--- abstract: "In this paper, the issue of adapting probabilities for Evolutionary Algorithm (EA) search operators is revisited. A framework is devised for distinguishing between measurements of performance and the interpretation of those measurements for purposes of adaptation. Several examples of measurements and statistical interpretations are provided. Probability value adaptation is tested using an EA with 10 search operators against 10 test problems with results indicating that both the type of measurement and its statistical interpretation play significant roles in EA performance. We also find that selecting operators based on the prevalence of outliers rather than on average performance is able to provide considerable improvements to\r\nadaptive methods and soundly outperforms the non-adaptive\r\ncase." altloc: - http://www.ceic.unsw.edu.au/staff/Tuan_Pham/fp122-whitacre.pdf chapter: ~ commentary: ~ commref: ~ confdates: 'July 8-12, 2006' conference: GECCO 2006 confloc: 'Seattle, Washington, USA' contact_email: ~ creators_id: [] creators_name: - family: Whitacre given: James M honourific: Dr lineage: '' - family: Pham given: Tuan Q. honourific: Dr lineage: '' - family: Sarker given: Ruhul A. honourific: Dr lineage: '' date: 2006-07-08 date_type: published datestamp: 2009-07-06 09:42:49 department: ~ dir: disk0/00/00/65/79 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 6579 fileinfo: /style/images/fileicons/application_pdf.png;/6579/1/Statistical_interpretation_of_adaptive_performance_in_genetic_algorithms%2Dwhitacre.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: "Evolutionary Algorithm, Genetic Algorithm, Feedback\r\nAdaptation" lastmod: 2011-03-11 08:57:23 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: ~ pubdom: TRUE publication: ~ publisher: ~ refereed: TRUE referencetext: "[1] Barbosa, H. J. C. and e Sá, A. M. On Adaptive Operator\r\nProbabilities in Real Coded Genetic Algorithms, In\r\nWorkshop on Advances and Trends in Artificial Intelligence\r\nfor Problem Solving (SCCC '00), (Santiago, Chile,\r\nNovember 2000).\r\n[2] Bedau, M. A. and Packard, N. H. Evolution of evolvability\r\nvia adaptation of mutation rates. BioSystems 69 (2003), 143-\r\n162.\r\n[3] Boeringer D. W., Werner D. H., Machuga D. W. A\r\nsimultaneous parameter adaptation scheme for geneticalgorithms\r\nwith application to phased array synthesis, IEEE\r\nTrans. on Antannas and Propagation 53, 1 (Jan. 2005),\r\n356-371 Part 2.\r\n[4] Chew, E. P., Ong, C. J., and Lim, K. H. Variable period\r\nadaptive genetic algorithm. Comput. Ind. Eng. 42, 2-4 (Jun.\r\n2002), 353-360.\r\n[5] Davis, L. Handbook of Genetic Algorithms, van Nostrand\r\nReinhold, New York, 1991.\r\n[6] De Jong, K. An analysis of the behaviour of a class of\r\ngenetic adaptive systems. Ph. D Thesis, University of\r\nMichigan, Ann Arbor, Michigan, 1975.\r\n[7] Eiben, Á. E., Hinterding R., and Michalewicz Z. Parameter\r\ncontrol in evolutionary algorithms, IEEE Trans. Evol.\r\nComput., 3 (Jul. 1999), 124–141.\r\n[8] Espinoza, F. P. Minsker, B. S. and Goldberg, D. E.\r\nAdaptive Hybrid Genetic Algorithm for Groundwater\r\nRemediation Design. Journal of Water Resources Planning\r\nand Management, 131, 1 (Jan. 2005), 14-24.\r\n[9] Herrera, F. and Lozano, M. Adaptive genetic operators\r\nbased on coevolution with fuzzy behaviors. IEEE Trans.\r\nEvolutionary Computation 5, 2 (2001), 149-165.\r\n[10] Herrera, F. and Lozano, M. Tackling real-coded genetic\r\nalgorithms: Operators and tools for the behavioural analysis,\r\nArtificial Intelligence Review 12, 4, (1998), 265-319.\r\n[11] Herrera, F., Lozano, M., and Sánchez, A. M. 2005. Hybrid\r\ncrossover operators for real-coded genetic algorithms: an\r\nexperimental study. Soft Comput. 9, 4 (Apr. 2005), 280-298.\r\n[12] Hong, T. P. Wang, H. S. Lin, W. Y. and Lee, W. Y.\r\nEvolution of Appropriate Crossover and Mutation Operators\r\nin a Genetic Process. Appl. Intell. 16, 1 (2002), 7-17.\r\n[13] Igel, C. Friedrichs, F. and Wiegand, S. Evolutionary\r\nOptimization of Neural Systems: The Use of Strategy\r\nAdaptation. Trends and Applications in Constructive\r\nApproximation. International Series of Numerical\r\nMathematics, 151, (2005), 103-123.\r\n[14] Janka, E. Vergleich stochastischer Verfahren zur globalen\r\nOptimierung, Diploma Thesis, University of Vienna,\r\nVienna, Austria, 1999.\r\n[15] Julstrom, B. A. Adaptive operator probabilities in a genetic\r\nalgorithm that applies three operators. In Proceedings of the\r\n1997 ACM Symposium on Applied Computing (SAC '97)\r\n(San Jose, California, United States). ACM Press, New\r\nYork, NY, 233-238, 1997.\r\n[16] Muhlenbein, H., Schomisch, M. and Born, J. The parallel\r\ngenetic algorithm as function optimizer. In Proc. of 4th\r\nInternational Conference of Genetic Algorithms, 271-278,\r\n1991.\r\n[17] Pham, Q.T. Dynamic Optimization of Chemical Engineering\r\nProcesses by an Evolutionary Method. Comp. Chem. Eng.,\r\n22 (1998), 1089-1097.\r\n[18] Pham, Q. T. Competitive evolution: a natural approach to\r\noperator selection. In: Progress in Evolutionary\r\nComputation, Lecture Notes in Artificial Intelligence,\r\n(Evolutionary Computation Workshop) (Armidale,\r\nAustralia, November 21-22, 1994). Springer-Verlag,\r\nHeidelberg, 1995, 49-60.\r\n[19] Smith, J. and Fogarty, T.C. Operator and parameter\r\nadaptation in genetic algorithms. Soft Computing, 1, 2\r\n(1997), 81-87.\r\n[20] Storn, R. and Price, K. Differential Evolution - A Simple\r\nand Efficient Adaptive Scheme for Global Optimization over\r\nContinuous Spaces. Technical Report TR-95-012,\r\nInternational Computer Science Institute, Berkeley, CA,\r\n1995.\r\n[21] Thierens, D. An adaptive pursuit strategy for allocating\r\noperator probabilities. In Proceedings of the 2005\r\nConference on Genetic and Evolutionary Computation\r\n(GECCO '05). ACM Press, New York, NY, 2005, 1539-\r\n1546.\r\n[22] Tuson, A. and Ross, P. Cost based operator rate adaptation:\r\nAn investigation. In Proceedings of the 4th Conference on\r\nParallel Problem Solving from Nature, number 1141 in\r\nLecture Notes in Computer Science, Springer, Berlin, 1996,\r\n461-469.\r\n[23] Whitacre, J. M., Pham, Q. T., Sarker, R. A. Credit\r\nAssignment in Adaptive Evolutionary Algorithms. In\r\nProceedings of the 2006 Conference on Genetic and\r\nEvolutionary Computation (GECCO '06) (Seattle, USA, July\r\n8-12, 2006). ACM Press, New York, NY, 2006.\r\n[24] Wong Y. Y., Lee K. H., Leung K.S, C.-W. Ho: A novel\r\napproach in parameter adaptation and diversity maintenance\r\nfor genetic algorithms. Soft Comput. 7, 8 (2003), 506-515." relation_type: [] relation_uri: [] reportno: ~ rev_number: 21 series: ~ source: ~ status_changed: 2009-07-06 09:42:49 subjects: - comp-sci-art-intel succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: "Use of Statistical Outlier Detection Method in Adaptive\r\nEvolutionary Algorithms" type: confpaper userid: 8971 volume: ~