Long Short-Term Memory Neural Network to Enhance the Data Rate and Performance for Rolling Shutter Camera Based Visible Light Communication (VLC)

Abstract

We propose and demonstrate using Long-Short-Term-Memory neural-network (LSTM-NN) to mitigate inter-symbol-interference (ISI) in 4-level pulse-amplitude-modulation (PAM4) camera based visible-light-communication (VLC) system. Data-rate of 14.4-kbit/s with 3-m free-space transmission is achieved.