Wavelet Blind Equalization Algorithm Based on Support Vector Machine

In order to improve steady-state mean square error performance and increase the convergence rate, this paper presents a blind wavelet equalization algorithm based on Support Vector Machine initialized. This algorithm uses Support Vector Machine to utilize a short initial data segment, transforms blind equalization problem into support vector regression problem and sets the initial weight. Orthogonal wavelet transform is introduced before signal equalized. The results of computer simulation based on a water channel demonstrate that the algorithm converges fast and the error performance is stable.