Context based clearing procedure: A niching method for genetic algorithms

Abstract In this paper we present CBC (context based clearing), a procedure for solving the niching problem. CBC is a clearing technique governed by the amount of heterogeneity in a subpopulation as measured by the standard deviation. CBC was tested using the M7 function, a massively multimodal deceptive optimization function typically used for testing the efficiency of finding global optima in a search space. The results are compared with a standard clearing procedure. Results show that CBC reaches global optima several generations earlier than in the standard clearing procedure. In this work the target was to test the effectiveness of context information in controlling clearing. A subpopulation includes a fixed number of candidates rather than a fixed radius. Each subpopulation is then cleared either totally or partially according to the heterogeneity of its candidates. This automatically regulates the radius size of the area cleared around the pivot of the subpopulation.

[1]  Yew-Soon Ong,et al.  Valley-Adaptive Clearing Scheme for Multimodal Optimization Evolutionary Search , 2009, 2009 Ninth International Conference on Intelligent Systems Design and Applications.

[2]  Edmund K. Burke,et al.  Parallel Problem Solving from Nature - PPSN IX: 9th International Conference, Reykjavik, Iceland, September 9-13, 2006, Proceedings , 2006, PPSN.

[3]  Claudio De Stefano,et al.  Where Are the Niches? Dynamic Fitness Sharing , 2007, IEEE Transactions on Evolutionary Computation.

[4]  Ralph R. Martin,et al.  A Sequential Niche Technique for Multimodal Function Optimization , 1993, Evolutionary Computation.

[5]  Kalyanmoy Deb,et al.  Massive Multimodality, Deception, and Genetic Algorithms , 1992, PPSN.

[6]  Kalyanmoy Deb,et al.  An Investigation of Niche and Species Formation in Genetic Function Optimization , 1989, ICGA.

[7]  Günter Neumann,et al.  Interleaving Natural Language Parsing and Generation Through Uniform Processing , 1998, Artif. Intell..

[8]  白鳥 則郎,et al.  ADIPSフレームワークにおける Java オブジェクトのエージェント化実現方式 , 1999 .

[9]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[10]  Márk Jelasity,et al.  UEGO, an Abstract Niching Technique for Global Optimization , 1998, PPSN.

[11]  Márk Jelasity,et al.  GAS, A Concept on Modeling Species in Genetic Algorithms , 1998, Artif. Intell..

[12]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[13]  Márk Jelasity,et al.  Two Approaches for Parallelizing the UEGO Algorithm , 2001 .

[14]  Ofer M. Shir,et al.  Dynamic niching in evolution strategies with covariance matrix adaptation , 2005, 2005 IEEE Congress on Evolutionary Computation.

[15]  J. David Schaffer,et al.  Proceedings of the third international conference on Genetic algorithms , 1989 .

[16]  Ofer M. Shir,et al.  Niche Radius Adaptation in the CMA-ES Niching Algorithm , 2006, PPSN.

[17]  Alain Pétrowski,et al.  A clearing procedure as a niching method for genetic algorithms , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.