With the growth of intelligent transportation systems, enhancing the accuracy of short-term traffic flow predictions is crucial for effective real-time traffic management. This paper introduces a method for short-term traffic flow forecasting that utilizes Empirical Mode Decomposition (EMD) for data processing, combined with a LightGBM model optimized through Bayesian optimization. EMD first decomposes the traffic flow data. Then, Bayesian optimization fine-tunes the LightGBM model parameters, creating a prediction model. The method’s effectiveness is assessed using publicly available traffic flow data and compared to existing algorithms. Results show that this approach better captures traffic flow trends, offering improved prediction accuracy for short-term forecasting.
Boosting Short-Term Traffic Flow Prediction with EMD and Bayesian Optimization
Lect. Notes Electrical Eng.
International Conference on Computer Engineering and Networks ; 2024 ; Kashi, China October 18, 2024 - October 21, 2024
Proceedings of the 14th International Conference on Computer Engineering and Networks ; Chapter : 25 ; 275-283
2025-05-13
9 pages
Article/Chapter (Book)
Electronic Resource
English
Short-term traffic flow prediction method and system based on Bayesian optimization
European Patent Office | 2020
|Short-Term Traffic Flow Prediction Based on Bayesian Fusion
TIBKAT | 2020
|Short‐term traffic flow prediction with linear conditional Gaussian Bayesian network
Online Contents | 2016
|Short-Term Freeway Traffic Flow Prediction: Bayesian Combined Neural Network Approach
Online Contents | 2006
|