Presentation 2012-11-26
A New Classification Method Focusing on Prediction Accuracy of Classifiers for ECOC Classification Systems
Sotaro ISHIBASHI, Kenta MIKAWA, Takashi ISHIDA, Masayuki GOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The ECOC method is known as a powerful tool using a combination of binary classifiers for multi-valued document classification. We propose a new classification method focusing on prediction accuracy of each classifier and error correcting capability of the code used for ECOC classification systems. Through simulation experiment for document classification, the effectiveness of proposed method is clarified.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multi-valued Classification Problem / Relevance Vector Machine / Error Correcting Output Codes / Reject Rule
Paper # AI2012-16
Date of Issue

Conference Information
Committee AI
Conference Date 2012/11/19(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A New Classification Method Focusing on Prediction Accuracy of Classifiers for ECOC Classification Systems
Sub Title (in English)
Keyword(1) Multi-valued Classification Problem
Keyword(2) Relevance Vector Machine
Keyword(3) Error Correcting Output Codes
Keyword(4) Reject Rule
1st Author's Name Sotaro ISHIBASHI
1st Author's Affiliation Graduate School of Creative Science and Engineering, Waseda University()
2nd Author's Name Kenta MIKAWA
2nd Author's Affiliation Graduate School of Creative Science and Engineering, Waseda University
3rd Author's Name Takashi ISHIDA
3rd Author's Affiliation Media Network Center, Waseda University
4th Author's Name Masayuki GOTO
4th Author's Affiliation School of Creative Science and Engineering, Waseda University
Date 2012-11-26
Paper # AI2012-16
Volume (vol) vol.112
Number (no) 319
Page pp.pp.-
#Pages 6
Date of Issue