• Swanand Vijay Kulkarni
• Prof. A.V. Shah

Real-time microcontrollers and low-power embedded systems are examples of the contemporary technologies required for the realization of our idea. The fundamental components of our architecture are primarily smart and intelligent sensor systems that can gather data in real time, use edge machine learning to identify patterns in sensor data to facilitate decision-making, and send intelligence to distant devices. The goal of this research is to create a defensive alerting system that can identify and warn of the dangers posed by careless driving. Based on machine learning methods, we suggest a cooperative driving performance rating (CDPR) mechanism to automatically and intelligently identify irresponsible vehicles by combining the computing power of a cloud server with that of modern automobiles. Vehicles, road-side units (RSU), and a cloud server comprise the three-tier system architecture that is created from current vehicular networks to provide such a defensive alerting system. Furthermore, we build our scheme such that each vehicle only uploads data of driving actions with irresponsible potential to RSUs, further reducing the transmission burden of the CDPR mechanism, considering that the majority of vehicles can be trusted to drive carefully. The cloud server uses support vector machine (SVM) and decision-tree machine learning models to score each vehicle's driving performance globally based on the aggregated data. Finally, for evaluation, we incorporate the suggested CDPR mechanism into Simulation of Urban Mobility (SUMO), a well-known traffic simulator.

Cooperative driving performance rating (CDPR), Road-side units (RSU), Simulation of Urban Mobility (SUMO)

"AI BASED RASH DRIVING DETECTION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.c460-c465, May-2025, Available :http://www.jetir.org/papers/JETIR2505259.pdf

"AI BASED RASH DRIVING DETECTION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppc460-c465, May-2025, Available at : http://www.jetir.org/papers/JETIR2505259.pdf