Learning a robust classifier for short-term traffic state prediction

作者：

Highlights：

• A robust multi-class SVM is proposed to alleviate the effect of traffic data with outliers.

• An iterative algorithm is designed to solve non-smooth L 2,p-norm optimization problem.

• A novel classification indicator (ample degree) is utilized to forecast the traffic state.

• A hybrid kernel function is built by combining polynomial and Gaussian kernel for multi-class SVM.

摘要

•A robust multi-class SVM is proposed to alleviate the effect of traffic data with outliers.•An iterative algorithm is designed to solve non-smooth L 2,p-norm optimization problem.•A novel classification indicator (ample degree) is utilized to forecast the traffic state.•A hybrid kernel function is built by combining polynomial and Gaussian kernel for multi-class SVM.

论文关键词：Classification indicator system,Model optimization framework,Robust prediction model,Short-term traffic state prediction,Support vector machine

论文评审过程：Received 23 September 2021, Revised 2 February 2022, Accepted 3 February 2022, Available online 10 February 2022, Version of Record 24 February 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108368