论文信息 - An upper bound on the probability of misclassification in terms of Matusita's measure of affinity

An upper bound on the probability of misclassification in terms of Matusita's measure of affinity

SummaryA distribution-free upper bound is derived on the Bayes probability of misclassification in terms of Matusita's measure of affinity among several distributions for theM-hypothesis discrimination problem. It is shown that the bound is as sharp as possible.

Godfried T. Toussaint | Binay K. Bhattacharya

[1] K. Matusita,et al. Some properties of affinity and applications , 1971 .

[2] T. Kailath. The Divergence and Bhattacharyya Distance Measures in Signal Selection , 1967 .

[3] G. Toussaint. Probability of error, expected divergence, and the affinity of several distributions , 1978 .

[4] A. M. Mathai,et al. An axiomatic foundation for a multivariate measure of affinity among a number of distributions , 1973 .

[5] Godfried T. Toussaint,et al. Some properties of Matusita's measure of affinity of several distributions , 1974 .

[6] K. Matusita. DISCRIMINATION AND THE AFFINITY OF DISTRIBUTIONS , 1973 .

[7] A lower bound on bayes risk in classification problems , 1976 .

[8] G. Toussaint. An upper bound on the probability of misclassification in terms of the affinity , 1977, Proceedings of the IEEE.

[9] K. Matusita. On the notion of affinity of several distributions and some of its applications , 1967 .