120 Offspring Generation Method for interactive Genetic Algorithms considering Multimodal Preferences and Dependencies
120 対話型遺伝的アルゴリズムにおける嗜好の多峰性および依存関係を考慮した個体生成方法の検討

Fuyuko ITO, Misato TANAKA, Tomoyuki HIROYASU, Mitsunori MIKI, Hisatake YOKOUCHI
2008 The Proceedings of OPTIS  
Interactive genetic algorithms ( iGAs )are 皿 ethods that acquire and analyse nser preference based on user , s sub − jective evaluation . IGA has been applied to various unimedal problems , such as parameter setting of a hear 主 ng aid and fashiDn des } gn . On the other hand, the goal of this study is achieving iGA which also corresponds to multimoda 玉 preferences wj もh equivalent 且tness at the peaks . R 〕r example , when users select products on shopplng sites , they have several types of
more » ... rence trends at the same time . In this case , renecting all the trends in product presentation leads to increased sales and consumer satisfaction . The dependency among desig囂 variable8 should be also considercd toward each trend ef preference . In this study , a new of 聴 pring generation method that enables ef 丘cient search even if user preference is multimodal and there are dependencies among design variables is proposed . The proposed method is capable to detect a mu Σ timodal pre 魚 rence using clustering , and spawn off − spring based on probabilistic rnodel eliminating the dependencies among design variables by principal component analysis . The results of experiments indicate that the proposed method can generate offspring corresponding to multjmodal preferences with equiva 至 ent 且tness at the peaks and dependencies among design variables . However , there are f 合 w subjects who have dependencies within their pref α ences . Key word : interactive genetic algorithms , offspring generation, multimodality , dependency
doi:10.1299/jsmeoptis.2008.8.103 fatcat:kbbz34pxpveuve24q7moylk3hq