Abstract

Aimed at the shortcoming of neural network blind equalization algorithm, namely, the structure of neural network is difficult to determine, two basic principles of neural network blind equalization algorithm optimized by genetic algorithm were analyzed in the paper, by combining genetic algorithm and neural network blind equalization algorithm. At first, the structure and weight of neural network were optimized together by genetic algorithm, and then, blind equalization algorithm was adopted. The code strategy and the choice of genetic operation operator were elaborated, and the basic step of optimization operation was given. Computer simulations show that, compared with traditional neural network blind equalization algorithm, the steady state residual error of the proposed algorithm is decreased, BER is reduced and convergence speed is quickened.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call