Quantization of prior probabilities for hypothesis testing

被引：28
|
作者：
Varshney, Kush R. [1 ]
Varshney, Lav R. [1 ]
机构：
[1] MIT, Informat & Decis Syst Lab, Cambridge, MA 02139 USA
来源：
IEEE TRANSACTIONS ON SIGNAL PROCESSING | 2008年 / 56卷 / 10期
基金：
美国国家科学基金会;
关键词：
Bayesian hypothesis testing; Bayes risk error; categorization; classification; detection; quantization;
D O I：
10.1109/TSP.2008.928164
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper, Bayesian hypothesis testing is investigated when the prior probabilities of the hypotheses, taken as a random vector, are quantized. Nearest neighbor and centroid conditions are derived using mean Bayes risk error (NORE) as a distortion measure for quantization. A high-resolution approximation to the distortion-rate function is also obtained. Human decision making in segregated populations is studied assuming Bayesian hypothesis testing with quantized priors.
引用
收藏
页码：4553 / 4562
页数：10
相关论文
共 50 条
12345