Intelligent Traffic Control: Predicting Congestion in Smart Cities Using Voting Classifier
Main Article Content
Abstract
As urbanization continues to accelerate, efficient traffic management has become an essential challenge for the development of smart cities. Traditional traffic prediction methods often struggle to capture the complexity and dynamic nature of city-wide congestion patterns, limiting their effectiveness in real-time traffic control and urban mobility Voting Classifier. This study investigates the use of deep learning techniques, specifically Voting Classifier , to forecast traffic congestion with improved accuracy and reliability. By leveraging both historical and real-time traffic data, we develop neural network models that capture the spatiotemporal dynamics of traffic patterns. The proposed AI-driven framework integrates a variety of urban data sources, including road sensors, GPS trajectories, and weather conditions, to enhance predictive capabilities. Experimental results demonstrate that deep learning models, particularly VOTING CLASSIFIER , outperform conventional statistical methods in traffic congestion forecasting. Our evaluation, using Kaggle datasets, shows that the VOTING CLASSIFIER model achieves superior performance in metrics such as precision, recall, F1score, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), and consistently outperforms other methods across different time intervals. These findings underscore the potential of AI-powered traffic intelligence for smart cities, offering actionable insights for traffic control, route optimization, and overall urban mobility plVoting Classifier ing. The results point to a promising future where urban transportation systems are more efficient, adaptive, and sustainable, thanks to advanced AI techniques.