Neural network matched filter receivers for CDMA systems

A new receiver design using feed-forward artificial neural networks for efficient multi-user detection in CDMA systems is presented in this paper. The heart of the receiver is a special neural network, the neural matched filter (NMF), is trained not only to detect the spreading code of the assigned user but also to suppress the multiple-access interference caused by the waveforms of other users. This technique is shown to be highly resistant to near-far effects. A comparative performance analysis of conventional, optimum multiuser and NMF single user receivers is carried out via Monte Carlo simulation. It is shown that the proposed single user NMF detectors have comparative, and even better, performance than the optimum multi-user receiver in severe near-far cases. This exalted performance is due to the implicit cancellation of cross-correlation between different users´ codes. The suggested technique is also not sensitive to the code selection and does not necessitates the use of sophisticated optimized code families