[MH2] Underwater Transmission

3:15 PM - 3:30 PM JST(6:15 AM - 6:30 AM UTC)

[MH2-6] Wave-distorted Signal Correction Using a Convolutional Neural Network in a Water-air OWC System

○ANZI XU¹, YUJIE DI¹, Lian-Kuan Chen¹ (1.The Chinese University of Hong Kong)

Keywords:

Free-space optical transmission,Artificial intelligence and machine learning for optical transmission systems and subsystems,Digital signal processing algorithms for optical communications

A convolutional neural network-based detector is designed to mitigate wave-induced power fluctuation in the wavy WA-OWC channel. The packet loss rate was significantly reduced from 38% to 5%, at a data rate of 1 Gbit/s.