Jacobian linear regression and Tate Bryant Euler angle enabled autonomous vehicle LiFi communication sustained IOT

Abstract

Artificial Intelligence (AI) and the constant paradigm shift in road traffic have led to a need for significant improvement in road safety to minimize traffic accidents. LiFi helps minimize accidents by transmitting data between multiple vehicles (i.e. Vehicle-to-Vehicle (V2V)) and between vehicles and infrastructure (i.e. Vehicle-to-Infrastructure (V2I)) without interference. LiFi uses light to transmit data between devices or vehicles, which ensures efficient data transmission speed and is therefore considered a safe technology. A method called Deep Jacobian Regression and Tate Bryant Euler Recommendation (DJR-TBER) is proposed in this paper based on V2V and V2I autonomous vehicle communication. The proposed method DJR-TBER consists of an input layer, four hidden layers and finally an output layer. Sensors are first used to obtain the information. A linear regression-based speed evaluation model is developed and followed by a Jacobi matrix-based distance evaluation model in the hidden layer. The third hidden layer by developing a distance evaluation model. The use of Laplacian function ensures secure V2I communication for the autonomous vehicle. Finally, a Tate-Bryant-Euler angle-based model for emergency handling is proposed in the hidden layer to optimally consider the aspect of braking in emergency situations and thus increase driving safety.

Keywords

• Artificial intelligence
• vehicle to vehicle
• vehicle to infrastructure
• light fidelity
• Deep Jacobian Regression
• Tate Bryant Euler recommendation