Nonlinear feature extraction using evolutionary algorithm

E.K. TANG, Ponnuthurai Nagaratnan SUGANTHAN, Xin YAO

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

2 Citations (Scopus)


We propose a method of nonlinear feature extraction for 2-class problems. A simple sigmoid function is used to extract features that are negatively correlated to each other. To evaluate the effectiveness of the proposed method, we employ linear and non-linear support vector machines to classify using the extracted feature sets and the original feature sets. Comparison on 4 datasets shows that our method is effective for nonlinear feature extraction. © Springer-Verlag Berlin Heidelberg 2004.
Original languageEnglish
Title of host publicationNeural Information Processing : 11th International Conference, ICONIP 2004 Calcutta, India, November 22–25, 2004 Proceedings
EditorsNikhil Ranjan PAL, Nik KASABOV, Rajani K. MUDI, Srimanta PAL, Swapan Kumar PARUI
PublisherSpringer Berlin Heidelberg
Number of pages6
ISBN (Electronic)9783540304999
ISBN (Print)9783540239314
Publication statusPublished - 2004
Externally publishedYes
Event11th International Conference on Neural Information Processing, ICONIP 2004 - Calcutta, India
Duration: 22 Nov 200425 Nov 2004

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin, Heidelberg
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference11th International Conference on Neural Information Processing, ICONIP 2004


Dive into the research topics of 'Nonlinear feature extraction using evolutionary algorithm'. Together they form a unique fingerprint.

Cite this