A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering
The recently proposed learning-to-learn iterative search algorithm (LISA) for multiple-input multiple-output (MIMO) detection can achieve excellent BER performance for low-order modulation signals, such as BPSK/QPSK, but its performance is degraded as the modulation order increases. This limits its...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10496989/ |
| _version_ | 1797197302719315968 |
|---|---|
| author | Zichun Huang Yuehua Ding Biyun Ma Jie Li Yide Wang |
| author_facet | Zichun Huang Yuehua Ding Biyun Ma Jie Li Yide Wang |
| author_sort | Zichun Huang |
| collection | DOAJ |
| description | The recently proposed learning-to-learn iterative search algorithm (LISA) for multiple-input multiple-output (MIMO) detection can achieve excellent BER performance for low-order modulation signals, such as BPSK/QPSK, but its performance is degraded as the modulation order increases. This limits its application in high data rate transmission. Motivated by this observation, this paper proposes a decomposition-ordering-based LISA (DO-LISA) to improve the accuracy of LISA for higher-order QAM signals. Firstly, the detection of high-order QAM signal is transformed into the detection of QPSK signal to exploit the facility of binary classification. To further exploit the sequential features of a bidirectional long short-term memory (BiLSTM) network, channel ordering is adopted to enhance the detection accuracy. Moreover, to make the proposed method more practical, low-rank decomposition and channel pruning are adopted to accelerate and compress the neural network. Numerical experiments show that the proposed method can achieve quasi-ML BER performance. Compared with the full model, the compact model achieves <inline-formula> <tex-math notation="LaTeX">$2.37\times $ </tex-math></inline-formula> compression ratio and <inline-formula> <tex-math notation="LaTeX">$2.38\times $ </tex-math></inline-formula> acceleration ratio with limited accuracy loss. In addition, the proposed DO-LISA shows its good generalization ability by preserving very good BER performance both in the correlated channel condition and imperfect channel condition. |
| first_indexed | 2024-04-24T06:41:49Z |
| format | Article |
| id | doaj.art-0a3da683fd85494ea88224d8947cc9b6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T06:41:49Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0a3da683fd85494ea88224d8947cc9b62024-04-22T23:00:26ZengIEEEIEEE Access2169-35362024-01-0112539585396410.1109/ACCESS.2024.338753210496989A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel OrderingZichun Huang0Yuehua Ding1https://orcid.org/0000-0003-3100-2204Biyun Ma2https://orcid.org/0000-0002-0765-6753Jie Li3https://orcid.org/0000-0002-9797-5407Yide Wang4https://orcid.org/0000-0002-1461-2003School of Electronics and Information Engineering, South China University of Technology, Guangzhou, ChinaSchool of Electronics and Information Engineering, South China University of Technology, Guangzhou, ChinaSchool of Electronics and Information Engineering, South China University of Technology, Guangzhou, ChinaSchool of Electronics and Information Engineering, South China University of Technology, Guangzhou, ChinaInstitut d’Electronique et des Technologies du numeRique (IETR), CNRS UMR6164, Nantes University, Nantes, FranceThe recently proposed learning-to-learn iterative search algorithm (LISA) for multiple-input multiple-output (MIMO) detection can achieve excellent BER performance for low-order modulation signals, such as BPSK/QPSK, but its performance is degraded as the modulation order increases. This limits its application in high data rate transmission. Motivated by this observation, this paper proposes a decomposition-ordering-based LISA (DO-LISA) to improve the accuracy of LISA for higher-order QAM signals. Firstly, the detection of high-order QAM signal is transformed into the detection of QPSK signal to exploit the facility of binary classification. To further exploit the sequential features of a bidirectional long short-term memory (BiLSTM) network, channel ordering is adopted to enhance the detection accuracy. Moreover, to make the proposed method more practical, low-rank decomposition and channel pruning are adopted to accelerate and compress the neural network. Numerical experiments show that the proposed method can achieve quasi-ML BER performance. Compared with the full model, the compact model achieves <inline-formula> <tex-math notation="LaTeX">$2.37\times $ </tex-math></inline-formula> compression ratio and <inline-formula> <tex-math notation="LaTeX">$2.38\times $ </tex-math></inline-formula> acceleration ratio with limited accuracy loss. In addition, the proposed DO-LISA shows its good generalization ability by preserving very good BER performance both in the correlated channel condition and imperfect channel condition.https://ieeexplore.ieee.org/document/10496989/MIMO detectiondeep learningLSTMV-BLASTcompression |
| spellingShingle | Zichun Huang Yuehua Ding Biyun Ma Jie Li Yide Wang A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering IEEE Access MIMO detection deep learning LSTM V-BLAST compression |
| title | A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering |
| title_full | A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering |
| title_fullStr | A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering |
| title_full_unstemmed | A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering |
| title_short | A Deep MIMO Detector Based on MQAM Signal Decomposition and Channel Ordering |
| title_sort | deep mimo detector based on mqam signal decomposition and channel ordering |
| topic | MIMO detection deep learning LSTM V-BLAST compression |
| url | https://ieeexplore.ieee.org/document/10496989/ |
| work_keys_str_mv | AT zichunhuang adeepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT yuehuading adeepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT biyunma adeepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT jieli adeepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT yidewang adeepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT zichunhuang deepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT yuehuading deepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT biyunma deepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT jieli deepmimodetectorbasedonmqamsignaldecompositionandchannelordering AT yidewang deepmimodetectorbasedonmqamsignaldecompositionandchannelordering |