einsetzbaren Editor vor, der den Dialekt KML (Knowledge Management Language) der Markup-Language ML\ensuremath{^3} nutzt. Bemerkungen zum Konzept der Erprobung des Editors hinsichtlicht Eignung, Akzeptanz und Einbindung der mit Hilfe des Editors erstellten und modifizierbaren Produkte (E-Learning-Module) in akademische und schulische Lehre schlie{\ss}en den Vortrag ab.},
    sortkey = {0796093derplattformunabhngigekmleditorals},
    }

Leave a Reply

Your email address will not be published.

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code class="" title="" data-url=""> <del datetime=""> <em> <i> <q cite=""> <strike> <strong> <pre class="" title="" data-url=""> <span class="" title="" data-url="">