Abstract: In order to solve the problems of high bit error rate and poor communication quality in the current communication system interference signal separation method, we proposed a method of computer communication interference signal separation based on neural network. Firstly, the limitations were pointed out by analyzing the current computer communication interference signal separation. Secondly, the channel model of computer communication system was built, and neural networks was used to optimize and control the stability of computer communication system, and the interference signals were separated. Finally, the simulation experiment was used to analyze the validity and superiority. The results show that the proposed method can separate computer communication interference signal accurately, improve the signal to noise ratio of output signal, and reduce bit error rate of communioation system.

Key words: channel model, signal to noise ratio, neural network, bit error rate, communication system, signal separation