Presentation 2004/11/12
Induction of Decision Trees from the Distance Space Generated by NNC
Takaharu Kawatsure, Qiangfu Zhao,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Nearest Neighbor Classifier (NNC) is one of the simplest methods for pattern recognition. Currently, we have proposed an R^4-rule that can make the smallest or nearly smallest NNCs. On the other hand, decision tree (DT) is often considered as one of the most comprehensible methods. If the data set is large, however, DTs may become too large and no longer comprehensible. In this paper, we propose a new method for inducing DTs from a distance space generated by an NNC. The NNC itself is designed by the R^4-rule. Using this method, we can induce more compact and more comprehensible DTs. The efficiency of the method is verified through experiments with several public databases.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pattern recognition / decision tree / nearest neighbor classifier / R^4-rule / distance space
Paper # PRMU2004-114,HIP2004-54
Date of Issue

Conference Information
Committee HIP
Conference Date 2004/11/12(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Induction of Decision Trees from the Distance Space Generated by NNC
Sub Title (in English)
Keyword(1) Pattern recognition
Keyword(2) decision tree
Keyword(3) nearest neighbor classifier
Keyword(4) R^4-rule
Keyword(5) distance space
1st Author's Name Takaharu Kawatsure
1st Author's Affiliation The University of Aizu()
2nd Author's Name Qiangfu Zhao
2nd Author's Affiliation The University of Aizu
Date 2004/11/12
Paper # PRMU2004-114,HIP2004-54
Volume (vol) vol.104
Number (no) 450
Page pp.pp.-
#Pages 6
Date of Issue