Title :
Optimal design of convex combinations for adaptive filtering with parallel signals
Author :
Zhu, Yunmin ; Gao, Aijun
Author_Institution :
Inst. of Comput. Appl., Acad. Sinica, Chengdu, China
Abstract :
In practical applications of adaptive filtering, we often face a group of parallel signals. Therefore, the optimal design of the convex combinations of those parallel signals for adaptive filtering in the least mean square sense is an important problem. In this paper, we present the optimal convex combination coefficients, which depend only on the covariance of the distinct part of each individual signal from others. Furthermore we suggest an adaptive algorithm for the adaptive filtering to implement the above optimal design of convex combinations of the parallel signals
Keywords :
adaptive filters; filtering and prediction theory; least squares approximations; state estimation; adaptive algorithm; adaptive filtering; convex combinations; covariance; least mean square sense; observers; parallel signals; Adaptive algorithm; Adaptive filters; Algorithm design and analysis; Approximation algorithms; Computer applications; Concurrent computing; Filtering; Least squares approximation; Signal design; Sonar;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344805