Support Vector Machine Wavelet Blind Equalization Algorithm Based on Improved Genetic Algorithm

Abstract

AbstractIn order to greatly overcome the disadvantages of low convergence rate, large mean square error and the local convergence of Wavelet Transform Constant Modulus blind equalization Algorithm(WTCMA), support vector machine wavelet transform constant modulus blind equalization algorithm based on improved genetic algorithm is proposed. This proposed algorithm can make full use of the global optimization ability of genetic algorithm to choose better parameters of Support Vector Machine(SVM) and uses SVM to initialize weight vector via a short initial data segment. When the weight vector of the equalizer is initialized by SVM, the proposed algorithm will carry out the WTCMA. The simulation result with underwater acoustic channel shows that the proposed algorithm outperforms the CMA and WTCMA in the convergent rate and mean square error.KeywordsCMAgenetic algorithmsupport vector machineorthogonal wavelet transform