Feature ordering for neural incremental attribute learning based on Fisher's Linear Discriminant

Ting Wang, Sheng Uei Guan

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

9 Citations (Scopus)

Abstract

Incremental attribute learning (IAL) often gradually imports and trains pattern features in one or more size, which makes feature ordering become a novel preprocessing work in IAL process. In previous studies, the calculation of feature ordering is often Based on feature's single contribution to outputs, which is similar to wrapper methods in feature selection. However, such a process is time-consuming. In this paper, a new approach for feature ordering is presented, where feature ordering is ranked by Fisher Score, a metric derived by Fisher's Linear Discriminant (FLD). Based on neural network IAL model, experimental results verified that feature ordering derived by Fisher Score can not only save time, but also obtain the best classification rate compared with those in previous studies.

Original languageEnglish
Title of host publicationProceedings - 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2013
Pages507-510
Number of pages4
DOIs
Publication statusPublished - 2013
Event2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2013 - Hangzhou, Zhejiang, China
Duration: 26 Aug 201327 Aug 2013

Publication series

NameProceedings - 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2013
Volume2

Conference

Conference2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2013
Country/TerritoryChina
CityHangzhou, Zhejiang
Period26/08/1327/08/13

Keywords

  • Feature ordering
  • Fisher's Linear Discriminant
  • Incremental attribute learning
  • Neural networks
  • Pattern classification

Fingerprint

Dive into the research topics of 'Feature ordering for neural incremental attribute learning based on Fisher's Linear Discriminant'. Together they form a unique fingerprint.

Cite this