Transfer Learning–Based Artificial Neural Networks Post-Equalizers for Underwater Visible Light Communication

In this paper, we demonstrate two transfer learning based dual-branch multi-layer perceptron post-equalizers (TL-DBMLPs) in underwater visible light communication (UVLC) system. The transfer learning algorithm could reduce the dependence of artificial neural networks (ANN) based post-equalizer on big data and extended training cycles. Compared with DBMLP, the TL-DBMLP is more robust to the jitter of the bias current ( ) of LED, which indicates that TL-DBMLP does not require further training in varying UVLC system. In terms of Vpp varying VLC system, DBMLP requires a training set with a size of more than and 50 training epochs. On the counterpart, the TL-DBMLP only requires a training set with a size of less than and 10 training epochs. Finally, we experimentally demonstrate that transfer learning can effectively reduce ANN dependence on extensive size training data and long training epochs, whether in VLC systems with varying and varying Vpp.