Abstract:
A new feature selection procedure based on the Kullback J-divergence between two class conditional density functions approximated by a finite mixture of parameterized den...Show MoreMetadata
Abstract:
A new feature selection procedure based on the Kullback J-divergence between two class conditional density functions approximated by a finite mixture of parameterized densities of a special type is presented. This procedure is suitable especially for multimodal data. Apart from finding a feature subset of any cardinality without involving any search procedure, it also simultaneously yields a pseudo-Bayes decision rule. Its performance is tested on real data.
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 18, Issue: 2, February 1996)
DOI: 10.1109/34.481557