Deep Learning Based Parallel Detector for MIMO Systems
Di Huang, Xueqin Jiang, Sijing Chen, Yun Ping Wu, Enjian Bai · 2020
Multi-input multi-output (MIMO) technology becomes one of the most popular technologies for the fifth-generation (5G) wireless networks due to the advantages in terms of spectrum efficiency and data rate. However, some existing MIMO detectors cannot achieve a good trade-off between the performance and computational complexity. In this paper, we propose a novel DL-based detector for signal detection in MIMO systems, which integrates several modified DNNs into a parallel structure. By changing the connection between layers of conventional deep neural network (DNN) detectors and introducing some differences into these modified DNNs, the diversity of the detection results of these modified DNNs can be achieved. The numerical results verify that our proposed DL-based detector can obtain better performance in MIMO systems compared with some existing linear detectors and conventional DNN detector.