Secondary Accident Data Fusion for Assessing Long-Term Performance of Transportation Systems, 2007

Secondary accident statistics can be useful for studying the impact of traffic incident management strategies. An easy-to-implement methodology is presented for classifying secondary accidents using data fusion of a police accident database with intranet incident reports. A current method for classifying secondary accidents uses a static threshold that represents the spatial and temporal region of influence of the primary accident, such as two miles and one hour. An accident is considered secondary if it occurs upstream from the primary accident and is within the duration and queue of the primary accident. However, using the static threshold may result in both false positives and negatives because accident queues are constantly varying. The methodology presented in this report seeks to improve upon this existing method by making the threshold dynamic. An incident progression curve is used to mark the end of the queue throughout the entire incident. Four steps in the development of incident progression curves are described. Step one is the processing of intranet incident reports. Step two is the filling in of incomplete incident reports. Step three is the nonlinear regression of incident progression curves. Step four is the merging of individual incident progression curves into one master curve. To illustrate this methodology, 5,514 accidents from Missouri freeways were analyzed. The results show that secondary accidents identified by dynamic versus static thresholds can differ by more than 30%.

Automated incident management plan using geographic information systems technology for traffic management centers. Final report.

Texas Department of Transportation, Austin

Predicting delay reductions from freeway traffic diversion for incident management

Traffic incidents are a major source of traffic congestion on freeways. Freeway traffic diversion using pre-planned alternate routes has been used as a strategy to reduce traffic delays due to major traffic incidents. However, it is not always beneficial to divert traffic when an incident occurs. Route diversion may adversely impact traffic on the alternate routes and may not result in an overall benefit. This dissertation research attempts to apply Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques to predict the percent of delay reduction from route diversion to help determine whether traffic should be diverted under given conditions. The DYNASMART-P mesoscopic traffic simulation model was applied to generate simulated data that were used to develop the ANN and SVR models. A sample network that comes with the DYNASMART-P package was used as the base simulation network. A combination of different levels of incident duration, capacity lost, percent of drivers diverted, VMS (variable message sign) messaging duration, and network congestion was simulated to represent different incident scenarios. The resulting percent of delay reduction, average speed, and queue length from each scenario were extracted from the simulation output. The ANN and SVR models were then calibrated for percent of delay reduction as a function of all of the simulated input and output variables. The results show that both the calibrated ANN and SVR models, when applied to the same location used to generate the calibration data, were able to predict delay reduction with a relatively high accuracy in terms of mean square error (MSE) and regression correlation. It was also found that the performance of the ANN model was superior to that of the SVR model. Likewise, when the models were applied to a new location, only the ANN model could produce comparatively good delay reduction predictions under high network congestion level.

Predicting delay reductions from freeway traffic diversion for incident management

Traffic incidents are a major source of traffic congestion on freeways. Freeway traffic diversion using pre-planned alternate routes has been used as a strategy to reduce traffic delays due to major traffic incidents. However, it is not always beneficial to divert traffic when an incident occurs. Route diversion may adversely impact traffic on the alternate routes and may not result in an overall benefit. This dissertation research attempts to apply Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques to predict the percent of delay reduction from route diversion to help determine whether traffic should be diverted under given conditions. The DYNASMART-P mesoscopic traffic simulation model was applied to generate simulated data that were used to develop the ANN and SVR models. A sample network that comes with the DYNASMART-P package was used as the base simulation network. A combination of different levels of incident duration, capacity lost, percent of drivers diverted, VMS (variable message sign) messaging duration, and network congestion was simulated to represent different incident scenarios. The resulting percent of delay reduction, average speed, and queue length from each scenario were extracted from the simulation output. The ANN and SVR models were then calibrated for percent of delay reduction as a function of all of the simulated input and output variables. The results show that both the calibrated ANN and SVR models, when applied to the same location used to generate the calibration data, were able to predict delay reduction with a relatively high accuracy in terms of mean square error (MSE) and regression correlation. It was also found that the performance of the ANN model was superior to that of the SVR model. Likewise, when the models were applied to a new location, only the ANN model could produce comparatively good delay reduction predictions under high network congestion level.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Integrated Risk Management for Improving Internal Traffic Control, Work-Zone Safety, and Mobility during Major Construction, TPF-5(081), 2012

Highway construction is among the most dangerous industries in the US. Internal traffic control design, along with how construction equipment and vehicles interact with the traveling public, have a significant effect on how safe a highway construction work zone can be. An integrated approach was taken to research work-zone safety issues and mobility, including input from many personnel, ranging from roadway designers to construction laborers and equipment operators. The research team analyzed crash data from Iowa work-zone incident reports and Occupational Safety and Health Administration data for the industry in conjunction with the results of personal interviews, a targeted work-zone ingress and egress survey, and a work-zone pilot project.

A Smartphone-Based Prototype System for Incident/Work Zone Management Driven by Crowd-Sourced Data, 2015

This project develops a smartphone-based prototype system that supplements the 511 system to improve its dynamic traffic routing service to state highway users under non-recurrent congestion. This system will save considerable time to provide crucial traffic information and en-route assistance to travelers for them to avoid being trapped in traffic congestion due to accidents, work zones, hazards, or special events. It also creates a feedback loop between travelers and responsible agencies that enable the state to effectively collect, fuse, and analyze crowd-sourced data for next-gen transportation planning and management. This project can result in substantial economic savings (e.g. less traffic congestion, reduced fuel wastage and emissions) and safety benefits for the freight industry and society due to better dissemination of real-time traffic information by highway users. Such benefits will increase significantly in future with the expected increase in freight traffic on the network. The proposed system also has the flexibility to be integrated with various transportation management modules to assist state agencies to improve transportation services and daily operations.

Utilization of Incident Reporting in The Finnish Maritime Industry

Marine traffic is expected to increase rapidly in the future, both in the Baltic Sea and in the Gulf of Finland. As the number of vessels in the area increases, so does the risk of serious marine accidents. To help prevent such accidents in the future, the International Maritime Organization (IMO) has put forth the International Safety Management Code (the ISM Code), which aims to improve the safety of the vessels. The second work package of the Development of maritime safety culture (METKU) project investigates the effects of the ISM Code and potential areas of improvement in maritime safety. The first phase in the work package used a literature review to determine how maritime safety culture could be improved. Continuous improvement, management commitment and personnel empowerment and motivation were found to be essential. In the second phase, shipping companies and administrators were interviewed. It was discovered that especially incident reporting based on continuous improvement was felt to be lacking. This third phase aims to take a closer look at incident reporting and suggest improvements based on the findings. Both the IMO and national legislation encourage shipping companies in incident reporting, and on the national level a shared incident reporting system (ForeSea) is being pushed forward. The objective of this research project was to find out the IMO’s attitude towards incident reporting, to establish a theoretical framework of reference in incident reporting, and to observe how reporting is actually being employed on the seas. Existing incident reporting systems were also researched. The study was carried out using a literature review and the results previously gathered in interviews. The results of phase two were elaborated further for themes relating to incident reporting. According to the findings of this research, the theoretical background of incident reporting dates back to the early 20th century. Although some theories are widely accepted, some have also received criticism. The lack of a concise, shared terminology poses major difficulties in maritime incident reporting and in determining its efficiency. A central finding is the fact that existing incident reporting focuses mostly on information flow away from the ship, whereas the backward information flow is much less planned and monitored. In incident reporting, both nationally and internationally, stakeholders are plenty. The information produced by these parties is scattered, however, and thus not very usable. Based on this research, the centralizing of this information should be made a priority. Traditionally, the success of incident reporting has been determined statistically, from the number of reported incidents. Yet existing reporting systems have not been designed with such statistical analysis in mind, so different methodologies might yield a more comprehensive view. The previous findings of seafarers and management (including shipping companies and administration) having differing views on safety work and safety management were backed up by the results of this study. Seafarers find seamanship and storytelling important, while management wants a more systematic and broad approach on safety matters. The research project was carried out by the Centre for Maritime Studies of the University of Turku, in the Kotka unit (Maritime Logistics Research), with coordination by the Kotka Maritime Research Centre. The major financiers of the project were the European Union and the city of Kotka. The financing authority was the Regional Council of Päijät-Häme. Partners in the project were the shipping companies Finnlines Oyj, Kristina Cruises Oy, Meriaura Oy and VG-Shipping Oy, and the ports of Helsinki, Kotka and Hamina. The partners provided both funding for the project and information for the research.

Incident management program for Virginia. Final report.

Virginia Department of Transportation, Richmond

Incident response and clearance in the State of Texas: case studies of four motorist assistance patrols.

Texas Department of Transportation, Austin

Method for selecting among alternative incident detection strategies.

Texas Department of Transportation, Austin