Deep Learning Aided LLR Correction Improves the Performance of Iterative MIMO Receivers

A Deep Learning (DL) aided Logarithmic Likelihood Ratio (LLR) correction method is proposed for improving the performance of Multiple-Input Multiple-Output (MIMO) receivers, where it is typical to adopt reduced-complexity algorithms for avoiding the excessive complexity of optimal full-search algorithms. These sub-optimal techniques typically express the probabilities of the detected bits using LLRs that often have values that are not consistent with their true reliability, either expressing too much confidence or not enough confidence in the value of the corresponding bits, leading to performance degradation. To circumvent this problem, a Deep Neural Network (DNN) is trained for detecting and correcting both over-confident and under-confident LLRs. We demonstrate that the complexity of employing the DL-aided technique is relatively low compared to the popular reduced-complexity receiver detector techniques since it only depends on a small number of real-valued inputs. Furthermore, the proposed approach is applicable to a wild variety of iterative receivers as demonstrated in the context of an iterative detection and decoding aided MIMO system, which uses a low-complexity Smart Ordering and Candidate Adding (SOCA) scheme for MIMO detection and Low-Density Parity Check (LDPC) codes for channel coding. We adopt Extrinsic Information Transfer (EXIT) charts for quantifying the Mutual Information (MI) and show that our DL method significantly improves the BLock Error Rate (BLER). Explicitly, we demonstrate that about 0.9 dB gain can be achieved at a BLER of 10-3 by employing the proposed DL-aided LLR correction method, at the modest cost of increasing the complexity by 16% compared to a benchmarker dispensing with LLR correction.