Title :
A fast metric approach to feature subset selection
Author_Institution :
Aizu Univ., Fukushima, Japan
Abstract :
A simple approach to feature subset selection is proposed. During the training stage, the method selects the features that simultaneously minimize the within-class distance and maximize the between-class distance. Experiments performed on the Iris Plants Database and the Pima Indians Diabetes Database show that the approach is practical because it is fast and yet the correct classification rates are competitive
Keywords :
data handling; factographic databases; learning (artificial intelligence); pattern classification; Iris Plants Database; Pima Indians Diabetes Database; between-class distance; classification rates; fast metric approach; feature subset selection; training stage; within-class distance; Biological cells; Diabetes; Euclidean distance; Fuzzy neural networks; Iris; Nearest neighbor searches; Neural networks; Probability; Scattering; Spatial databases;
Conference_Titel :
Euromicro Conference, 1998. Proceedings. 24th
Conference_Location :
Vasteras
Print_ISBN :
0-8186-8646-4
DOI :
10.1109/EURMIC.1998.708095
