{"title":"Rule extraction from an RBF classifier based on class-dependent features","authors":"Xiuju FU, Lipo Wang","doi":"10.1109/CEC.2002.1004536","DOIUrl":"https://doi.org/10.1109/CEC.2002.1004536","url":null,"abstract":"Rule extraction is a technique for knowledge discovery. Compact rules with high accuracy are desirable. Due to the curse of irrelevant features to classifiers, feature selection techniques are discussed widely. We propose to extract rules based on class-dependent features from a radial basis function (RBF) classifier by genetic algorithms (GA). Each Gaussian kernel function of the RBF neural network is active for only a subset of patterns which are approximately of the same class. Since each feature may have different capabilities in discriminating different classes, features should be masked differently for different classes. In our method, different feature masks are used for different groups of Gaussian kernel functions corresponding to different classes. The feature masks are adjusted by GA. The classification accuracy of the RBF neural network is used as the fitness function. Thus, the dimensionality of a data set is reduced. Concise rules with high accuracy are subsequently obtained based on the class-dependent features. We demonstrate our approach using computer simulations.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115364022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kevin P. Anchor, Paul D. Williams, G. Gunsch, G. Lamont
{"title":"The computer defense immune system: current and future research in intrusion detection","authors":"Kevin P. Anchor, Paul D. Williams, G. Gunsch, G. Lamont","doi":"10.1109/CEC.2002.1004384","DOIUrl":"https://doi.org/10.1109/CEC.2002.1004384","url":null,"abstract":"The Computer Defense Immune System is an artificial immune system for detecting computer viruses and network intrusions. This paper discusses the system architecture, presents current research and results in enhancing the system, and discusses planned future research topics that will be used to improve the system's capabilities.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115564137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Capturing human judgment to simulate objective function","authors":"A. Moroni, F. V. Zuben, J. Manzolli, A. Mammana","doi":"10.1109/CEC.2002.1006290","DOIUrl":"https://doi.org/10.1109/CEC.2002.1006290","url":null,"abstract":"Evolutionary concepts are being used to support the implementation of higher level information processing devices than could be easily built by human design. We introduce an input device that proved to be appropriate for the study of human perception. The sequence of judgments can be captured to simulate an objective function. The repeated interaction between user and computer allows the user to search hyperspaces of possible solutions without being required to design equations by hand or even understand them. Two musical environments, Vox Populi, an evolutionary composition system, and InstrumentAll, a combined hardware and software musical interface, are briefly described.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115668335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Issues in designing a neutral genotype-phenotype mapping","authors":"R. Shipman, M. Shackleton","doi":"10.1109/CEC.2002.1004441","DOIUrl":"https://doi.org/10.1109/CEC.2002.1004441","url":null,"abstract":"This paper discusses issues that arise when a redundant genotype-phenotype mapping is used in the context of a real-world application. Previous studies have suggested that a redundant mapping, which introduces neutrality into the search space, can provide a beneficial role. Many of the studies to date have concentrated on relatively abstract search spaces. In this paper we consider these issues in the context of a specific real-world application. We show that redundancy can indeed be useful, but that it must be carefully introduced with due consideration to details of the application being considered, and its associated search space. Although the details of the redundant encoding are specific to the application, we seek to deduce some heuristics that are likely to prove useful for designing genetic encodings for other problems to facilitate search for fitter phenotypes.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124322557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Realizing unstable social efficiency with mutual learning of meta-rules","authors":"Y. Murakami, H. Sato, A. Namatame","doi":"10.1109/CEC.2002.1004468","DOIUrl":"https://doi.org/10.1109/CEC.2002.1004468","url":null,"abstract":"It is an interesting question to answer how the society groups its way towards efficient equilibrium in an imperfect world when self-interested agents learn from others. In this paper, we focus on mutual learning. Each agent learns the rule of interaction in the negotiation situations formulated as hawk-dove games. It is known the mixed Nash strategy of hawk-dove games will result in an inefficient equilibrium. In this paper we consider both mimicry and crossover as the methodology of individual learning. We show that all agents mutually learn to behave as doves, which result in social efficiency. We also investigate the meta-rules acquired by agents through mutual learning. With mimicry the meta-rules of all agents are categorized into a few meta-rules. On the other hand, with crossover, almost all agents have acquired different meta-rules with one common feature.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116027297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Genetic algorithm-derived digital integrators and their applications in discretization of continuous systems","authors":"C. Hsu, Wei-Yen Wang, Chih-Yung Yu","doi":"10.1109/CEC.2002.1006275","DOIUrl":"https://doi.org/10.1109/CEC.2002.1006275","url":null,"abstract":"A set of enhanced digital integrators (EDI) with improved accuracy using genetic algorithms are proposed in this paper. By specifying a desired power for the integrator to be sought and the interval for comparison, chromosomes consisting of parameters of the enhanced digital integrator are then searched by the genetic algorithm based on root mean squared (RMS) error between the original integrator and candidates of the enhanced digital integrator. Thus, all the best parameters of an optimal enhanced digital integrator can be evolutionarily obtained. To demonstrate the effectiveness of the proposed approach, the derived enhanced digital integrators are used to obtain the discrete approximation for continuous systems.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122164223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A resource limited artificial immune classifier","authors":"A. Watkins, L. Boggess","doi":"10.1109/CEC.2002.1007049","DOIUrl":"https://doi.org/10.1109/CEC.2002.1007049","url":null,"abstract":"This paper presents a new supervised learning paradigm inspired by mechanisms exhibited in immune systems. This work provides an explication of a resource limited artificial immune classification algorithm, named AIRS (Artificial Immune Recognition System), and provides results on simulated data sets to demonstrate the fundamental behavior of the algorithm.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116865988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ant colony optimization for FOP shop scheduling: a case study on different pheromone representations","authors":"C. Blum, M. Sampels","doi":"10.1109/CEC.2002.1004474","DOIUrl":"https://doi.org/10.1109/CEC.2002.1004474","url":null,"abstract":"In this work we deal with the FOP shop scheduling problem which is a general scheduling problem including job shop scheduling, open shop scheduling and mixed shop scheduling as special cases. The aim of this paper is to compare different pheromone representations taken from the literature with our new approach. The pheromone representations are used by an ant colony optimization algorithm to construct solutions to the FOP shop scheduling problem.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"326 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124601251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An application of immunocomputing to the evolution of rules for ecosystem management","authors":"M. Janssen, Daniel W. Stow","doi":"10.1109/CEC.2002.1007009","DOIUrl":"https://doi.org/10.1109/CEC.2002.1007009","url":null,"abstract":"This paper discusses the evolution of rules between people for the management of ecosystems. Four aspects of the rules are discussed: coding, creation, selection and memory. The immune system provides a useful metaphor to relate these four aspects into a coherent framework. We sketch a framework for a computational model to study the evolution of rules for the management of ecosystems.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124892419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Two-way mutation evolution strategies","authors":"Yong Liang, K. Leung","doi":"10.1109/CEC.2002.1007026","DOIUrl":"https://doi.org/10.1109/CEC.2002.1007026","url":null,"abstract":"In this paper, a new two-way adaptive search mutation strategy is proposed, and a \"two-way evolution strategy\" (TWES) is established. The experimental results show that TWES yields much faster convergence than classical evolution strategies. This paper also discusses the relationship between the parameter setting and the convergent speed by TWES.","PeriodicalId":184547,"journal":{"name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128469269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}