Entity

Time filter

Source Type


Chen D.,Beijing Jiaotong University | Chen L.,Macau University of Science and Technology | Liu J.,Beijing STONE Intelligent Transportation System Integration Co.
Applied Soft Computing Journal | Year: 2013

This paper develops two soft computing models, i.e., the multilayer feedforward network (MFN) based model and the adaptive-network-based fuzzy inference system (ANFIS) based model, to mine the traffic speed patterns/trends for a road link using the sparse historical probe vehicles (PVs) data at the same link. The two models and an additional naive arithmetical average model are tested on the field datasets obtained in some Beijing (China)'s urban expressways. The results illustrate that the soft computing based models have higher robustness to the problem of missing data and their generalization capabilities are better than the arithmetic average model. Comprehensively considering all the performance metrics suggest that the ANFIS offers the best model of traffic trends in studied links. Furthermore, the traffic trends produced by ANFIS provide us the opportunities to identify some meaningful hidden traffic speed patterns. The missing data's influence on the mined traffic speed patterns is also investigated. It is found that the reliability of mined traffic speed patterns decreases with the increasing of the missing data's percentage. Nevertheless, ANFIS based model shows great robustness to the missing data problem. © 2013 Elsevier B.V. All rights reserved. Source


Yang S.-J.,Beijing STONE Intelligent Transportation System Integration Co. | Peng H.-Q.,Beijing Jiaotong University | Wang X.,Beijing Railway Bureau
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2011

Design of traffic signs will affect the route choices of drivers and affect the efficiency of road utilization. This research analyzes the characteristics of the traffic flows of various types of vehicles coming into and going out of the Beijing Southern Railway Station. It is found that the traffic signs on the roads near the Beijing South Railway Station are not enough, and some of the existing traffic signs are discontinuous, irrationally established or unreasonably located. These problems are summarized according to the principle of information coherence and clearness. Finally, the countermeasures are proposed base on the characteristics of the traffic flows around the Beijing Southern Railway Station and the design principle of traffic signs. Source


Yuan S.-P.,China Tietong | Qi K.,Beijing Jiaotong University | Guan J.-Z.,Beijing STONE Intelligent Transportation System Integration Co.
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2011

Variable Message Signs (VMS) system is applied in the trunk road networks in the major cities of China, and plays a positive role in releasing traffic jams. In this research, the development, working principle, information generation, etc. of the urban traffic flow guidance system which is based on VMS are introduced in detail. Meanwhile, the previous research on the traffic flow guidance at home and abroad is reviewed. With the analysis of the requirements of the VMS users and the factors influencing the site distribution of VMS, the location choice model of the VMS is improved by following the principle of the VMS location choices and analyzing the effect of the guiding information on route choices. The impact of the VMS applied for the roads near Beijing South Railway Station is analyzed. Source


Fan L.-L.,Beijing Jiaotong University | Guan W.,Beijing Jiaotong University | Guo T.-D.,University of Chinese Academy of Sciences | Zheng C.-Q.,Beijing Traffic Management Bureau | Guan J.-Z.,Beijing STONE Intelligent Transportation System Integration Co.
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | Year: 2014

Based on traffic guidance information data released by Beijing variable message signs (VMS) system in recent three years, spatial association rules of traffic guidance information release strategy are studied in this paper. At first, hierarchical clustering algorithm is adopted to analyze association degree between event node and upstream VMS. According to intensity of association degree, upstream road sections of event node are divided into different levels of influence space. At the same time, spatial extent of each influence space is determined. Then, association rule mining algorithm based on relational algebra theory is adopted to analyze association degree between adjacent VMS sets. Empirical analysis is conducted based on traffic guidance information data released by Beijing VMS system. Empirical analysis shows that spatial association rules can classify upstream influence road sections into different levels, and identify dependencies between VMS sets. The spatial association rules will be used to lock different influence road sections and corresponding VMS sets in traffic guidance information dissemination. The proposed spatial association rules are applicable to develop traffic guidance information release strategy. ©, 2014, Systems Engineering Society of China. All right reserved. Source


He Z.-B.,Beijing Jiaotong University | Guan W.,Beijing Jiaotong University | Fan L.-L.,Beijing Jiaotong University | Guan J.-Z.,Beijing STONE Intelligent Transportation System Integration Co.
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2014

A macroscopic fundamental diagram(MFD) gives an invariant functional relationship among macroscopic variables in a large urban area. Beijing as one of the largest cities in the world has a number of unique traffic features. A MFD is presented for Beijing urban ring freeways by using traffic detector data. It shows the characteristics of a MFD pertaining to Beijing urban ring freeways, and provides insight into traffic conditions in Beijing. A pattern that lower occupancy variance is associated with lower network flow is observed; it is different from present findings. The observation is investigated and is further attributed to outsync of 5th ring and a radial spread of congestion in Beijing. Source

Discover hidden collaborations