Abstract

A spatiotemporal approach that simultaneously utilises both spatial and temporal relationships is gaining scientific interest in the field of traffic flow forecasting. Accurate identification of the spatiotemporal structure (dependencies amongst traffic flows in space and time) plays a critical role in modern traffic forecasting methodologies, and recent developments of data-driven feature selection and extraction methods allow the identification of complex relationships. This paper systematically reviews studies that apply feature selection and extraction methods for spatiotemporal traffic forecasting. The reviewed bibliographic database includes 211 publications and covers the period from early 1984 to March 2018. A synthesis of bibliographic sources clarifies the advantages and disadvantages of different feature selection and extraction methods for learning the spatiotemporal structure and discovers trends in their applications. We conclude that there is a clear need for development of comprehensive guidelines for selecting appropriate spatiotemporal feature selection and extraction methods for urban traffic forecasting. Document type: Article

Abstract

Timely predicting and controlling the traffic congestion in a station caused by an emergency is an important task in railway emergency management. However, traffic forecasting in an emergency is subject to a dynamic service network, with uncertainty surrounding elements such as the capacity of the transport network, schedules, and plans. Accurate traffic forecasting is difficult. This paper proposes a practical time&ndash space network model based on a train diagram for predicting and controlling the traffic congestion in a station caused by an emergency. Based on the train diagram, we constructed a symmetric time&ndash space network for the first time by considering the transition of the railcar state. On this basis, an improved A* algorithm based on the railcar flow route was proposed to generate feasible path sets and a dynamic railcar flow distribution model was built to simulate the railcar flow distribution process in an emergency. In our numerical studies, these output results of our proposed model can be used to control traffic congestion. Document type: Article