Water-to-Air PAM4 Optical Camera Communication Using Long Short Term Memory Neural Network (LSTM-NN)

Abstract

We demonstrate a wide field-of-view (FOV) water-to-air transmission using rolling-shutter-based optical-camera-communication (OCC). Long-short-term-memory-neural-network (LSTM-NN) is utilized to mitigate the wavy water-surface induced link outage and to decode 4-level pulse-amplitude-modulation (PAM4) rolling-shutter pattern.