Title :
A paradigm for blind IIR equalization using the constant modulus criterion and an artificial immune network
Author :
Attux, Romis R F ; de Castro, Leandro N. ; Von Zuben, Fernando J. ; Romano, João Marcos T
Author_Institution :
FEEC/Unicamp, Campinas, Brazil
Abstract :
We propose a new paradigm for optimal blind IIR equalization using the well-known constant modulus criterion and an artificial immune network. Tests in three different scenarios reveal the efficiency of the proposal, attested by excellent global convergence rates (100% in two cases) and adaptation patterns.
Keywords :
IIR filters; blind equalisers; recurrent neural nets; artificial immune network; blind IIR equalization; constant modulus criterion; Blind equalizers; Convergence; Filtering theory; IIR filters; Interference; Nonlinear filters; Poles and zeros; Process design; Proposals; Testing;
Conference_Titel :
Neural Networks for Signal Processing, 2003. NNSP'03. 2003 IEEE 13th Workshop on
Print_ISBN :
0-7803-8177-7
DOI :
10.1109/NNSP.2003.1318083
