In view of reducing the complexity of signal detection in massive multiple-input multiple-output (MIMO) receivers, the use of non-coherent detection is favored over usual coherent techniques that require complex channel estimation. In this paper, a deep-learning approach to implement non-coherent multiple-symbol detection for differential phase-shift keying (DPSK) multi-user massive MIMO systems is proposed. The proposed deep-learning implementation reduces the high computational complexity required in conventional DPSK detection techniques. Two deep-learning-based multiple-symbol differential detection receiver designs are proposed and compared with decision-feedback differential detection (DFDD), and conventional multiple-symbol differential detection (MSDD) for the same system parameters. Multiple-symbol differential sphere detection (MSDSD) is used to implement conventional MSDD. The results show that the proposed deep-learning-based multiple-symbol differential detection implementation outperforms decision-feedback differential detection and achieves an optimal performance compared to conventional multiple-symbol differential detection implemented by multiple-symbol differential sphere detection for single-user and multi-user scenarios.
In this work, non-coherent massive MIMO differential phase-shift keying modulation (DPSK) detection is considered to get rid of the complexity of channel estimation. However, most of the well-performing DPSK detection techniques require high computational complexity at the receiver. The use of deep-learning is proposed for detecting the transmitted DPSK symbols over a single-user massive MIMO system. We provide a multiple-symbol differential detection implementation using deep-learning. Two deep-learning-based multiple-symbol differential detection receiver designs are proposed and compared with differential detection (DD), decision-feedback differential detection (DFDD), and multiple-symbol differential detection (MSDD) for the same system parameters. Where multiple-symbol differential sphere detection (MSDSD) is used to implement MSDD. The results show that the proposed deep-learning-based classification neural networks outperform decision-feedback differential detection and achieve an optimal performance compared to conventional multiple-symbol differential detection implemented by multiple-symbol differential sphere detection.