Recursive optimization of an extended Fisher discriminant criterion

Research output: Contribution to conferencePaperpeer-review

Abstract

A method for recursive optimization of an extended Fisher (ExF) discriminant criterion is proposed. The method consists of obtaining a discriminant direction which optimizes the ExF criterion, transforming the data along it into data with greater class overlap, and iterating to obtain the next discriminant direction. An application to a medical dataset indicates the potential of the proposed method for finding a sequence of oblique directions with significant class separation.

Original languageEnglish
Pages708-711
Number of pages4
StatePublished - 1 Dec 1996
EventProceedings of the 1996 3rd IEEE International Conference on Electronics, Circuits, and Systems, ICECS. Part 2 (of 2) - Rodos, Greece
Duration: 13 Oct 199616 Oct 1996

Conference

ConferenceProceedings of the 1996 3rd IEEE International Conference on Electronics, Circuits, and Systems, ICECS. Part 2 (of 2)
CityRodos, Greece
Period13/10/9616/10/96

ASJC Scopus subject areas

  • Engineering (all)

Cite this