A New Sequential Detection Based on Hopfield Neural Network in Frequency Selective Fading Channels

摘要

In this paper,a new Hopfield Neural Network(HNN) detector is described to estimate the transmitted sequences from the received signals in mobile communications and order to avoid the convergence of HNN in local minima,a new decreasing step algorithm(DSA) is presented to search the optimum sequence quickly on the basis of the traditional Simulated Annealing (SA)al-gorithm.Computer simulation results show that the new HNN detector provides almost the same performance as that of the Viterbi detector with less calculations. Moreover,compared with Viterbi detector ,direct hardware implementation for HNN detector is feasible and convenient es-pecially for the long constraint length convolutional code.