Blind Equalization using Higher-Order Statistics and Fuzzy-ARTMAP
이정식 · 한국통신학회논문지 · 2002
This paper discusses a blind equalization technique for FIR channel system, that might be minimum phase or not, in digital communication. The proposed techniques consist of two parts. One is to estimate the original channel coefficients based on fourth-order cumulants of the channel output, the other is to employ fuzzy-ARTMAP neural network to model an inverse system for the original channel. Here, the estimated channel is used as a reference system to train the fuzzy-ARTMAP. The proposed fuzzy-ARTMAP equalizer provides fast and easy learning, due to the structural efficiency of fuzzy-ARTMAP; a small number of parameters, automatic increase of hidden units, and the capability of adding new data without retraining previously trained data. In simulation studies, the performance of the proposed blind equalizer is compared with both linear and other neural basis equalizers.