Deep Neural Network Based Parallel Signal Detection in SM-OFDM System
- Resource Type
- Conference
- Authors
- Zhang, Jinmei; Bai, Zhiquan; Yang, Kaiyue; Mohamed, Abeer; Kwak, Kyungsup; Hao, Xinhong
- Source
- 2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN) Ubiquitous and Future Networks (ICUFN), 2022 Thirteenth International Conference on. :125-129 Jul, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Signal Processing and Analysis
Deep learning
Training
Simulation
OFDM
Bit error rate
Neural networks
Modulation
Deep neural network (DNN)
signal detection
spatial modulation based orthogonal frequency division multiplexing (SM-OFDM)
bit error rate (BER)
- Language
- ISSN
- 2165-8536
A novel deep neural network based parallel signal detection (DNN-PSD) is proposed for the spatial modulation based orthogonal frequency division multiplexing (SM-OFDM) system. With the purpose to reduce the complexity of the conventional DNN, a uniform small-scale DNN with fewer parameters and less training time is exploited to detect the signals for each subcarrier parallelly. Apart from maximum likelihood (ML) and maximal ratio combining (MRC) detection schemes, the detailed DNN-PSD algorithm and its complexity analysis are presented. Simulation results confirm that the bit error rate (BER) performance of the proposed DNN-PSD is far superior to the MRC detection and similar to the optimal ML detection but with much lower complexity under different scenarios. It has more robustness and achieves a finer compromise between BER performance and complexity.