•  
  •  
 

Abstract

Given the growing complexity of urban transportation systems, precise traffic flow forecasting is essential for reducing not only issues of congestion but also, for boosting road safety and enhancing mobility management. This study integrates Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Long Short-Term Memory (LSTM), and Recurrent Neural Networks (RNN) to present a hybrid deep learning framework for traffic prediction. Of these, the CNN-LSTM model is a reliable option for real-time traffic forecasting since it successfully captures both spatial and temporal dependencies, resulting in superior predictive performance. The dataset used to assess the framework includes 48,120 records from a traffic monitoring system that include hourly vehicle counts at several intersections. With an average of 22.79 vehicles per hour, a variance of 430.57, and a standard deviation of 20.75, statistical analysis shows that traffic fluctuates significantly. Based on experimental results, CNN-LSTM achieves a competitive Mean sq\.d Error (MSE) of 0.0095, a precision of 0.73, and a recall of 0.74, outperforming LSTM and RNN in high-traffic situations. This study demonstrates the potential of hybrid models–-in particular, CNN-LSTM–-in striking a balance between computational efficiency and predictive accuracy. Future research should incorporate GPS feeds and real-time data from IoT sensors to improve model adaptability and offer a scalable and clever urban traffic management solution.

Download

Included in

Engineering Commons

Share

COinS