Belief Propagation based Deep Neural Networks for MIMO Detection: DNN-BP

• Published in: IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC ...) (Online) Vol. 4; pp. 835 - 839
• Main Authors: Zhou, Changqing, Ma, Bo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.06.2021
• Subjects: Bit error rate; Damping; Information management; Machine learning; Machine learning algorithms; MIMO system signal detection; Neural networks; Simulation; Symbol-based BP detection algorithm
• ISSN: 2693-2776
• DOI: 10.1109/IMCEC51613.2021.9482384

The paper introduces principles of Belief Propagation (BP) algorithm and Damped BP algorithm firstly. Then, with the BP algorithm and machine learning, this paper proposes a detection algorithm based on BP based deep neural networks (DNN-BP). The DNN-BP algorithm selects the optimal damping factor through machine learning methods, which solves the problem that the damping factor is difficult to determine in traditional algorithms. Simulation results show that the DNN-BP detection algorithm can further improve the convergence of the BP algorithm and improve the Bit Error Rate performance.