Rough set based on modified ChiMerge algorithm and its application

Author

Gu, Xiao-Hong ; Hou, Di-Bo ; Zhou, Ze-Kui ; Yu, Dan

Author_Institution

Dept. of Control Sci. & Eng., Zhejiang Univ., Hangzhou, China

Volume

2

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

1004

Abstract

Aimed at the rough set theory cannot be directly applied to deal with continuous attributes, a rough set based on modified ChiMerge algorithm is presented. The basic concepts of the rough set theory and the modified ChiMerge algorithm are introduced and adequately illustrated firstly. The modified ChiMerge algorithm presents a stop criterion without needing experience compared to ChiMerge algorithm. The additional information can be eliminated and the rules can be extracted directly from data based on rough set theory after continuous values are discretized by modified ChiMerge algorithm. Finally the rough set theory based on modified ChiMerge algorithm is applied to a QSAR (quantitative structure activity relationships) problem, the results show that the algorithm is a useful tool for the analysis of continuous, inexact, uncertain, or vague data.

Keywords

rough set theory; uncertainty handling; QSAR problem; modified ChiMerge algorithm; quantitative structure activity relationships problem; rough set theory; stop criterion; uncertain data; Algorithm design and analysis; Artificial intelligence; Data mining; Databases; Expert systems; Information systems; Machine learning; Machine learning algorithms; Rough sets; Set theory; ChiMerge algorithm; QSAR problem; Rough set theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527090

Filename

1527090