Qing-Jie Kong

An Approach to Urban Traffic State Estimation by Fusing Multisource Information

This paper presents an information-fusion-based approach to the estimation of urban traffic states. The approach can fuse online data from underground loop detectors and global positioning system (GPS)-equipped probe vehicles to more accurately and completely obtain traffic state estimation than using either of them alone. In this approach, three parts of the algorithms are developed for fusion computing and the data processing of loop detectors and GPS probe vehicles. First, a fusion algorithm, which integrates the federated Kalman filter and evidence theory (ET), is proposed to prepare a robust, credible, and extensible fusion platform for the fusion of multisensor data. After that, a novel algorithm based on the traffic wave theory is employed to estimate the link mean speed using single-loop detectors buried at the end of links. With the GPS data, a series of technologies are combined with the geographic information systems for transportation (GIS-T) map to compute another link mean speed. These two speeds are taken as the inputs of the proposed fusion platform. Finally, tests on the accuracy, conflict resistance, robustness, and operation speed by real-world traffic data illustrate that the proposed approach can well be used in urban traffic applications on a large scale.

Efficient Traffic State Estimation for Large-Scale Urban Road Networks

This paper presents a systematic solution to efficiently estimate the traffic state of large-scale urban road networks. We first propose the new approach to construct the exact GIS-T digital map. The exact digital map can lay the solid foundation for the traffic state estimation with the data from Global Positioning System (GPS) probe vehicles. Then, we present the following two effective methods based on GPS probe vehicles for the traffic state estimation: (1) the curve-fitting-based method and (2) the vehicle-tracking-based method. Finally, we test the proposed solution with a large number of real data from GPS probe vehicles and the standard digital map of Shanghai, China. In the experiments, data from thousands of GPS-equipped taxies were taken as the probe vehicles. The estimation accuracy and operation speed of the two different methods were systematically measured and compared. In addition, the coverages of the GPS sampling points were also investigated for the large-scale urban road network in the spatial and temporal domains. For the accuracy experiment, the ground truth was obtained by repeating the videos that were recorded on 24 road sections in downtown Shanghai. The experimental results illustrate that the proposed methods are effective and efficient in monitoring the traffic state of large-scale urban road networks.

A GPS/GIS Integrated System for Urban Traffic Flow Analysis

In this paper, a GPS/GIS integrated system for urban traffic flow analysis is proposed. Urban GIS-T data are used to construct the GIS map of urban area when the system begins its work. Afterwards, real-time GPS data of probe vehicles are periodically collected to implement the location amendment. And then, location-amended GPS data are dynamically fitted with the adaptive traffic flow model. By using fitted traffic flow models, states of traffic flow are ultimately estimated along rolling time periods. Compared with conventional works, the proposed system successfully preserves the continuity of vehicle travels without additional data sources. Experiments based on GIS-T data of Shanghai and GPS signals of taxis in Shanghai indicate that the new system is both efficient and robust.

A fusion-based system for road-network traffic state surveillance: a case study of Shanghai

In this paper, we will introduce a fusion-based system composed of real-time traffic state surveillance. This system can realize the real-time traffic state estimation with over 10,000 bidirectional road sections, all the links of the Shanghai urban road network. The system consists of three modules: SCATS data processing (MS), GPS data processing (MG), and Fusion Module (FM). In MS, traffic information collected by SCATS is converted into a kind of link-based spatio-temporal mean-speeds. Similarly, the taxisinformation is also calculated for the spatio-temporal mean-speeds by means of a GIS-T map in MG. The spatio- temporal mean-speed here is defined by the mean-speed of all the vehicles running on a link during a period of time. Finally, the mean-speeds from these two sources are fused using an improved evidential fusion model.

Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction

Current research on traffic flow prediction mainly concentrates on generating accurate prediction results based on intelligent or combined algorithms but ignores the interpretability of the prediction model. In practice, however, the interpretability of the model is equally important for traffic managers to realize which road segment in the road network will affect the future traffic state of the target segment in a specific time interval and when such an influence is expected to happen. In this paper, an interpretable and adaptable spatiotemporal Bayesian multivariate adaptive-regression splines (ST-BMARS) model is developed to predict short-term freeway traffic flow accurately. The parameters in the model are estimated in the way of Bayesian inference, and the optimal models are obtained using a Markov chain Monte Carlo (MCMC) simulation. In order to investigate the spatial relationship of the freeway traffic flow, all of the road segments on the freeway are taken into account for the traffic prediction of the target road segment. In our experiments, actual traffic data collected from a series of observation stations along freeway Interstate 205 in Portland, OR, USA, are used to evaluate the performance of the model. Experimental results indicate that the proposed interpretable ST-BMARS model is robust and can generate superior prediction accuracy in contrast with the temporal MARS model, the parametric model autoregressive integrated moving averaging (ARIMA), the state-of-the-art seasonal ARIMA model, and the kernel method support vector regression.

UTN-Model-Based Traffic Flow Prediction for Parallel-Transportation Management Systems

Aiming to comply with the requirement of parallel-transportation management systems (PtMS), this paper presents a short-term traffic flow prediction method for signal-controlled urban traffic networks (UTNs) based on the macroscopic UTN model. In contrast with other time-series-based or spatio-temporal correlation methods, the proposed method focuses more on using the substantial mechanism of traffic transmission in road networks and the topology model of the entire UTN. Furthermore, this approach employs a speed-density model based on the fundamental diagram (FD) to obtain more accurate travel times in links. In the comparison experiment, the microscopic traffic simulation software CORSIM is adopted to simulate the real urban traffic. The experiment results fully verify the outstanding performances of the proposed prediction method.

Sample size analysis of GPS probe vehicles for urban traffic state estimation

Nowadays, probe vehicles equipped with Global Position System (GPS) are an effective way of collecting real-time traffic information. This paper first briefly introduces the Curve-Fitting Estimation Model (CFEM), which is one of the typical methods using GPS data to estimate the traffic flow state. After that, it is detailedly analyzed how many probe vehicles the CFEM requires in order to ensure enough estimated accuracy. Furthermore, a sample size algorithm is developed to calculate the minimum sample size of the CFEM. In the algorithm, the road type, the length of road section, and sample frequency are taken into account. Finally, the proposed algorithm of sample size analysis are tested by the experiments using the data collected from the road network of the whole center region of Shanghai.

Short-term traffic volume prediction using classification and regression trees

Accurate short-term traffic flow prediction plays a fundamental role in intelligent transportation systems (ITS), e.g. advanced traffic management systems (ATMS). To generate accurate short-term traffic volume, nonparametric models have gained credit from quantities of researchers. On the basis of the common thought that future traffic states can be predicted according to the similar states in the historical traffic data, this paper presents a novel nonparametric-model-based method to predict the short-term traffic volume. The applied nonparametric model is the classification and regression trees (CART) model. In the application, the CART model first classifies the historical traffic states into plentiful categories. Afterwards, the linear regression model is built corresponding to each traffic state pattern. Finally, the model predicts the short-term traffic state through clustering the current state vector into the most congenial historical pattern and regression model. In the experiments, the proposed method is tested by using the 15 minutes average traffic volumes on freeways and is compared with the classic nonparametric methods k-nearest neighbors (k-NN) model, and the parametric method Kalman filter model. The results indicate that the CART-based prediction method outperforms the k-NN and Kalman filter methods in both the mean absolute percentage error and the mean absolute scaled error.

Urban traffic flow prediction based on road network model

This paper addresses an issue of short-term traffic flow prediction in urban traffic networks with traffic signals in intersections. An effective spatial prediction approach is proposed based on a macroscopic urban traffic network model. In contrast with other time series based or spatio-temporal correlation methods, this research focuses on the substantial mechanism of vehicles transmission on road segments and the spatial model of the entire urban network. Furthermore, this approach employs a simple speed-density model based on the macroscopic fundamental diagram (MFD) to obtain a more accurate vehicle travel time on the link. Finally, the microscopic traffic simulation software, CORSIM, is adopted to simulate the real urban traffic, and the proposed method is used to predict the traffic flows generated by CORSIM. The simulation results illustrate that our approach performs effective prediction timely in the rush hours, as well as the suddenly changed traffic states.

An Improved Evidential Fusion Approach for Real-time Urban Link Speed Estimation

On the basis of previous researches, an improved evidential fusion approach is presented to integrate heterogeneous multi-sensor data in Urban Advanced Traveler Information Systems. The method inherits the advantages of the previous model in terms of the real-time processing feature; meanwhile, its performance is improved by adding a mechanism to evaluate the dynamic reliability of sensors. In this paper, the whole evidence reliability algorithms, which contain both the static one and the dynamic one, are provided primarily. After that, the frame and computational procedures of the new approach are given. Finally, a simulation test and a real-world data experiment are discussed to explain the advantage of the proposed method in comparison with the previous model. The real-world data of loop detectors and GPS probe vehicles were collected from an urban arterial road section in Shanghai.