MULTIUSER DETECTION USING NEURAL NETWORK FOR FD-MC-CDMA SYSTEM IN FREQUENCY SELECTIVE FADING CHANNELS

Multiple combination of direct sequence CDMA is referred as the Multi-Carrier Code-Division Multiple Access (MC-CDMA). It is known that the MC-CDMA is a kind of signaling method which is used to perform optimal detection of carrier signals under the increased Doppler spread. Multi-user detection in a fading channel environment is a challenging problem in mobile communication MC-CDMA. To solve this problem in this work proposed a new multi-user detector using a Neural network. In order to improve the performance of the MC-CDMA system, Frequency Division is integrated to system known as FD-MC-CDMA system. The proposed FD-MC-CDMA system operates in frequency domain to detect multi-users in a frequency selective fading channel environment. Especially, FD-MC-CDMA divides users into subset of users and enable them to transmit their information through sub carriers instead of utilizing all carriers for information transmission. The proper selection of subset of carriers would ensure the full utilization of merits of frequency diversity which would lead to reduction of MAI experience faces by users. The performance of the proposed FD-MC-CDMA detector shows the ability of adaptive multi-user detection in fading channels such as Additive White Gaussian Noise (AWGN), Rayleigh and Rician fading channels. The simulations demonstrate that the proposed FD-MC-CDMA system structures not only perform similar to a Multiuser Detection (MUD) that detects one user at a time, but its computational complexity is significantly lower. The proposed system is measured in terms of Bit Error Rate (BER), Signal Noise Ratio (SNR) for the number of user's simulations, although both have the same complexity.