LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications
In order to improve the accuracy of signal recovery after transmitting over atmospheric turbulence channel, a deep-learning-based signal detection method is proposed for a faster-than-Nyquist (FTN) hybrid modulated optical wireless communication (OWC) system. It takes advantage of the long short-ter...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8992 |
| _version_ | 1797463897104449536 |
|---|---|
| author | Minghua Cao Ruifang Yao Jieping Xia Kejun Jia Huiqin Wang |
| author_facet | Minghua Cao Ruifang Yao Jieping Xia Kejun Jia Huiqin Wang |
| author_sort | Minghua Cao |
| collection | DOAJ |
| description | In order to improve the accuracy of signal recovery after transmitting over atmospheric turbulence channel, a deep-learning-based signal detection method is proposed for a faster-than-Nyquist (FTN) hybrid modulated optical wireless communication (OWC) system. It takes advantage of the long short-term memory (LSTM) network in the recurrent neural network (RNN) to alleviate the interdependence problem of adjacent symbols. Moreover, an LSTM attention decoder is constructed by employing the attention mechanism, which can alleviate the shortcomings in conventional LSTM. The simulation results show that the bit error rate (BER) performance of the proposed LSTM attention neural network is 1 dB better than that of the back propagation (BP) neural network and outperforms by 2.5 dB when compared with the maximum likelihood sequence estimation (MLSE) detection method. |
| first_indexed | 2024-03-09T18:00:10Z |
| format | Article |
| id | doaj.art-85795a19679f4ced9078d38388083da7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:00:10Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-85795a19679f4ced9078d38388083da72023-11-24T09:59:04ZengMDPI AGSensors1424-82202022-11-012222899210.3390/s22228992LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless CommunicationsMinghua Cao0Ruifang Yao1Jieping Xia2Kejun Jia3Huiqin Wang4School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, ChinaIn order to improve the accuracy of signal recovery after transmitting over atmospheric turbulence channel, a deep-learning-based signal detection method is proposed for a faster-than-Nyquist (FTN) hybrid modulated optical wireless communication (OWC) system. It takes advantage of the long short-term memory (LSTM) network in the recurrent neural network (RNN) to alleviate the interdependence problem of adjacent symbols. Moreover, an LSTM attention decoder is constructed by employing the attention mechanism, which can alleviate the shortcomings in conventional LSTM. The simulation results show that the bit error rate (BER) performance of the proposed LSTM attention neural network is 1 dB better than that of the back propagation (BP) neural network and outperforms by 2.5 dB when compared with the maximum likelihood sequence estimation (MLSE) detection method.https://www.mdpi.com/1424-8220/22/22/8992faster-than-Nyquistneural networkhybrid modulationattention mechanismoptical wireless communication |
| spellingShingle | Minghua Cao Ruifang Yao Jieping Xia Kejun Jia Huiqin Wang LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications Sensors faster-than-Nyquist neural network hybrid modulation attention mechanism optical wireless communication |
| title | LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications |
| title_full | LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications |
| title_fullStr | LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications |
| title_full_unstemmed | LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications |
| title_short | LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications |
| title_sort | lstm attention neural network based signal detection for hybrid modulated faster than nyquist optical wireless communications |
| topic | faster-than-Nyquist neural network hybrid modulation attention mechanism optical wireless communication |
| url | https://www.mdpi.com/1424-8220/22/22/8992 |
| work_keys_str_mv | AT minghuacao lstmattentionneuralnetworkbasedsignaldetectionforhybridmodulatedfasterthannyquistopticalwirelesscommunications AT ruifangyao lstmattentionneuralnetworkbasedsignaldetectionforhybridmodulatedfasterthannyquistopticalwirelesscommunications AT jiepingxia lstmattentionneuralnetworkbasedsignaldetectionforhybridmodulatedfasterthannyquistopticalwirelesscommunications AT kejunjia lstmattentionneuralnetworkbasedsignaldetectionforhybridmodulatedfasterthannyquistopticalwirelesscommunications AT huiqinwang lstmattentionneuralnetworkbasedsignaldetectionforhybridmodulatedfasterthannyquistopticalwirelesscommunications |