Trace Ratio Criterion for Feature Extraction in Classification. (14th May 2014)

• Record Type: Journal Article
• Authors: Li, Guoqi; Wen, Changyun; Wei, Wei; Xu, Yi; Ding, Jie; Zhao, Guangshe; Shi, Luping
• Other Names: Tang Yang Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2014(2014)
• Publication Date: 2014-05-14
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2014/725204
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : A generalized linear discriminant analysis based on trace ratio criterion algorithm (GLDA-TRA) is derived to extract features for classification. With the proposed GLDA-TRA, a set of orthogonal features can be extracted in succession. Each newly extracted feature is the optimal feature that maximizes the trace ratio criterion function in the subspace orthogonal to the space spanned by the previous extracted features.