Shanghai Municipal Transportation Information Center

Shanghai, China

Shanghai Municipal Transportation Information Center

Shanghai, China
SEARCH FILTERS
Time filter
Source Type

Zhang Y.,Shanghai Municipal Transportation Information Center | Liu Y.,Shanghai JiaoTong University
Journal of Advanced Transportation | Year: 2011

Accurate and timely traffic forecasting is crucial to effective management of intelligent transportation systems (ITS). To predict travel time index (TTI) data, we select six baseline individual predictors as basic combination components. Applying the one-step-ahead out-of-sample forecasts, the paper proposes several linear combined forecasting techniques. States of traffic situations are classified into peak and non-peak periods. Based on detailed data analyses, some practical guidance and comments are given in what situation a combined model is better than an individual model or other types of combined models. Indicating which model is more appropriate in each state, persuasive comparisons demonstrate that the combined procedures can significantly reduce forecast error rates. It reveals that the approaches are practically promising in the field. To the best of our knowledge, it is the first time to systematically investigate these approaches in peak and non-peak traffic forecasts. The studies can provide a reference for optimal forecasting model selection in each period. © 2010 John Wiley & Sons, Ltd.


Zhang W.,Shanghai Research Center for Wireless Communications | Zhang W.,Chinese Academy of Sciences | Zhang W.,University of Chinese Academy of Sciences | Yang Y.,Shanghai Research Center for Wireless Communications | And 6 more authors.
IEEE International Conference on Communications | Year: 2012

Traffic flow models are essential to performance analysis/evaluation for applications/services provided by Intelligent Transportation Systems (ITS)/Vehicular Ad-hoc networks (VANET). They are also useful guidance for the deployment of ITS/VANET. Many macroscopic traffic flow models have been proposed in the past few decades on the basis of empirical data collected in the US, Canada, Turkey and etc. However these models may not be accurate for traffic flows in cities in China due to the differences in population, transportation infrastructure, and driving culture. In this paper, we collected a large amount of empirical traffic flow data in Shanghai overhead road during three different time periods. Statistical results showed that the lane-level traffic volumes in Shanghai followed Gaussian distribution rather than Poisson distribution which was normally assumed in literature. Regarding lane-level vehicles' velocities, they matched well with Gaussian distribution. The empirical probability mass functions (PMF) for both the traffic volumes and vehicles' velocities were presented. In addition, how these models would impact performance analysis in VANETs was discussed. © 2012 IEEE.


Zhang L.,Tongji University | Shi Y.,Tongji University | Yang W.,Tongji University | Yang T.,Shanghai Municipal Transportation Information Center
Wuhan Ligong Daxue Xuebao (Jiaotong Kexue Yu Gongcheng Ban)/Journal of Wuhan University of Technology (Transportation Science and Engineering) | Year: 2014

Based on the historical traffic data of the west-side North-South Viaduct in Shanghai, this paper introduces survival analysis into the analysis of traffic congestion mechanism, and a hazard-based traffic congestion duration time model is presented. This model analyzes the time attributes of many traffic congestion samples, and employs nonparametric regression-based Kaplan-Meyer model to estimate traffic congestion duration time. Then, the key influence factors of traffic congestion are divided into five types including weekdays, peak time, data year, location and weather, and the spatial-temporal distribution characteristics of traffic congestion duration time is analyzed. Analsis results has shown that the 70% of traffic congestion durations on road segments of west-side North-South Viaduct are no longer than an hour, and there exists significant difference of distribution characteristics under different influence factors.


Yang W.-C.,Tongji University | Zhang L.,Tongji University | Shi Y.-C.,Tongji University | Yang T.,Shanghai Municipal Transportation Information Center
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2014

This paper introduces the survival analysis into the traffic incident mechanism. A survival analysis based Modeling of traffic incident duration for urban expressways is presented. Based on the observed traffic incident data of viaduct expressways in Shanghai, China, this model first analyzes the feature attributes of many traffic incident samples, and employs nonparametric regression based on Kaplan-Meyer model to estimate hazard- based traffic incident duration. Then, the key impact factors of traffic incident are classified into five types and the spatial-temporal distribution characteristics of traffic incident duration time are analyzed. Finally, linear Cox regression is used to comprehensively evaluate multidimensional influencing factors of traffic incident duration. The key characteristic parameters of expressway incident management in Shanghai are optimized to analyze the evolution mechanism of incident duration. The result shows that, for different type of influencing factors, the spatial-time distribution of traffic incident duration in Shanghai expressway has significant difference, and nine factors as day and night, incident type, related vehicle number, related lane number, location, bottleneck and trailer significantly affect the incident duration.


Wang M.,East China University of Science and Technology | Zhang Y.,Shanghai Municipal Transportation Information Center | Shi H.,East China University of Science and Technology
Industrial and Engineering Chemistry Research | Year: 2012

A local model-based predictive control strategy based on linear programming is proposed for partial differential equation descriptions unknown spatially distributed systems (SDSs). First, the interval type-2 T-S fuzzy based local modeling approach is developed to estimate the dynamics of the SDS based on the input-output data. On the basis of the local IT2 T-S fuzzy model, the local model-based predictive controller is designed to obtain local controlled outputs through minimizing the local optimization objective. Finally, the global controlled outputs are obtained by a linear programming method, where the deviations of the spatial temporal outputs from their spatial set points over the prediction horizon are considered as the optimal objective. The accuracy and efficiency of the proposed methodologies are tested in the simulation case. © 2012 American Chemical Society.


Zhang Y.,Shanghai Municipal Transportation Information Center
IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC | Year: 2011

The long term and great number of visitors to World Exposition 2010 Shanghai China (World Expo 2010) brought additional pressure to the regular urban traffic. This study provided daily visitor volume forecasts before the Expo Site opened each day. Related government departments benefited from the prediction in the management of Expo park service system and transportation scheduling. According to the natural classification of expo visitors into individuals and groups, the letter applied a hybrid methodology of fuzzy Takagi-Sugeno (T-S) models and linear least squares regression (LLSR) model to obtain the forecasts. The proposed approach showed the capacity of highly accurate prediction and remarkable robustness. And the results were timely issued through the Comprehensive Transportation Information Platform (CTIP) to the Shanghai government and Bureau of Shanghai World Expo Coordination for reference. © 2011 IEEE.


Zhang Y.,Shanghai Municipal Transportation Information Center
IEEE Signal Processing Letters | Year: 2011

Accurate and timely forecasting of traffic status is crucial to effective management of intelligent transportation systems (ITS). An interacting multiple model (IMM) predictor is proposed to forecast travel time index (TTI) data in the letter. To the best of our knowledge, it is the first time to propose the novel combined predictor. Seven baseline individual predictors are selected as combination components because of their proved effectiveness. Experimental results demonstrate that the IMM predictor can significantly outperform the other predictors and provide a large improvement in stability and robustness. This reveals that the approach is practically promising in traffic forecasting. © 2006 IEEE.

Loading Shanghai Municipal Transportation Information Center collaborators
Loading Shanghai Municipal Transportation Information Center collaborators