Feature selection for multi-class classification using pairwise class discriminatory measure and covering concept

被引：8

作者：

Ji, H ^{[1
]}

Bang, SY ^{[1
]}

机构：

[1] Pohang Univ Sci & Technol, Dept Comp Sci & Engn, Pohang 790784, South Korea

来源：

ELECTRONICS LETTERS | 2000年 / 36卷 / 06期

关键词：

Algorithms - Database systems - Mathematical models - Problem solving - Set theory;

D O I：

10.1049/el:20000458

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An algorithm is presented for selecting a suboptimal set of features which classify given data into classes as effectively as the entire set of features. The algorithm is useful for reducing the number of features in a multi-class problem. In this algorithm, For each pair of classes a feature is successively selected which best discriminates the pair. The algorithm stops when all the pairs are covered. Preliminary experimental results are good.

引用

页码：524 / 525

页数：2

共 7 条

[1]

ALMUALLIM H, 1991, PROCEEDINGS : NINTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2, P547

[2]

Blake C.L., 1998, UCI repository of machine learning databases

[3] Selection of relevant features and examples in machine learning [J].

Blum, AL ;

Langley, P .

ARTIFICIAL INTELLIGENCE, 1997, 97 (1-2) :245-271

[4]

GUERINDUGUE A, TEXTURE DATABASE LAB

[5]

Hong SJ, 1997, IEEE T KNOWL DATA EN, V9, P718, DOI 10.1109/69.634751

[6]

John GH, 1994, P 11 INT C MACH LEAR, P121, DOI 10.1016/B978-1-55860-335-6.50023-4

[7]

Kira K., 1992, P 9 INT WORKSH MACH, P249, DOI DOI 10.1016/B978-1-55860-247-2.50037-1

← 1 →