Authors: Joselin Mercy J, Rithu Kumari R, Dr. K. Geetha
Abstract: Traffic congestion has become a serious issue in rapidly growing cities, causing delays, increased fuel usage, and environmental damage. Traditional traffic systems rely on fixed signals and limited data, making them ineffective in handling real-time traffic variations. To overcome these limitations, this study introduces a smart traffic prediction system that combines Artificial Intelligence (AI) and the Internet of Things (IoT). The system gathers real-time data from devices such as traffic cameras, GPS trackers, and roadside sensors. This data is then analyzed using machine learning models, especially Long Short-Term Memory (LSTM), to predict future traffic conditions. The goal of this system is to improve traffic flow, reduce congestion, and support better decision-making for traffic authorities. With the help of cloud computing, the system can efficiently handle large amounts of data. Experimental results show that this approach performs better than traditional methods by improving prediction accuracy and reducing delays. Overall, this system contributes to smarter cities and better quality of life.
DOI: https://doi.org/10.5281/zenodo.19064146
