Artificial Neural Network-Based Scheme for 4-PWM OCC System
Jing He, Yiting Yang, Jing He
Abstract
In the letter, an artificial neural network (ANN)-based scheme is proposed and experimentally demonstrated to alleviate the inter-symbol interference (ISI) from the overlap of the exposure time in 4-pulse width modulation (PWM) optical camera communication (OCC) system. By using ANN, it directly restores the gray value sequence to the corresponding data symbol. And down-sampling is not required. The experimental results show that, compared with the conventional demodulation scheme, the ANN demodulation scheme can effectively improve the data rate. When the symbol resolution is 6 pixels per symbol and the illuminance is 2440 lux, the bit error rate (BER) can be reduced to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.78\times 10^{-5}$ </tex-math></inline-formula> at the data rate of 15.84 kb/s in 4-PWM OCC system.