AN RKHS APPROACH TO ROBUST L-2 ESTIMATION AND SIGNAL-DETECTION

被引:10
作者
BARTON, RJ
POOR, HV
机构
[1] UNIV ILLINOIS,DEPT ELECT ENGN,URBANA,IL 61801
[2] UNIV ILLINOIS,COORDINATED SCI LAB,URBANA,IL 61801
基金
美国国家科学基金会;
关键词
D O I
10.1109/18.54898
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The application of reproducing kernel Hilbert space (RKHS) theory to the problems of robust signal detection and estimation is investigated. It is shown that this approach provides a general and unified framework in which to analyze the problems of L2 estimation, matched filtering, and quadratic detection in the presence of uncertainties regarding the second-order structure of the random processes involved. © 1990 IEEE
引用
收藏
页码:485 / 501
页数:17
相关论文
共 22 条
[1]   THEORY OF REPRODUCING KERNELS [J].
ARONSZAJN, N .
TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1950, 68 (MAY) :337-404
[2]   OPTIMUM QUADRATIC DETECTION OF A RANDOM VECTOR IN GAUSSIAN NOISE [J].
BAKER, CR .
IEEE TRANSACTIONS ON COMMUNICATION TECHNOLOGY, 1966, CO14 (06) :802-&
[3]  
Barbu V., 1986, CONVEXITY OPTIMIZATI
[4]  
BARTON RJ, IN PRESS GENERALIZED
[5]   THE AUTOMATIC ROBUSTNESS OF MINIMUM DISTANCE FUNCTIONALS [J].
DONOHO, DL ;
LIU, RC .
ANNALS OF STATISTICS, 1988, 16 (02) :552-586
[6]  
DUNFORD N, 1963, LINEAR OPERATORS
[7]  
Folland G. B., 1984, REAL ANAL
[10]   RKHS APPROACH TO DETECTION AND ESTIMATION PROBLEMS .2. GAUSSIAN SIGNAL DETECTION [J].
KAILATH, T ;
WEINERT, HL .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1975, 21 (01) :15-23