An Intelligent Transportation Network for the Brain based on Observed Driving Patterns

This Connected autonomous vehicle can effectively overcome the perceived limitations of human drivers through the use of communication and artificial intelligence technology. However, due to the high dynamics of the vehicular network and the various disruptions and handovers that occur, providing solid communication lines between cars is still difficult, and this might have disastrous consequences. This work proposes a technique for intelligently grouping vehicles in the heterogeneous Cognitive Internet of Vehicles based on their driving behaviours (CIoVs). The driving mode with numerous feature parameters is analysed in the proposed method to precisely capture driving traits. With the goal of facilitating trustworthy clustering of networked autonomous cars, a method based on neural network pattern recognition and the principles of evolutionary algorithms is developed. The cognitive engines can identify the different driving styles and cluster cars that share that style together. We also study the clustering mechanism's communication performance and construct the stability and life duration of clusters. Data from simulations shows that associated to state-of-the-art methods, the suggested mechanism increases reliable communication throughput by around 14.4% and average cluster lifespan by about 11.5%.