Neural network based multiuser detection techniques in SDMA-OFDM system

Abstract

The multiuser detection (MUD) process followed by the prominent channel estimation at the receiver end of the SDMA-OFDM (Space Division Multiple Access - Orthogonal Frequency Division Multiplexing) system plays a vital role to retrieve data appropriately. This paper examines the neural network (NN) model based MUD schemes as a possible alternative to Genetic Algorithm (GA) based Minimum Bit Error Rate (MBER) MUD schemes. In this paper, both Widrow-Hoff (WH) learning in single layer structured NN and Back Propagation (BP) learning in a Multi layer perceptron (MLP) structured NN models are described. These techniques offer low complexity and the need for channel estimation can be eliminated. Simulation based performance study is carried out to prove the efficiency of the proposed techniques. The bit Error Rate (BER) and complexity plots show improvement over the previous techniques.