Conditional Mutual Information Based Feature Selection

Author

Cheng, Hongrong ; Qin, Zhiguang ; Qian, Weizhong ; Liu, Wei

Author_Institution

Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu

fYear

2008

fDate

21-22 Dec. 2008

Firstpage

103

Lastpage

107

Abstract

In this paper, a new greedy feature selection algorithm is proposed to detect more precisely informative features. It overcomes the limitation of many existing MI-based gready feature selection algorithms. It is capable of detecting the relation of relevant feature combinations in some degree.In addition, the requirements of the memory storage and computation cost are low. Experimental results for the UCI benchmark dataset demonstrate the good performance of the proposed algorithm on the experimented data sets.

Keywords

feature extraction; greedy algorithms; learning (artificial intelligence); pattern classification; conditional mutual information; feature detection; greedy feature selection algorithm; memory storage requirement; pattern classification; supervised learning; Accuracy; Boolean functions; Computational efficiency; Computer science; Filters; Knowledge acquisition; Knowledge engineering; Machine learning; Mutual information; Probability distribution; conditional mutual information; entropy; feature combination; feature selection;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Acquisition and Modeling, 2008. KAM '08. International Symposium on

Conference_Location

Wuhan

Print_ISBN

978-0-7695-3488-6

Type

conf

DOI

10.1109/KAM.2008.85

Filename

4732795