Authors:
Y. N. Trupthi, K. Chitra, V. M. Harilakshmi, P. Paramasivan, S. Suman Rajest, M. Mohamed Sameer Ali, Prasanna Ranjith Christodoss
Addresses:
Department of Computer Applications, Dayananda Sagar Academy of Technology and Management, Bengaluru, Karnataka, India. Department of Research and Development & International Student Affairs, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Computing, Mathematics and Physics, Messiah University, Mechanicsburg, Pennsylvania, United States of America.
Abstract:
According to the opinions of other academics, traffic prediction is a contentious problem. It is becoming an increasing concern as the amount of motorised traffic continues to climb, and there is limited space available for transportation infrastructure development. An unabated rise in the number of motorised vehicles causes congestion in smart cities. When designing effective traffic management systems for smart cities, it is necessary to provide accurate estimates of traffic activity. This challenge is tackled in this study by applying two models, Random Forest and K-Nearest Neighbours (KNN), to estimate daily traffic levels. Random Forest is a modelling technique that uses multiple decision trees. An actual traffic manager in Morocco is consulted to obtain ten months' worth of actual traffic volumes for a specific road stretch. This information is then used to accomplish the task of prediction. Metrics that have been established in advance are used to evaluate performance. The results of the experiments demonstrate that the developed Random Forest model achieves the highest level of prediction accuracy, which is roughly 95%.
Keywords: Advanced Machine Learning; Predictive Model; Traffic Prediction; Urban Traffic Management; Traffic Congestion; Random Forest; K-Nearest Neighbours (KNN); Transport Infrastructure.
Received: 08/10/2024, Revised: 05/01/2025, Accepted: 19/02/2025, Published: 07/06/2025
DOI: 10.64091/ATICS.2025.000135
AVE Trends in Intelligent Computing Systems, 2025 Vol. 2 No. 2 , Pages: 111-121