An Improved soft decision method in Viterbi decoder using artificial neural networks

In this paper, the application of artificial neural networks to improve the efficiency of soft decision in Viterbi decoder is proposed. By adding neural network to the decisionblock of Viterbi decoders and training in supervisor manner, neural networks will be able to anticipate and handle a widerange of distortion. Using the neural networks soft decision inViterbi decoder block would reduce the bit error rate (BER) in data transmission for AWGN channels. This method can providelow bit BER for data transmission on channels with low signal to noise ratio (SNR). The results show that the proposed techniquecan improve the efficiency of decision making in comparison with other methods of decision making (soft, hard and slow), in term ofBER.

Keywords:

Soft decision , Viterbi decoder , neural networks , AWGN channel , Bit Error Rate (BER