Zhanfeng Jia

Bio: Zhanfeng Jia is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Shortest path problem & Traffic congestion. The author has an hindex of 7, co-authored 8 publications receiving 588 citations.

Freeway performance measurement system: mining loop detector data

Abstract: Performance Measurement System (PeMS) is a freeway performance measurement system for all of California. It processes 2 GB/day of 30-s loop detector data in real time to produce useful information. At any time managers can have a uniform, comprehensive assessment of freeway performance. Traffic engineers can base their operational decisions on knowledge of the current status of the freeway network. Planners can determine whether congestion bottlenecks can be alleviated by improving operations or by minor capital improvements. Travelers can obtain the current shortest route and travel time estimates. Researchers can validate their theory and calibrate simulation models. PeMS, which has been in stable operation for 18 months, is a low-cost system. It uses the California Department of Transportation (Caltrans) network for data acquisition and is easy to deploy and maintain. It takes under 6 weeks to bring a Caltrans district online, and functionality can be added incrementally. PeMS applications are accessed...

The PeMS algorithms for accurate, real-time estimates of g-factors and speeds from single-loop detectors

Abstract: Presents the PeMS algorithms for the accurate, adaptive, real-time estimation of the g-factor and vehicle speeds from single-loop detector data. The estimates are validated by comparison with independent, direct measurements of the g-factor and vehicle speeds from 20 double-loop detectors on I-80 over a three-month period. The algorithm is used to process data from all freeways in Caltrans District 12 (Orange County, CA) over a 20-month period beginning January 1998. Analysis of those data shows that the g-factors for different loops in the district differ by as much as 100 percent, and the g-factor for the same loop can vary up to 50 percent over a 24-hour period. Many transportation districts now post real-time speed and travel time estimates on the World Wide Web. Those estimates often are derived from single-loop detector data assuming a common g-factor for all detectors in the district. This study suggests that those estimates can be in error by 50 percent, and so they are of little value to travelers. The use of the PeMS algorithm will reduce those errors.

Causes and cures of highway congestion

Abstract: People believe congestion occurs because demand exceeds capacity, so they support initiatives to build additional highway capacity or curtail highway travel demand Politicians work to bring highway construction projects into their districts; environmentalists support proposals to make transit more attractive or automobile use more costly This article argues that the facts do not support the belief that congestion occurs because demand exceeds capacity

Congestion, excess demand, and effective capacity in California freeways

Abstract: The paper makes four assertions, supported by an extensive empirical study of freeways in Los Angeles and Orange County. First, maximum throughput occurs at the free flow speed of 60 mph, and not between 35 and 45 mph, as is often assumed. So congestion must be measured as the additional vehicle-hours of delay traveling below 60 mph. Second, the maximum throughput over a link—its effective capacity—depends on how a link is connected to other links and the pattern of traffic, as well as its physical characteristics. A challenge to traffic theory is to determine the maximum throughput of a link, given the network topology and traffic pattern.

Heuristic Methods for Delay-Constrained Least-Cost Routing Problem Using -Shortest-Path Algorithms

Abstract: The QoS routing problem is abstracted as a Delay-Constrained Least-Cost (DCLC) routing problem, which is -complete. Many algorithms have been pro- posed to solve this problem in a practically efficient way. None of them achieves the optimum. This paper presents two new methods based on -Shortest-Path ( SP) algo- rithms. These heuristic methods-one centralized, the other distributed—are proved to be polynomial. Numerical ex- periments show their unique feature: the proposed algo- rithms almost always find the optimal paths.

Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting

Abstract: Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem on graphs and build the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Experiments show that our model STGCN effectively captures comprehensive spatio-temporal correlations through modeling multi-scale traffic networks and consistently outperforms state-of-the-art baselines on various real-world traffic datasets.

Review of road traffic control strategies

Abstract: Traffic congestion in urban road and freeway networks leads to a strong degradation of the network infrastructure and accordingly reduced throughput, which can be countered via suitable control measures and strategies. After illustrating the main reasons for infrastructure deterioration due to traffic congestion, a comprehensive overview of proposed and implemented control strategies is provided for three areas: urban road networks, freeway networks, and route guidance. Selected application results, obtained from either simulation studies or field implementations, are briefly outlined to illustrate the impact of various control actions and strategies. The paper concludes with a brief discussion of future needs in this important technical area.

Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting

Abstract: Forecasting the traffic flows is a critical issue for researchers and practitioners in the field of transportation. However, it is very challenging since the traffic flows usually show high nonlinearities and complex patterns. Most existing traffic flow prediction methods, lacking abilities of modeling the dynamic spatial-temporal correlations of traffic data, thus cannot yield satisfactory prediction results. In this paper, we propose a novel attention based spatial-temporal graph convolutional network (ASTGCN) model to solve traffic flow forecasting problem. ASTGCN mainly consists of three independent components to respectively model three temporal properties of traffic flows, i.e., recent, daily-periodic and weekly-periodic dependencies. More specifically, each component contains two major parts: 1) the spatial-temporal attention mechanism to effectively capture the dynamic spatialtemporal correlations in traffic data; 2) the spatial-temporal convolution which simultaneously employs graph convolutions to capture the spatial patterns and common standard convolutions to describe the temporal features. The output of the three components are weighted fused to generate the final prediction results. Experiments on two real-world datasets from the Caltrans Performance Measurement System (PeMS) demonstrate that the proposed ASTGCN model outperforms the state-of-the-art baselines.

Evaluation of Traffic Data Obtained via GPS-Enabled Mobile Phones: the Mobile Century Field Experiment

Abstract: The growing need of the driving public for accurate traffic information has spurred the deployment of large scale dedicated monitoring infrastructure systems, which mainly consist in the use of inductive loop detectors and video cameras. On-board electronic devices have been proposed as an alternative traffic sensing infrastructure, as they usually provide a cost-effective way to collect traffic data, leveraging existing communication infrastructure such as the cellular phone network. A traffic monitoring system based on GPS-enabled smartphones exploits the extensive coverage provided by the cellular network, the high accuracy in position and velocity measurements provided by GPS devices, and the existing infrastructure of the communication network. This article presents a field experiment nicknamed Mobile Century, which was conceived as a proof of concept of such a system. Mobile Century included 100 vehicles carrying a GPS-enabled Nokia N95 phone driving loops on a 10-mile stretch of I-880 near Union City, California, for 8 hours. Data were collected using virtual trip lines, which are geographical markers stored in the handset that probabilistically trigger position and speed updates when the handset crosses them. The proposed prototype system provided sufficient data for traffic monitoring purposes while managing the privacy of participants. The data obtained in the experiment were processed in real-time and successfully broadcast on the internet, demonstrating the feasibility of the proposed system for real-time traffic monitoring. Results suggest that a 2-3% penetration of cell phones in the driver population is enough to provide accurate measurements of the velocity of the traffic flow.

Real-time freeway traffic state estimation based on extended Kalman filter: a general approach

Abstract: A general approach to the real-time estimation of the complete traffic state in freeway stretches is developed based on the extended Kalman filter. First, a general stochastic macroscopic traffic flow model of freeway stretches is presented, while some simple formulae are proposed to model real-time traffic measurements. Second, the macroscopic traffic flow model along with the measurement model is organized in a compact state-space form, based on which a traffic state estimator is designed by use of the extended-Kalman-filtering method. While constructing the traffic state estimator, special attention is paid to the handling of the boundary conditions and unknown parameters of the macroscopic traffic flow model. A number of simulations are conducted to test the designed traffic state estimator under various traffic situations in a freeway stretch with on/off-ramps and a long inter-detector distance. Some key issues are carefully investigated, including tracking capability of the traffic state estimator, comparison of various estimation schemes, evaluation of different detector configurations, significance of the on-line model parameter estimation, sensitivity of the traffic state estimator to the initial values of the estimated model parameters and to the related standard deviation values, and dynamic tracking of time-varying model parameters. The achieved simulation results are very promising for the subsequent development and testing work that is briefly outlined.