TRAFFIC CONGESTION PREDICTION THROUGH DEEP LEARNING

Authors

  • Hrushikesh Shelke, Vivek Lokhande, Akshay Pawar, Mahesh Solanke, Prof. Tanvi Ghodke Department of Computer Engineering K.J College of Engineering and Management Research, Pune-India

Keywords:

Traffic Congestion, Artificial Neural Networks, Decision Making, Segrigation, Machine learning, Labelling, Smart City, Traffic Managment.

Abstract

Congestion in cities has become an increasingly severe concern across the planet, affecting progress and people's everyday lives. It also happens in India’s medium and large areas, posing a threat to the nation’s growth. Humans may learn from the governance and administration of urban traffic systems that traffic congestion can be mitigated or reduced if we could somehow predict traffic congestion that will happen in just few moments or which have already transpired in a few seconds and apply timely, appropriate traffic mitigation strategies. As a result, traffic congestion forecasting is critical for enhancing energy effectiveness and reliability of the transportation system. For this purpose a number of different approaches on this topic have been evaluated and detailed in this survey article. This has allowed the effective realization of our approach for a traffic congestion prediction system that will be detailed in the subsequent editions of this research article.

Downloads

Published

-

How to Cite

Hrushikesh Shelke, Vivek Lokhande, Akshay Pawar, Mahesh Solanke, Prof. Tanvi Ghodke. (2022). TRAFFIC CONGESTION PREDICTION THROUGH DEEP LEARNING. EPRA International Journal of Research and Development (IJRD), 7(1), 34–37. Retrieved from http://www.eprajournals.net/index.php/IJRD/article/view/17