Traffic Congestion Prediction using Queuing Theory, Decision Tree, Random Forest, and Deep Belief Network

The exponential growth of urban populations and vehicular owner- ship has escalated the challenge of road traffic congestion in both developed and developing countries. Congestion not only increases travel delays but also aggravates fuel consumption and environmental pollution, impeding the vision of smart, sustainable cities. Traditional statistical and rule-based traffic predic- tion models often fail to capture the dynamic and nonlinear evolution of con- gestion, especially under the influence of exogenous factors such as weather, road incidents, and infrastructural changes. Recent advancements in machine learning and deep learning have offered new paradigms for data-driven, adap- tive traffic prediction. In this research, we propose a comprehensive framework that synergistically combines queuing theory with machine learning algo- rithms—specifically Decision Tree, Random Forest, and Deep Belief Network (DBN)—to provide both interpretable and robust predictions of traffic conges- tion. The model integrates historical and real-time multimodal data, including GPS trajectories, sensor feeds, and incident reports, while leveraging queuing theory to model the fundamental dynamics of vehicular flow at the micro-level. Decision Trees facilitate rule-based feature dominance and initial classification, Random Forests enhance robustness and feature selection, and DBNs perform deep spatiotemporal feature learning. Experimental validation on real-world datasets demonstrates that the proposed hybrid model outperforms conven- tional approaches on key accuracy metrics such as precision and recall. This research contributes a scalable and generalizable traffic congestion prediction solution aligned with the evolving needs of intelligent transportation systems and urban mobility management.