Signal Detection and Channel Estimation in Multiple Input Multiple Output Communication Systems using Distributed Approximate Message Passing

In recent years, Multiple-Input Multiple-Output (MIMO) have revolutionized reliability and spectral efficiency of wireless communication systems. These systems exploit multiplexing and spatial diversity which enabling the essential for meeting the growing demands of modern wireless networks but it had challenges in detection of signals and estimation of channels. The traditional approaches for signal detection had faced challenges which include computational resources and network architecture. Therefore, this research proposes Distributed Approximate Message Passing (DAMP) for Signal Detection and Channel Estimation in MIMO communication systems. The collected data contains various digital and communication system which are pre-processed by using Deceived Non-Local Means (DNLM) and reduce the noise. These pre-processed data optimal features are extracted using Independent Component Analysis (ICA) with wavelet transform that separates mixed signals into independent components for eliminating the irrelevant attributes. Finally, Distributed Approximate Message Passing (DAMP) is employed that enables message passing framework to approximate the posterior distribution for detecting the signal and channel estimation in MIMO communication systems. The proposed DAMP succeeded with high results including accuracy (98.92%), precision (94.85%), recall (96.86%), F1-score (94.35%) when compared with existing Generative Adversarial Network (GAN).