Novel Methods for Feature Subset Selection with Respect to Problem Knowledge
Recent advances in the statistical methodology for selecting optimal subsets of features for data representation and classification are presented. This chapter attempts to provide a guideline of which approach to choose with respect to the extent of a priori knowledge of the problem. Two basic approaches are reviewed and the conditions under which they should be used are specified. One approach involves the use of the computationally effective Floating search methods. The alternative approach trades off the requirement for a priori information for the requirement of sufficient data to represent the distributions involved. Owing to its nature it is particularly suitable for cases when the underlying probability distributions are not unimodal. The approach attempts to achieve simultaneous feature selection and decision rule inference. According to the criterion adopted there are two variants allowing the selection of features either for optimal representation or discrimination.
KeywordsFeature Selection Feature Extraction Feature Subset Feature Selection Method Subset Selection
Unable to display preview. Download preview PDF.
- F.J. Ferri, P. Pudil, M. Hatef, and J. Kittler (1994). Comparative study of technique for large-scale features selection. In Pattern Recognition in Practice IV: Multiple Paradigms,Comparative Studies and Hybrid Systems; edited by E.S. Gelsema and L.N.Kanal,pages 403–413, North-Holland Elsevier.Google Scholar
- Novovičová, J. and Pudil, P. (1997). Dealing With Complexity: Neural Network Approach, chapter Feature Selection and Classification by Modified Model with Latent Structure. Springer Verlag.Google Scholar
- Pudil, P. and Novovičová, J. (1998). Novel methods for subset selection with respect to problem knowledge. IEEE Intelligent Systems - Special Issue on Feature Transformation and Subset Selection,in print.Google Scholar