An adaptive serial acquisition of PN sequence in nonhomogenous AWGN channel using artificial neural networks

In this paper, we propose an adaptive non-coherent serial pseudo-noise (PN) acquisition scheme for code division multiple access (CDMA) communication systems. Acquisition systems based on a fixed threshold may not be able to adapt to varying mobile communication environments leading to a high false alarm rate and/or a low detection probability. Accordingly, an adaptively varying threshold scheme based on artificial neural networks, namely the artificial neural networks constant false alarm rate (ANN-CFAR) algorithm for the serial system under consideration to improve the detection performance. The performance of the proposed system in terms of probability of detection, false alarm rate and mean acquisition time in a nonhomogenous Gaussian channel is studied and compared with those of the conventional adaptive acquisition scheme based on CA-CFAR and OS-CFAR detectors.