Presentation 2007-03-16
Adaptive Classifiers-Ensemble System for Changing Situations
Kyosuke NISHIDA, Koichiro YAMAUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The ability to adapt to various types of changes is essential to dealing with real-world problems. To improve the performance of our previously reported an online learning system that uses an ensemble of classifiers, the adaptive classifiers-ensemble (ACE) system, we have improved the weighting method, which combines the outputs of classifiers, and have added a new classifier pruning method. ACE consists of one online classifier, many batch classifiers, and a drift detection mechanism. The experimental results showed that the enhanced version of ACE performed well for a synthetic dataset in which there are sudden changes, gradual changes, and recurring concepts.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) concept drift / multiple classifiers system / changing environments / drift detection
Paper # PRMU2006-272
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/3/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Adaptive Classifiers-Ensemble System for Changing Situations
Sub Title (in English)
Keyword(1) concept drift
Keyword(2) multiple classifiers system
Keyword(3) changing environments
Keyword(4) drift detection
1st Author's Name Kyosuke NISHIDA
1st Author's Affiliation Division of Synergetic Information Science, Graduate School of Information Science and Technology Hokkaido University()
2nd Author's Name Koichiro YAMAUCHI
2nd Author's Affiliation Division of Synergetic Information Science, Graduate School of Information Science and Technology Hokkaido University:Japan Society for the Promotion of Science
Date 2007-03-16
Paper # PRMU2006-272
Volume (vol) vol.106
Number (no) 606
Page pp.pp.-
#Pages 6
Date of Issue