DocumentCode :
928586
Title :
Renyi´s entropy and the probability of error
Author :
Ben-Bassat, Moshe ; Raviv, Josef
Volume :
24
Issue :
3
fYear :
1978
fDate :
5/1/1978 12:00:00 AM
Firstpage :
324
Lastpage :
331
Abstract :
The basic properties of Renyi\´s entropy are reviewed, and its concavity properties are characterized. New bounds (referred to as 
bounds) on the probability of error are derived from Renyi\´s entropy and are compared with known bounds. It is proved that for the two-class case, the 
bound is sharper than many of the previously known bounds. The difference between the bound and the real value of the probability of error is at most 0.09.
bounds) on the probability of error are derived from Renyi\´s entropy and are compared with known bounds. It is proved that for the two-class case, the bound is sharper than many of the previously known bounds. The difference between the bound and the real value of the probability of error is at most 0.09.Keywords :
Entropy functions; Pattern classification; Entropy; Intersymbol interference; Noise shaping; Process control; Random variables; Sampling methods; Spectral analysis; Stochastic processes; Stochastic resonance; Terminology;
fLanguage :
English
Journal_Title :
Information Theory, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9448
Type :
jour
DOI :
10.1109/TIT.1978.1055890
Filename :
1055890
Link To Document :
