• Ms. G Bhavya Vani
• Mr. O. Sampath

Persistent congestions in the dense transportation networks, which vary in strength and length, pose the biggest threat to sustainable mobility. This kind of congestion cannot be effectively handled by the adaptive traffic signal control standard. Deep learning-based algorithms have demonstrated their value in anticipating adjective outcomes to enhance decision-making on traffic length estimates. The identification and prioritization of harmful elements in order to make human life simpler required the use of deep learning models, which have been around for a while in various application domains. To deal with issues brought on by traffic congestion in real time, a variety of techniques are in use. This study demonstrates how DL models can relieve traffic congestion by merely allowing vehicles to pass through a signal based on their length. Our Our suggested technique combines a number of strategies in an effort to strengthen the exploration operation's teamwork. In this work, we put into practice an application that counts the number of automobiles in user-provided photos. We are utilizing the YOLO pretrained weights in this case to detect the number of vehicles.

Machine Learning Based Traffic Prediction System

" Machine Learning Based Traffic Prediction System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.g193-g196, July-2023, Available :http://www.jetir.org/papers/JETIR2307631.pdf

" Machine Learning Based Traffic Prediction System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppg193-g196, July-2023, Available at : http://www.jetir.org/papers/JETIR2307631.pdf