Affiliations: [a] College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China | [b] State Key Laboratory of Geo-Information Engineering, Xi’an, Shaanxi, China | [c] Department of Applied Sciences, École Normale Supérieure, Bujumbura, Burundi
Correspondence:
[*]
Corresponding author: Zhu Xiao, College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, Hunan, China. Tel.: +86 189 3246 5227; E-mail: [email protected].
Abstract: Short-term traffic flow prediction plays a crucial component in transportation management and deployment. In this paper, a novel regression framework for short-term traffic flow prediction with automatic parameter tuning is proposed, with the SVR being the primary regression model for traffic flow prediction and the Bayesian Optimization being the major method for parameters selection. First, the preprocessing of raw traffic flow is carried out by seasonal difference to eliminate the non-stationary of the data. Then, Support Vector Regression model is trained by the pre-processed data. In order to optimize the model parameters, the generalization performance of SVR is modeled as a sample from a Gaussian process (GP). Bayesian optimization determines the parameters configuration of the regression model by optimizing the acquisition function over the GP. Finally, the optimal short-term traffic flow regression model is constructed through repeated GP update and iteratively multiple training of the model. Experiment results show that the accuracy of proposed method is superior to methods of classical SARIMA, MLP-NN, ERT and Adaboost.
