• Prajwal C L
• Manyashree U J
• Harshitha N
• Jyothish K S
• Tanushree Mohapatra

This integrated review synthesizes findings from four comprehensive surveys on machine learning approaches for traffic prediction in Intelligent Transportation Systems (ITS). The analysis covers 20 key studies employing diverse techniques including LSTM, GRU, YOLO variants (v5/v8), RT-DETR, Graph Convolutional Networks, and hybrid architectures. The review identifies three dominant research themes: temporal traffic prediction using recurrent networks, spatial-temporal modeling through graph-based approaches, and real-time object detection for adaptive control. Across all studies, deep learning models demonstrated superior performance over traditional methods, with LSTM achieving 92.3% prediction accuracy and YOLOv8 reaching 95.8% detection precision. Critical challenges include handling missing data (addressed via tensor completion and GANs), computational efficiency (improved through GRU and edge computing), and system integration (facilitated by IoT and reinforcement learning). The paper concludes with recommendations for future research directions in scalable, multi-modal traffic prediction systems.

Traffic Prediction, Deep Learning, LSTM, YOLO, Graph Neural Networks, Intelligent Transportation Systems.

"Integrated Review on Machine Learning Approaches for Traffic Prediction in Intelligent Transportation Systems ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.b497-b502, May-2025, Available :http://www.jetir.org/papers/JETIR2505156.pdf

"Integrated Review on Machine Learning Approaches for Traffic Prediction in Intelligent Transportation Systems ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppb497-b502, May-2025, Available at : http://www.jetir.org/papers/JETIR2505156.pdf