Title :
Application of genetic algorithms to Volterra filter structure determination for adaptive systems
Author :
Mandyam, Giridhar
Author_Institution :
Wireless Commun. Syst., Texas Instrum. Inc., Dallas, TX, USA
Abstract :
In this paper a genetic algorithm is used to determine the form of an adaptive Volterra filter that will best model a particular system. A fitness functional is defined that quantifies the performance of a particular Volterra system structure in the adaptation process, and using this functional, a genetic algorithm is utilized to find the best possible Volterra system structure for a given data set. Simulations are done to demonstrate the effectiveness of this approach to this problem.
Keywords :
Volterra series; adaptive filters; adaptive signal processing; conjugate gradient methods; filtering theory; genetic algorithms; nonlinear filters; Volterra filter structure determination; adaptive filters; conjugate gradient algorithm; fitness functional; genetic algorithms; linear filters; nonlinear filters; signal processing; simulation; Adaptive filters; Adaptive systems; Genetic algorithms; Instruments; Microwave communication; Microwave filters; Nonlinear filters; Plasma applications; Vectors; Wireless communication;
Conference_Titel :
Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-8186-7646-9
DOI :
10.1109/ACSSC.1996.599123