.png){kind=icon}
.png){kind=icon}
Return
SHINE: Symbol-Based Heuristic Iterative NB-LDPC Coded MIMO BP Detection and Decoding
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2025.3561223.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this letter, we propose SHINE, a Symbol-based Heuristic Iterative NB-LDPC codEd MIMO BP detection and decoding scheme. More specifically, we develop an NB-LDPC coded iterative detection and decoding (IDD) receiver equiped with a fine-tailored LLR interface between the real-domain detection and the Galois-field decoding. To further reduce the complexity of the IDD receiver, we propose a Joint Symbol Pruning Optimization (JSPO) framework, leveraging metaheuristic learning to jointly optimize the symbol search space in both detection and decoding. Numerical results demonstrate that compared with its basic version, SHINE succeeds in achieving up to 37.32% and 58.31% complexity reduction for the detection and the decoding w/o performance degradation. Numerical results also demonstrate the performance merits of the proposed SHINE compared with other NB-LDPC coded IDD counterparts.
Keywords:
Iterative detection and decoding (IDD)
belief propagation (BP)
NB-LDPC codes
multiple-input multiple-output (MIMO)
metaheuristic learning
Journal
IF:
4.4
Papers:
1.3W
Citations:
2.2W