Vehicle light communication design using an efficient learning model

Abstract

Vehicle communication is preferable in vehicular visible light communication (VVLC) owing to its low complexity, secure, interference-free characteristics, line of sight exploitation, vehicle light emitting diodes, and vehicle light propagation characteristics. The channels of VVLC are stochastic and give less accuracy during path loss prediction without considering external environmental factors. There is no wireless channel adopted for channel-based frequency response and node multi-access. This work concentrates on modeling a machine learning-based model for VVLC channel modeling and enhancing the accuracy by specifically concentrating on frequency response via multiple variables like environmental factors and vehicle mobility. The proposed model considers variables with the adoption of an Extreme learning model (ELM) with feed-forward neural networks (FFNN). This model performs information processing over the VLC channel to enhance prediction. The accuracy of the proposed model relies on channel modeling and multi-access relays among nodes. The proposed model performance is evaluated with prevailing approaches to produce distance prediction and response among the relay nodes. Some metrics like BER, SNR, MSE, received power, impulse, and frequency response, and received optical power are evaluated and compared with other approaches.