{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:19:35Z","timestamp":1776277175605,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T00:00:00Z","timestamp":1668902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the NSFC Program","award":["62265010"],"award-info":[{"award-number":["62265010"]}]},{"name":"the NSFC Program","award":["61875080"],"award-info":[{"award-number":["61875080"]}]},{"name":"the NSFC Program","award":["62261033"],"award-info":[{"award-number":["62261033"]}]},{"name":"the NSFC Program","award":["20JR5RA472"],"award-info":[{"award-number":["20JR5RA472"]}]},{"name":"Natural Science Foundation of Gansu Province, China","award":["62265010"],"award-info":[{"award-number":["62265010"]}]},{"name":"Natural Science Foundation of Gansu Province, China","award":["61875080"],"award-info":[{"award-number":["61875080"]}]},{"name":"Natural Science Foundation of Gansu Province, China","award":["62261033"],"award-info":[{"award-number":["62261033"]}]},{"name":"Natural Science Foundation of Gansu Province, China","award":["20JR5RA472"],"award-info":[{"award-number":["20JR5RA472"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s22228992","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T04:39:59Z","timestamp":1669005599000},"page":"8992","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["LSTM Attention Neural-Network-Based Signal Detection for Hybrid Modulated Faster-Than-Nyquist Optical Wireless Communications"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1610-2007","authenticated-orcid":false,"given":"Minghua","family":"Cao","sequence":"first","affiliation":[{"name":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifang","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieping","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejun","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiqin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"016103","DOI":"10.1117\/1.OE.59.1.016103","article-title":"Far-field laser spot image detection for use under atmospheric turbulence","volume":"59","author":"Ke","year":"2020","journal-title":"Opt. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.optcom.2018.10.027","article-title":"Performance and equilibrium experiment of a multiband CAP modulation system in wireless optical communication","volume":"434","author":"Wu","year":"2019","journal-title":"Opt. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1002\/j.1538-7305.1975.tb02043.x","article-title":"Faster-than-nyquist signaling","volume":"54","author":"Mazo","year":"1975","journal-title":"Bell Syst. Tech. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1109\/TIT.1974.1055186","article-title":"Optimal decoding of linear codes for minimizing symbol error rate","volume":"20","author":"Bahl","year":"1974","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Matar, M.O., Jana, M., Mitra, J., Lampe, L., Lis, M., and Soc, I.C. (2020, January 3\u20136). A Turbo Maximum-a-Posteriori Equalizer for Faster-than-Nyquist Applications. Proceedings of the 28th IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), Fayetteville, AR, USA.","DOI":"10.1109\/FCCM48280.2020.00030"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/MSP.2020.2988436","article-title":"Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities","volume":"38","author":"Cococcioni","year":"2021","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1049\/ote2.12060","article-title":"Low complexity deep learning algorithms for compensating atmospheric turbulence in the free space optical communication system","volume":"16","author":"Amirabadi","year":"2022","journal-title":"IET Optoelectron."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9174","DOI":"10.1109\/TVT.2020.3000074","article-title":"Time-domain vs. frequency-domain equalization for FTN signaling","volume":"69","author":"Li","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"36579","DOI":"10.1109\/ACCESS.2019.2901066","article-title":"Deep learning-based channel estimation for doubly selective fading channels","volume":"7","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"8549","DOI":"10.1109\/TVT.2018.2851783","article-title":"Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system","volume":"67","author":"Huang","year":"2018","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4","DOI":"10.29026\/oea.2020.200009","article-title":"Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode","volume":"3","author":"Hu","year":"2020","journal-title":"Opto-Electron. Adv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7900709","DOI":"10.1109\/JPHOT.2017.2788894","article-title":"Faster-than-Nyquist pre-coded CAP modulation visible light communication system based on nonlinear weighted look-up table pre-distortion","volume":"10","author":"Liang","year":"2018","journal-title":"IEEE Photonics J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Vinyals, O., Senior, A., and Sak, H. (2015, January 19\u201324). Convolutional, long short-term memory, fully connected deep neural networks. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, Australia.","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lai, S., and Li, M. (2020, January 7\u201311). Recurrent Neural Network Assisted Equalization for FTN Signaling. Proceedings of the IEEE International Conference on Communications (IEEE ICC)\/Workshop on NOMA for 5G and Beyond, Electr Network, Dublin, Ireland.","DOI":"10.1109\/ICC40277.2020.9148769"},{"key":"ref_16","unstructured":"Gong, B. (2021). Research on Demodulation Technology of OAM Atmospheric Laser Communication System Based on Deep Learning. [Master\u2019s Thesis, Beijing University of Posts and Telecommunications]."},{"key":"ref_17","unstructured":"Mao, S.Y. (2020). Research on Two Kinds of Aliasing Signals Translation Based on Recurrent Neural Network. [Master\u2019s Thesis, Xidian University]."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 15\u201320). Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xia, J., Cao, M., Wang, H., Zhou, H., and Qiu, Y. (2022, January 8\u201311). Deep Learning Based Signal Detection for Hybrid Modulated Faster-than-Nyquist Optical Wireless Communications. Proceedings of the 2022 IEEE 14th International Conference on Advanced Infocomm Technology (ICAIT), Chongqing, China.","DOI":"10.1109\/ICAIT56197.2022.9862811"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1109\/TCOMM.2002.800829","article-title":"Free-space optical communication through atmospheric turbulence channels","volume":"50","author":"Zhu","year":"2002","journal-title":"IEEE Trans. Commun."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1007\/s11801-016-6192-1","article-title":"PDM-DPSK-MPPM hybrid modulation for multi-hop free-space optical communication","volume":"12","author":"Wang","year":"2016","journal-title":"Optoelectron. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"168129","DOI":"10.1016\/j.ijleo.2021.168129","article-title":"A new ABER approximation of FSO system using PPM\u2013GMSK hybrid modulation scheme under weak turbulence","volume":"248","author":"Sharma","year":"2021","journal-title":"Optik"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7983812","DOI":"10.1155\/2020\/7983812","article-title":"Performance Evaluation of MPPM-Coded Wireless Optical MIMO System with Combined Effects over Correlated Fading Channel","volume":"2020","author":"Zhang","year":"2020","journal-title":"Int. J. Antennas Propag."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lin, X., Liu, R., Hu, W., Li, Y., Zhou, X., and He, X. (2017, January 6\u201310). A deep convolutional network demodulator for mixed signals with different modulation types. Proceedings of the 2017 IEEE 15th Intl Conf on Dependable, Autonomic and Secure Computing, 15th Intl Conf on Pervasive Intelligence and Computing, 3rd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC\/PiCom\/DataCom\/CyberSciTech), Orlando, FL, USA.","DOI":"10.1109\/DASC-PICom-DataCom-CyberSciTec.2017.150"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Phys. D Nonlinear Phenom."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1109\/LSP.2018.2835768","article-title":"Residual LSTM attention network for object tracking","volume":"25","author":"Kim","year":"2018","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, Y., Huang, C., and Gao, M. (2019). Object detection network based on feature fusion and attention mechanism. Future Internet, 11.","DOI":"10.3390\/fi11010009"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"154290","DOI":"10.1109\/ACCESS.2020.3017641","article-title":"Automatic modulation classification scheme based on LSTM with random erasing and attention mechanism","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.neucom.2019.01.078","article-title":"Bidirectional LSTM with attention mechanism and convolutional layer for text classification","volume":"337","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tian, F., Wang, L., and Xia, M. (2022). Signals Recognition by CNN Based on Attention Mechanism. Electronics, 11.","DOI":"10.3390\/electronics11132100"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"68866","DOI":"10.1109\/ACCESS.2020.2986679","article-title":"Receiver design for faster-than-Nyquist signaling: Deep-learning-based architectures","volume":"8","author":"Song","year":"2020","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Xu, T., Xu, T., and Darwazeh, I. (2018, January 1\u20134). Deep Learning for Interference Cancellation in Non-orthogonal Signal Based Optical Communication Systems. Proceedings of the Progress in Electromagnetics Research Symposium (PIERS-Toyama), Toyama, Japan.","DOI":"10.23919\/PIERS.2018.8597902"},{"key":"ref_33","first-page":"6","article-title":"Faster-than-Nyquist rate communication via convolutional neural networks-based demodulators","volume":"32","author":"Ouyang","year":"2016","journal-title":"J. Southeast Univ."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6391","DOI":"10.1007\/s10462-021-09975-1","article-title":"A systematic review on overfitting control in shallow and deep neural networks","volume":"54","author":"Bejani","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Andrews, L.C., Phillips, R.L., and Hopen, C.Y. (2001). Laser Beam Scintillation with Applications, SPIE Press.","DOI":"10.1117\/3.412858"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8992\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:22:28Z","timestamp":1760145748000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,20]]},"references-count":35,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228992"],"URL":"https:\/\/doi.org\/10.3390\/s22228992","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,20]]}}}