2019/11/22 by Mohammad Ali Amirabadi, Amirabadi, M. A.
Computer Science · Engineering · Medicine · Physics and Astronomy · #Corneal surgery and disorders #FOS: Electrical engineering #Optical Wireless Communication Technologies #Orbital Angular Momentum in Optics #Radar Systems and Signal Processing #Signal Processing (eess.SP) #Wireless Signal Modulation Classification #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1912.12232
openalex publication_date 2019/11/22 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
One of the main problems encountered with Free Space Optical (FSO)\nCommunication system is the atmospheric turbulence. Although many solutions\nexist for combating this effect, they have either high complexity or low\nperformance. In this paper, a comprehensive investigation is developed, and\nthree new effective Deep Learning (DL) based solutions are proposed. This\npaper, for the first time, deploys Deep Learning, transceiver learning, as well\nas transmitter learning in FSO communication. In addition, this is the first\ntime that DL approach is implemented in FSO-Multi-Input Multi-Output (MIMO)\ncommunication. Results of the proposed structure are compared with the state of\nthe art MQAM based FSO system with Maximum Likelihood Detection. Wide range of\natmospheric turbulence, from weak to the strong regime, are considered; results\nindicate that the proposed structures despite less complexity, have the same\nperformance as the outstanding conventional structure. In addition, in\ndifferent MIMO structures (different combiners and the different number of\ntransceiver apertures), the proposed structure still achieve the performance of\nthe state of the art conventional system.\n