Feature Selection via Correlation Coefficient Clustering

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/58496

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/58496

Title:	Feature Selection via Correlation Coefficient Clustering
Authors:	Hsu, Hui-Huang;Hsieh, Cheng-Wei
Contributors:	淡江大學資訊工程學系
Keywords:	Feature Selection;Clustering;Correlation Coefficient;Support Vector Machines (SVMs);Machine Learning;Classification
Date:	2010-12
Issue Date:	2011-10-01 12:00:52 (UTC+8)
Publisher:	Oulu: Academy Publisher
Abstract:	Feature selection is a fundamental problem in machine learning and data mining. How to choose the most problem-related features from a set of collected features is essential. In this paper, a novel method using correlation coefficient clustering in removing similar/redundant features is proposed. The collected features are grouped into clusters by measuring their correlation coefficient values. The most class-dependent feature in each cluster is retained while others in the same cluster are removed. Thus, the most class-related and mutually unrelated features are identified. The proposed method was applied to two datasets: the disordered protein dataset and the Arrhythmia (ARR) dataset. The experimental results show that the method is superior to other feature selection methods in speed and/or accuracy. Detail discussions are given in the paper.
Relation:	Journal of Software 5(12), pp.1371-1377
DOI:	10.4304/jsw.5.12.1371-1377
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
1796-217X_5(12)p1371-1377.pdf		449Kb	Adobe PDF	382	View/Open