Laser & Optoelectronics Progress, Volume. 58, Issue 11, 1106001(2021)
Intelligent Optical Communication Based on Self-Organizing Incremental Generative Adversarial Network
Figures & Tables(9)
Fig. 1. Flow chart of the online learning system. (a) End-to-end communication system; (b) online incremental end-to-end learning system
Fig. 5. Accuracy and loss function curves of different networks. (a) Accuracy; (b) loss function
Table 1. Environmental parameters of the experiment
View tableTable 1. Environmental parameters of the experiment
Category Parameter Operating system Windows10，64 bit Processor Intel i7 9700K GPU GTX 1060 RAM 16 GB DDR4 1600 MHz Anaconda3 5.2.0
Table 2. Parameters of the model
View tableTable 2. Parameters of the model
Parameter Value Transmitter hidden layers 32, 32 Learning rate 0.0005 Receiver hidden layers 32, 32 Learning rate 0.0005 Generator hidden layers 128, 128, 128 Discriminator hidden layers 32, 32, 32 Learning rate 0.0001
Table 3. Parameters of FSO system and channel
View tableTable 3. Parameters of FSO system and channel
Parameter Symbol Value Link distance /km L 100 Laser wavelength /nm λ 1550 Photoelectric conversion efficiency Rp 1 Receiver diameter /mm Dr 200 Refraction parameters Cn2 2.7×10-13 Rytov variance(Log) σR1 0.24 Rytov variance(G-G) σR2 1.7
Tools
Get Citation
Copy Citation Text
Di Mu, Wen Meng, Wenya Liu, Xiang Wang, Shanghong Zhao. Intelligent Optical Communication Based on Self-Organizing Incremental Generative Adversarial Network[J]. Laser & Optoelectronics Progress, 2021, 58(11): 1106001
Paper Information
Category: Fiber Optics and Optical Communications
Received: Sep. 12, 2020
Accepted: Oct. 29, 2020
Published Online: Jun. 7, 2021
The Author Email: Meng Wen (meng-wen_mw@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20