Proactive Traffic Management Research Articles

Megaregion Network Simulation for Evacuation Analysis

This paper describes a project to develop a microlevel traffic simulation for a megaregion. To accomplish that goal, a mass evacuation event was modeled with a traffic demand generation process that created a spatial and temporal distribution of departure times, origins, and destinations based on past hurricane scenarios. A megaregion-scale simulation was required to assess this event, because only at this level could traffic from multiple cities, over several days, with route assignments in multiple and overlapping directions be analyzed. One finding of the research was that it was possible to scale up and adapt existing models to reflect a simultaneous multicity evacuation covering a megaregion. The movements generated by the demand and operational models were logical and meaningful, and they were able to capture the key elements of the system, including the traffic progression over vast spaces and long time durations. They were also adequate to demonstrate the benefits of proactive traffic management strategies and the effect of increased and decreased advance warning times. The project also revealed numerous limitations of the existing modeling and computational processing capabilities. The knowledge and results gained from this research can be adapted and can be transferable for the evaluation of other locations with different road networks, populations, transportation resources, and hazard threats. Models such as this can also be modified to represent future anticipated growth and development in other large regions and can be used to evaluate the performance, varying conditions, and interrelationships between behavioral response and regional transportation management strategies.

Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions

Most literature on short-term traffic flow forecasting focused mainly on normal, or non-incident, conditions and, hence, limited their applicability when traffic flow forecasting is most needed, i.e., incident and atypical conditions. Accurate prediction of short-term traffic flow under atypical conditions, such as vehicular crashes, inclement weather, work zone, and holidays, is crucial to effective and proactive traffic management systems in the context of intelligent transportation systems (ITS) and, more specifically, dynamic traffic assignment (DTA). To this end, this paper presents an application of a supervised statistical learning technique called Online Support Vector machine for Regression, or OL-SVR, for the prediction of short-term freeway traffic flow under both typical and atypical conditions. The OL-SVR model is compared with three well-known prediction models including Gaussian maximum likelihood (GML), Holt exponential smoothing, and artificial neural net models. The resultant performance comparisons suggest that GML, which relies heavily on the recurring characteristics of day-to-day traffic, performs slightly better than other models under typical traffic conditions, as demonstrated by previous studies. Yet OL-SVR is the best performer under non-recurring atypical traffic conditions. It appears that for deployed ITS systems that gear toward timely response to real-world atypical and incident situations, OL-SVR may be a better tool than GML.

ATMS Implementation System for Identifying Traffic Conditions Leading to Potential Crashes

Predicting a crash occurrence is the key to traffic safety. Real-time identification of freeway segments with high crash potential is addressed in this paper. For this study, historical crashes and corresponding traffic-surveillance data from loop detectors were gathered from a 36-mi corridor of Interstate 4 for 4 years. Following an exploratory analysis, two types of logistic-regression models (i.e., simple and multivariate) were developed. It was observed that, although the simple models have the advantage of being tolerant in their data requirements, their classification accuracy was inferior to that of the final multivariate model. Hence, the simple models were used to deduce time-space patterns of variation in crash risk while the multivariate model was chosen for final classification of traffic patterns. As a suggested application for the simple models, their output may be used for the preliminary assessment of the crash risk. If there is an indication of high crash risk, then the multivariate model may be employed to explicitly classify the data patterns as leading or not leading to a crash occurrence. A demonstration of this two-stage real-time application strategy, based on simple and multivariate models, is provided in the paper. The output from these model-processing real-time loop-detector data may be utilized by traffic-management authorities for developing proactive traffic-management strategies

A Freeway Safety Strategy for Advanced Proactive Traffic Management

Reactive traffic management strategies such as incident detection are becoming less relevant with the advancement of mobile phone usage. Freeway management in the 21st century needs to shift focus toward proactive strategies that include anticipating incidents such as crashes. A simple approach to identify freeway locations with high probability of crashes through real-time traffic surveillance data is presented here. The crash and loop detector data for the study was collected from 36-mile corridor of Interstate-4 in Orlando, Florida. The analysis is based on simple (one covariate) logistic regression models developed under a matched study design. Individual traffic parameters obtained one at a time from series of loop detectors have been examined as potential covariates to these models. Hazard ratio for each individual covariate is the output from the models. Based on the hazard ratio and its statistical significance it was found that the log of coefficient of temporal variation in speed, standard deviation of volume, and average occupancy expressed as percentage are the parameters that are most critically associated with potential occurrence of multivehicle crashes. The univariate logistic regression models were validated based on their classification performance on an independent set of crash data. Using the relative location of loop detectors measuring these parameters with respect to the crash location contour maps depicting spatial-temporal distribution of crash risk was generated. Using the model outputs, a generic strategy to assess crash risk in real-time is also proposed. With this strategy one can identify the segment of freeway having high potential for crash occurrence within next 15–20 minutes. The crash mitigation and law enforcement set up can be prepared for dispatch to such locations based on the real-time assessment of crash potential.

Split Models for Predicting Multivehicle Crashes during High-Speed and Low-Speed Operating Conditions on Freeways

The future of traffic management and highway safety lies in proactive traffic management systems. Crash prediction models that use real-time traffic flow variables measured through a series of loop detectors are the most important component of such systems. A previous crash prediction model was developed with the matched case–control logistic regression technique. Although the model achieved reasonable classification accuracy, it remained open to improvement because of the limited study area, sample size, and transferability issues. Therefore, the previous work had been extended. Multivehicle freeway crashes under high- and low-speed traffic conditions were found to differ in severity and in their mechanism. The distribution of 5-min average speeds obtained immediately before the crash from the loop detector station closest to the crash shows two approximate mound-shaped distributions. This distribution is used as the basis to separate the models for crashes occurring under the two speed conditions. The results show that, as expected, variables that entered in the final models (for crashes under high and low speeds) were not the same. However, they were found to be consistent with the probable mechanisms of crashes under the respective speed conditions. A possible implementation of the separate models with the use of the odds ratios and with the balancing of the threshold between achieving high classification of crash potential and the false alarm situation is presented.

Split Models for Predicting Multivehicle Crashes During High-Speed and Low-Speed Operating Conditions on Freeways

The future of traffic management and highway safety lies in proactive traffic management systems. Crash prediction models that use real-time traffic flow variables measured through a series of loop detectors are the most important component of such systems. A previous crash prediction model was developed with the matched case-control logistic regression technique. Although the model achieved reasonable classification accuracy, it remained open to improvement because of the limited study area, sample size, and transferability issues. Therefore, the previous work had been extended. Multivehicle freeway crashes under high- and low-speed traffic conditions were found to differ in severity and in their mechanism. The distribution of 5-min average speeds obtained immediately before the crash from the loop detector station closest to the crash shows two approximate mound-shaped distributions. This distribution is used as the basis to separate the models for crashes occurring under the two speed conditions. The results show that, as expected, variables that entered in the final models (for crashes under high and low speeds) were not the same. However, they were found to be consistent with the probable mechanisms of crashes under the respective speed conditions. A possible implementation of the separate models with the use of the odds ratios and with the balancing of the threshold between achieving high classification of crash potential and the false alarm situation is presented.

Traffic Estimation for Proactive Freeway Traffic Control

Many operating agencies are developing computerized traffic management systems that support traffic operations as part of intelligent transportation system (ITS) user service improvements. To facilitate the prediction, diagnosis, and control decisions made with uncertain information, several numerical analysis methods are available for predictive traffic control. However, these methods cannot predict short-term traffic demand accurately. A neural network approach was proposed to improve short-term traffic demand prediction for the development of advanced traffic control strategies. A promising neural network approach to improving demand prediction and traffic data modeling to support proactive traffic control was examined. Specifically, the use of time-series detector data from a real-world freeway management system that were processed through neural network models was analyzed and the results were compared with real-world observations. In all cases, the proposed neural network approach can successfully predict traffic demand patterns. The proposed study approach of combining both neural networks and error correction was found to be promising for traffic prediction. Once the neural nets are successfully trained, the system can quickly pick up traffic demand trends for proactive traffic demand management. The error correction algorithm can further smooth out errors that may be caused by sharp neural net prediction.

The impacts of road traffic management on urban air quality

The effects of road traffic emissions on urban air quality are investigated, using long-term nitrogen dioxide (NO 2) data. The effectiveness of the several traffic management measures that have been made in Dundee city centre, UK, within the last 5 years in relation to urban air quality is discussed. The information assessed during this study indicates that the annual mean NO 2 levels at all the study sites are, at present, below the current EC and WHO (long-term) air quality standards for NO 2 concentration in the ambient air. Traffic restrictions appear to be effective in protecting urban air quality. The annual mean NO 2 concentration at two of the study sites is currently close to 40 μg/m 3, a value published in the Air Quality Regulations 1997 for the air quality objective to be achieved by the year 2005. Proactive traffic management mitigation measures are proposed for these sites and a methodology for the consideration of traffic management alternatives, based upon traffic flow modal split, is described. Some measures proposed are based upon a survey of vehicle occupancy rates, carried out at the busiest of the four study sites. The methodology and assessment procedures presented should be invaluable to assessors of traffic management and local air quality management in a small city, both at the planning and at the auditing stage.