Hybrid CNN and LSTM Model (HCLM) for Short-Term Traffic Volume Prediction | ||||
| International Journal of Intelligent Computing and Information Sciences | ||||
| Article 5, Volume 22, Issue 4, December 2022, Page 51-61 PDF (585.62 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ijicis.2022.142804.1189 | ||||
 View on SCiNiTO | ||||
| Author | ||||
Mohamed Ahmed Mead 
| ||||
| New Cairo Fifth Settlement | ||||
| Abstract | ||||
| Managing traffic on roads within cities, especially crowded roads, requires constant and rapid intervention to avoid any traffic congestion on these roads. Forecasting the volume of vehicles on the roads helps to avoid congestion on the roads by directing some of these vehicles to alternative routes. In this paper, it is studied how to deal with road congestion by using deep learning models and Time series dataset with different time intervals to predict the volume of road traffic. Hybrid CNN and LSTM Model (HCLM) is developed to predict the volume of road traffic. Determining the suitable hybrid CNN-LSTM model and parameters for this problem is a major objective of this research. The results confirm that the proposed HCLM for time series prediction achieves much better prediction accuracy than autoregressive integrated moving average (ARIMA) model, CNN model, and LSTM model for Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) measures at a time interval of 25 min and, 75 min. The time required to build these models was also compared, and the model HCLM was outperformed as it required 70% of the time to build it from its nearest competitor. | ||||
| Keywords | ||||
| Traffic Volume; Time Series; Deep Learning; CNN-LSTM; ARIMA | ||||
|
Statistics Article View: 275 PDF Download: 330 |
||||
