A class discriminality measure based on feature space partitioning

Abstract

-This paper presents a new class discriminability measure based on an adaptive partitioning of the feature space according to the available class samples. It is intended to be used as a criterion in a classifier-independent feature selection procedure. The partitioning is performed according to a binary splitting rule and appropriate stopping criteria… (More)
DOI: 10.1016/0031-3203(95)00122-0

17 Figures and Tables

Topics

  • Presentations referencing similar topics