Haizhong Wang

A novel work zone short-term vehicle-type specific traffic speed prediction model through the hybrid EMD–ARIMA framework

This paper presents a hybrid short-term traffic speed prediction framework through empirical mode decomposition (EMD) and autoregressive integrated moving average (ARIMA). The goals of this paper are to investigate (1) does the hybrid model provide better short-term traffic conditions (i.e. traffic speeds) than the traditional models? (2) how the performance of the hybrid model varies for varying scenarios such as mixed traffic flow and vehicle-type specific traffic prediction in a work zone, on-ramp, and off-ramp; and (3) why hybrid models provide better prediction than other single-staged models. Using empirical data from a work zone on interstate I91 in Springfield, MA and the on/off-ramp data from the Georgia State Route 400, the proposed hybrid EMD–ARIMA modelling framework is tested in the four distinct scenarios aforementioned. The prediction results of the hybrid EMD–ARIMA model are evaluated against the experimental data and also compared with the results from the traditional ARIMA, the Holt–Winters, the artificial neural network models, and a naive model. The evaluation results showed that the hybrid EMD–ARIMA model outperforms the traditional forecasting models in different scenarios.

Empirical Mode Decomposition–Autoregressive Integrated Moving Average: Hybrid Short-Term Traffic Speed Prediction Model

Short-term freeway traffic speed prediction is essential to improving mobility and roadway safety. It has been a challenging and unresolved issue. Traffic speed prediction can be applied to enhance the intelligent freeway traffic management and control for applications such as operational and regulation planning. For example, with more reliable traffic speed prediction, the advanced traveler information system can provide travelers with predictive travel time information and optimal routing, which allows them to arrange their schedules accordingly. Moreover, traffic managers can use the predicted information to deploy various traffic management strategies to increase system efficiency. In this paper, a hybrid empirical mode decomposition (EMD) and autoregressive integrated moving average (ARIMA) (or EMD-ARIMA) approach was developed to predict the short-term traffic speed on freeways. In general, there were three stages in the hybrid EMD-ARIMA forecasting framework. The first was the EMD stage, which decomposed the freeway traffic speed time series data into a number of intrinsic mode function (IMF) components and a residue. The second stage was to find the appropriate ARIMA model for each IMF and residue and then make predictions on the basis of the appropriate ARIMA model. The third stage was to combine the prediction results of each IMF and residue to make the predictions. The experimental results indicated that the proposed hybrid EMD-ARIMA framework was capable of predicting short-term freeway traffic speed with high accuracy.

Observations on the fundamental diagram and their interpretation from the human factors perspective

ABSTRACT Some observations are made on the fundamental diagram of freeway traffic,among which are three influence regions, three types of transition around capacity, and a capacity drop phenomenon. This research aspires to interpret these observations from the human factors perspective in traffic flow theory. A combination of these factors shapes the above-mentioned influence regions, transition around capacity, and capacity drop. Of critical importance in determining the transition around capacity and capacity drop is drivers aggressiveness, a factor that has long been overlooked in the past. This paper provides a detailed account of where it comes from and how it influences the fundamental diagram.

Preparing Oregon for Connected Vehicle Deployment: Application Prioritization Process

To build on a project recently completed for the Oregon Department of Transportation (DOT), processes and tools were developed to prioritize the implementation of connected vehicle (CV) applications. Internal mechanisms for addressing CV development and deployment at the Oregon DOT were assessed; the technical maturity of each potential CV application was scanned, reviewed, and assessed; preliminary goals were developed; prospective CV applications were linked; and applications that fit with the potential role of the Oregon DOT in advancing these initiatives were refined, prioritized, and ranked. A shared vision and business plan that prioritizes CV applications for Oregon is recommended. An internal effort aimed at producing a small set of priority CV applications for further development is described. This effort culminated in a CV application prioritization workshop that included a priority mapping exercise, discussion of the CV concept, and an initial mapping of goals and applications. The workshop identified seven near-term priority CV applications for the Oregon DOT; 12 applications that the Oregon DOT will monitor (and possibly collaborate on with others in the future); and eight applications that the Oregon DOT will monitor but that will be led by others. The Oregon DOT has used the results of this effort as a springboard for hiring new staff dedicated to CV policy, forming a CV steering team, and launching a CV business plan. The process and tools can be used by other states and transportation agencies in their CV application prioritization processes.

Development of a Crash Risk-Scoring Tool for Pedestrian and Bicycle Projects in Oregon

Methods for identifying and prioritizing high-crash locations for safety improvements are generally crash-based. There are fewer reported crashes involving non-motorized users and, in most states, reported crashes must involve a motor vehicle. This means that minor, non-injury events are not reported and those crashes that are reported tend to be more severe. Selecting projects based only on crash performance is sometimes limiting for these crash types and predicting where these crashes will occur next is also a challenging task. An alternative to crash-based selection is to develop risk-based criteria and methods. This paper presents the results of a research effort to develop a risk-scoring method with weights derived from data for use in project screening and selection in Oregon. To develop the risk model, data were collected from 188 segments and 184 intersections randomly selected on both state and non-state roadways. Geometric, land use, volume, and crash data were collected from Google Earth, EPA’s Smart Location Database, and the Oregon Department of Transportation crash database from 2009 to 2013. The sample included 213 bicycle and pedestrian crashes on the segments and 238 at intersections. Logistic regression models were developed and the outputs used to create pedestrian and bicycle risk-scoring tools for segments and intersections. The risk-scoring tool was applied to safety projects identified in the 2015 All Roads Transportation Safety (ARTS) project lists from Oregon. The risk scores for the case study applications aligned reasonably well with the project’s benefits-costs estimates.

A stochastic analysis of highway capacity: Empirical evidence and implications

ABSTRACT This paper presents a stochastic characterization of highway capacity and explores its implications on ramp metering control at the corridor level. The stochastic variation of highway capacity is captured through a Space–Time Autoregressive Integrated Moving Average (STARIMA) model. It is identified following a Seasonal STARIMA model (0, 0, 23) × (0, 1, 0)2, which indicates that the capacities of adjacent locations are spatially–temporally correlated. Hourly capacity patterns further verify the stochastic nature of highway capacity. The goal of this paper is to study (1) how to take advantage of the extra information, such as capacity variation, and (2) what benefits can be gained from stochastic capacity modeling. The implication of stochastic capacity is investigated through a ramp metering case study. A mean–standard deviation formulation of capacity is proposed to achieve the trade-off between traffic operation efficiency and robustness. Following that, a modified stochastic capacity-constraint ZONE ramp metering scheme embedded cell transmission model algorithm is introduced. The numerical experiment suggests that considering capacity variation information would alleviate the spillback effect and improve throughput. Monte Carlo simulation further supports this argument. This study helps verify and characterize the stochastic nature of capacity, validates the benefits of using capacity variation information, and thus enhances the necessity of implementing stochastic capacity in traffic operation.

Importance of Recognizing Locational Differences in Assessing the Impact of a Road User Charge: Oregon Case Study

Oregon Senate Bill 810 created a program that allows drivers to pay a flat-mileage road user charge (RUC) of 1.5 cents per mile rather than the 30 cents per gallon state fuel tax. Major concerns about the adoption of this RUC are that it could increase costs for rural households relative to urban households and that the costs would fall disproportionately on lower-income groups. Further, it has been suggested that significant differences in the impact of the RUC could arise from locational distinctions beyond the urban–rural split alone. Earlier studies analyzed the regional impacts of an RUC only at the statewide level or only with the use of a broad urban–rural distinction. The newly available Oregon Households Activity Survey (OHAS) data provide detailed household location information, which permits impacts to be assessed with regional and geographic definitions relevant to policy makers in Oregon. Results with the use of OHAS data showed that, on average, statewide households would pay 5 cents more daily under the RUC than they did under the fuel tax because the 1.5 cents per mile RUC actually will produce more gross revenue than the fuel tax. However, the price increase in rural regions will be less than the statewide average, whereas more urban regions will pay slightly more than the statewide average. Further, the distributional impact of the flat 1.5 cents RUC on all households in the OHAS data set differed, depending on the region of the state examined.

Assessing State Department of Transportation Readiness for Connected Vehicle–Cooperative Systems Deployment: Oregon Case Study

As connected vehicle (CV) research moves into deployment, metropolitan planning organizations; state, local, and transit agencies; and the private sector will start experiencing the effects of vehicles, aftermarket devices, mobile devices, and infrastructure with dedicated short-range wireless communications and other wireless connectivity at their cores. Like other states and regions, the Oregon Department of Transportation (DOT) could benefit from the preliminary scoping, evaluation, and assessment of the impact of CVs and infrastructure and a wide range of potential cooperative system applications. With this in mind, the Oregon DOT is determining whether to pursue the next phases of federal funding for CV applications. The Oregon DOT also wants to make an informed choice about taking a national leadership role in the CV arena and to assess opportunities to join projects with other partners. This paper describes the empirical results of a survey that, to assist the Oregon DOT in its assessment, was distributed to agency staff to gauge the perception of CV and automated vehicle (AV) technology. Most respondents had heard of this technology and were in favor of its application. However, many respondents had concerns about cybersecurity and the catastrophic consequences of system failure, and many respondents voiced concerns about the Oregon DOT’s preparedness for CVs or AVs. The Oregon DOT and other agencies can use these findings to help prepare for a better future with CVs and AVs.

Integrated Traffic Flow Models and Analysis for Automated Vehicles

With the emergence of connected and automated vehicle (CAV) technologies, research on traffic flow modeling and analysis will play a very important role in improving our understanding of the fundamental characteristics of traffic flow. The frontier of studies on CAV systems have examined the impacts of CAVs on freeway bottleneck capacity, and macroscopic traffic flow, CAV applications on optimization of individual vehicle trajectories, potentials of CAV in traffic signal control, and applications of CAV in network routing. For current and future research initiatives, the greatest challenge lies in the potential inconsistencies between user, operator, and manufacturer goals. Specific research needs were identified on data collection and analysis on CAV behavior and applications. This paper summarizes the presentations and discussions during the Automated Vehicles Symposium 2015 (AVS15) held in Ypsilanti, Michigan, on July 20–23, 2015.