大学サイト   学部サイト   学科サイト   EnglishPages
 
旧尾家・塚本研究室です.尾家祐二 現・九州工業大学学長の情報は こちら.
   
研究業績


GAuGEと遺伝的クラスタリングの組合せ
著者
  曽根田 拓也, 大西 圭
 
雑誌名/会議名
  第15回日本知能情報ファジィ学会九州支部学術講演会予稿集, pp.115-118, 山口県下関市, 2013年12月21日. 2013 年 12 月
 
アブストラクト
  We previously proposed a method combining a genetic algorithm (GA) with a data clustering method inspired by a model for speciation. The clustering method is highly consistent with GA in terms of procedures, and is expected to help GA maintain diversity of population. However, the used GA was shown to be ineffective if a given fixed crossover does not fit a give optimization problem. Therefore, this paper introduces a new GA that solves the problem of a fixed crossover, which is GA using grammatical evolution (GAuGE), and combines it with the clustering method. Simulation results show that the new method indeed improves the performance of the previous one.
 
キーワード
 
 
記述言語
  Japanese
 
 

web_admin [ at ] infonet.cse.kyutech.ac.jp /  Copyright (c) 2016 Oie & Tsukamoto Laboratory, All Right Reserved.