Monitor and Analyze Sensor Data from a Connected Vehicle Thanks to Cloud Edge Computing

Abstract

Progress on innovative wireless sensors and connected vehicles on intelligent transport systems (ITS) is a recent research topic. It involves the collection and processing of large quantities of sensor data. Many types of sensors embedded in today’s vehicles like cameras, lidar, and radar are useful for monitoring vehicle data. Reliable, low-cost detection, connectivity, computational capability, and powerful analytics usher in a new era of vehicle context detection and vehicle network detection (VANET). However, given the concerns about latency, bandwidth, cost, security, and privacy, as well as the growing capabilities of edge computing devices, it is necessary to examine edge and cloud computing together in order to make informed judgments based on context and performance. So, in this paper, we have proposed three algorithms focused on an intelligent transportation system (ITS) based on both Cloud and Edge computing for monitoring and analyzing vehicle sensor data and its environment. Our proposal is capable of receiving sensor data from the vehicle, analyzing it, and giving effective plans in real-time to the driver suited to his context. These plans can be helpful in reducing traffic congestion and educating the driver on the road situation. Thanks to our proposal, we have contributed to the vehicle, road safety, and traffic efficiency by providing real-time information to the operator. Finally, thanks to the measurements of recall, accuracy, F1 score, and evaluation of execution time, we have approved the performance of our proposal.