Design and Implementation of RS-OFDM scheme for Optical Camera Communication based on Deep Learning

In this paper, we proposed RS-OFDM, which has been suggested in IEEE 802.15.7a Task Group (TG7a Higher Rate, Longer Range Optical Camera Communications (OCC). To reduce ISI effect, which is effect by optical multipath channels, OFDM is proposed for high-rate communication. It is a digital multi-carrier modulation method used for broadband communication systems. For indoor applications such as IoT systems, e-health, transportation, and monitoring systems, OFDM has been widely used in wireless communication systems. In OCC systems, the mobility effect is a major issue since it causes the variance of the optical channel in the time domain, which reduces the system performance. In this paper, we suggested the YOLO algorithm for object identification and tracking in the RS-OFDM system with the mobility impact. Additionally, the deep neural network is used to replace conventional technology (RoI algorithms). Based on that, the RS-OFDM system attained with long distances (16 m) and low BER considering 3 m/s mobility.