Direction of Arrival (DoA) estimation for a Switched-Beam DS-CDMA System using Neural Networks

A new direction of arrival (DoA) estimation method using neural networks (NNs) is presented. The method is especially designed for a switched-beam system (SBS) that operates in an asynchronous direct sequence code division multiple access (DS-CDMA) scheme. The technique exploits the Multiple Access Interference (MAI) suppression done by the code-matched filters in DS-CDMA, and is simple and appropriate for real time applications. Simulations of DoA estimations tests show accurate results for a varying number of interferers.