期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 207, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2022.118050
关键词
Train dispatching; Control actions; Dwelling times and running times; Classification and regression; Deep forest
类别
资金
- National Nature Science Foundation of China [U1834209, 71871188]
- Science & Technology Department of Sichuan Province [2022NSFSC1867]
- Fundamental Research Funds for the Central Universities [2682021CX051]
In this paper, a hybrid prediction model based on deep forest ensemble learning is proposed to analyze two common rail traffic control actions. Experimental results show that the proposed method provides advanced and timely decision support for the controllers.
Advanced decision support for rail traffic control is significant for enhancing the safety and quality of railway transport service. Data-driven methods have shown powerful learning ability and wide extensibility for prediction, classification, and decision-making problems. In this paper, we propose a hybrid prediction model based on deep forest (DF) ensemble learning to analyze the two common rail traffic control actions, i.e., changing the dwelling times and running times. This basic concept is to mimic the decision-making of rail traffic controllers, providing them with advanced decisions/control actions using data-driven learning algorithms. According to the decision-making approach of rail traffic controllers, the learning process of the model is split into two stages, i.e., learning the type of action (ToA) and the number of changes (NoC) in the dwelling times and running times (i.e., how many dwelling times or running times have been changed compared with the planned ones). The first stage is a classification problem; thus, DF classifier with the synthetic minority oversampling technique (SMOTE) is employed to deal with imbalanced data. In the second stage, the DF regressor treats the NoC in the dwelling and running times as numerical variables and utilizes the information from stage one, i.e., the prediction results of the classification model, to make predictions. The proposed model is calibrated on train operation data from two high-speed railway lines in China. The experimental results and comparative analyses show that the proposed method provides advanced and timely decision support for controllers. These characteristics of the proposed model are imperative for supporting the dynamic decision-making of controllers to manage railway traffic.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据