Sub-optimal Multiuser Detector Using a Chaotic Neural Network with Decaying Chaotic Noise

Abstract

This paper proposes a sub-optimal multiuser detector (MUD) algorithm for CDMA system based on the neural network with a novel Chaotic Neural Network with Decaying Chaotic Noise, and gives a concrete model of the MUD after appropriate transformations and mappings. On the basis of the Hopfield neural network with transient chaos and time-varying gain (NNTCTG), the proposed chaotic noised Hopfield neural network(CNHNN) introduces the decaying chaotic noise to each neuron, and the noise is gradually reduced to zero. The proposed CNHNN has richer and more complex dynamics than NNTCTG, and the transient chaos enables the network to escape from local energy minima and to settle down at the global optimal solution, so that it can be expected to have much powerful ability to search for globally optimal or sub-optimal solutions ,and can refrain from the serious local optimal problem of Hopfield-type neural networks. Simulation experiments have been performed to show the effectiveness and validation of the proposed method for MUD problem.