Innovative methods for analyzing traffic are crucial for modernizing transportation infrastructure, particularly in highway planning. This study explores the integration of computer vision techniques, emphasizing image processing and machine learning, for real-time highway traffic analysis. Given the limitations of traditional methods like slow speed and inaccuracy, the importance of computer vision-based real-time analysis can never be exaggerated. In this paper, a hybrid LSTM-ARIMA model is proposed for accurate highway traffic flow estimation by exploiting modern deep learning techniques. This model fuses the advantages of Long Short-Term Memory (LSTM) with those of Autoregressive Integrated Moving Average (ARIMA) to improve forecasting accuracy. Based on the experimental findings, LSTM-ARIMA is more effective than both standalone LSTM and ARIMA approaches since it has a stacking MAE of 0.2662 in case of outgoing traffic as compared to 0.5385 for incoming traffic. These findings demonstrate strong evidence that our proposed approach could revolutionize traffic analysis and management to aid transportation authorities and infrastructure developers in making informed choices when planning their cities or municipalities.
Enhancing Traffic Analysis and Prediction through A Hybrid LSTM-ARIMA Model
2024-08-28
7293379 byte
Conference paper
Electronic Resource
English
Short traffic flow prediction method based on ARIMA and LSTM hybrid neural network
European Patent Office | 2021
|Prediction of ship track based on ARIMA-LSTM
British Library Conference Proceedings | 2022
|Taylor & Francis Verlag | 2025
|