Enhanced spectral embedding with semi-supervised feature selection

Weiwei Du, Kiichi Urahama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a spectral embedding technique for semisupervised pattern classification. Importance scores of features are firstly evaluated with a semi-supervised feature selection algorithm by Zhao et al. Training data are then embedded into a low-dimensional space with a spectral mapping derived from the selected and weighted feature vectors with which test data are classified by the nearest neighbor rule. The performance of the proposed pattern classification algorithm is examined with synthetic and real dataseis.

Original languageEnglish
Title of host publication5th International Conference on Natural Computation, ICNC 2009
Pages129-133
Number of pages5
DOIs
Publication statusPublished - Dec 1 2009
Event5th International Conference on Natural Computation, ICNC 2009 - Tianjian, China
Duration: Aug 14 2009Aug 16 2009

Publication series

Name5th International Conference on Natural Computation, ICNC 2009
Volume1

Other

Other5th International Conference on Natural Computation, ICNC 2009
CountryChina
CityTianjian
Period8/14/098/16/09

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Cite this

Du, W., & Urahama, K. (2009). Enhanced spectral embedding with semi-supervised feature selection. In 5th International Conference on Natural Computation, ICNC 2009 (pp. 129-133). [5365606] (5th International Conference on Natural Computation, ICNC 2009; Vol. 1). https://doi.org/10.1109/ICNC.2009.170