• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Leng, Qiang-Kui (Leng, Qiang-Kui.) | Li, Yu-Jian (Li, Yu-Jian.)

Indexed by:

EI PKU CSCD

Abstract:

Multiconlitron is a general framework for constructing piecewise linear classifiers. For convexly separable and commonly separable data sets, it can separate them correctly by using support conlitron algorithm (SCA) and support multiconlitron algorithm (SMA), respectively. On this basis, the paper proposes a maximal cutting construction method for multiconlitron design. The method consists of two training processes. In the first step, the maximal cutting process (MCP) is utilized iteratively to find a linear boundary such that it can obtain the maximum number of samples. Thus, the MCP can reduce the number of linear boundaries and construct a minimal set of decision functions, and ultimately simplify the classifiation model. To improve the generalization ability further, in the second step we employ a boundary adjusting process (BAP) to make the classifiation boundaries more fittable. Experiments on both synthetic and real data sets show that the presented method can produce more reasonable multiconlitron with better performance. Comparison with some other piecewise linear classifiers verifies its effctiveness and competitiveness. © 2014 Acta Automatica Sinica. All rights reserved.

Keyword:

Piecewise linear techniques Iterative methods

Author Community:

  • [ 1 ] [Leng, Qiang-Kui]College of Computer Science, Beijing University of Technology, Beijing 100124, China
  • [ 2 ] [Li, Yu-Jian]College of Computer Science, Beijing University of Technology, Beijing 100124, China

Reprint Author's Address:

Show more details

Related Keywords:

Related Article:

Source :

Acta Automatica Sinica

ISSN: 0254-4156

Year: 2014

Issue: 4

Volume: 40

Page: 721-730

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 1

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 0

Affiliated Colleges:

Online/Total:380/5461813
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.