Title :
Validation of relative feature importance using a natural data set
Author :
Holz, H.J. ; Loew, M.H.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., George Washington Univ., Washington, DC, USA
Abstract :
Feature analysis for classification is based on the discriminately power of features. In our previous research (1997), we presented a method for measuring the non-parametric discriminatory power of features, called relative feature importance (RFI). RFI has been shown to correctly rank features for a variety of artificial data sets. In this research, we validate RFI on natural data using a multiclass natural data set
Keywords :
feature extraction; pattern classification; feature extraction; multiclass problem; natural data set; pattern classification; relative feature importance; Costs; Feature extraction; Medical diagnosis; Pathology; Power engineering and energy; Power engineering computing; Power measurement; Radiofrequency interference; Scattering; Testing;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906100
