Woon Kim

Development of a Hybrid Prediction Model for Freeway Incident Duration: A Case Study in Maryland

This paper presents a methodology for estimating the incident duration and identifying its critical contributing factors in the state of Maryland. The incident database from the Maryland State Highway (MDSHA) and Police Accident Report database between years 2003 and 2005 were used for model development. This study employed a hybrid model to develop the primary estimation system, consisting of a Rule-Based Tree Model (RBTM), Multinomial Logit Model (MNL), and Naïve Bayesian Classifier (NBC). Through the extensive data analysis and model estimation, we have identified some critical relationships between the set of key factors and the resulting incident duration. The proposed model along with research findings can play a vital role for traffic agencies to establish an advanced traveler information system, and to provide the incident-induced delay to both pre-trip and the en-route drivers.

Empirical Analysis and Modeling of Freeway Incident Duration

This paper presents a methodology for developing a model to identify the variables influencing incident duration to estimate and predict incident duration in the state of Maryland. The incident information from years 2003 to 2005 from the Maryland State Highway (MDSHA) database was used for model development, and year 2006 for model validation. Classification Trees (CT) were employed for a preliminary analysis to understand the influence of the variables associated with an incident. Based on the findings from CT, this study constructed the Rule-Based Tree Model (RBTM) to develop the primary prediction model. The overall confidence for the estimated model was over 80% with several remarkable findings regarding the association between the identified factors and incident duration. Although the estimated results from RBTM were quite acceptable, in cases where RBTM did not provide incident duration within a desirable short range, a discrete choice model was developed as a supplemental model. It is deduced that supplemental models along with better quality database are required to improve the prediction accuracy of the duration of a detected incident.

Decision Model for Justifying the Benefits of Detour Operation under Non-Recurrent Congestion

This paper presents a detour decision model for freeway non-recurrent congestion management, based on the results of extensive simulation experiments and operational guidelines for highway agencies. The proposed model offers a reliable and effective tool for responsible traffic operators to make consistent detour decisions in response to a detected incident. Numerical results clearly indicate that a timely and well justified detour operation can yield substantial benefits to both the driving populations and the entire community.

Design of Emergency Response System to Minimize Incident Impacts: Case Study for Maryland District 7 Network

Analysis of incident data from the Maryland Highway Administration leads to the conclusion that efficient operations of an incident management team can contribute to reduction in not only response time but also clearance time. This paper presents an integer programming model for optimizing the deployment locations of emergency response units. Unlike models in most existing studies, the proposed model is designed to assign the available units to minimize the total delay caused by incidents rather than to minimize the units’ average response times. By giving more weight to locations likely to have more severe incidents and accounting for the variance in incident duration, the proposed model with incident data from Maryland can outperform both the popular P-median model and state-of-the-practice deployment strategies. Extensive sensitivity analyses with respect to various traffic volumes and incident frequencies have also confirmed the superior performance of the proposed model in minimizing the total delay caused by incidents.

Design and Benefit–Cost Analysis of Deploying Freeway Incident Response Units: Case Study for Capital Beltway in Maryland

This study presents an optimization strategy for highway agencies to distribute incident response units effectively along freeway segments plagued by frequent incidents. The proposed method, based on the p-median model, convincingly outperforms three state-of-the-practice deployment strategies for performance evaluation with the incident data from 2006 to 2010 on I-495 (Capital Beltway) in the state of Maryland. A comprehensive benefit–cost analysis of deploying an incident response system with different response units is also presented. Findings from this research could serve as the basis for traffic managers to design and to deploy a benefit–cost incident management system.

Advanced Traffic Management System: Integrated Multicriterion System for Assessing Detour Decisions During Nonrecurrent Freeway Congestion

Implementing a well-designed detour plan to minimize the impact of nonrecurrent congestion has long been adopted by responsible highway agencies, mainly on the basis of estimated incident duration or number of blocked lanes. Because an effective detour operation necessitates rigorous plans in advance and a vast amount of resources during implementation, a convincing justification for taking such actions becomes increasingly essential in practice, especially in view of diminishing resources for traffic management. This paper presents a multicriterion decision support system to assist traffic managers in effectively making such decisions in real-time operations by taking into account (a) associated costs and benefits from various perspectives, including the operational cost, and (b) the resultant benefits from reduced delay, fuel consumption, and emissions, as well as (c) the likelihood of incurring secondary incidents. The impact of potential driver compliance in response to the detour strategy and of the local traffic condition on the effectiveness of detour operations can be included in the decision process. The proposed system, with its embedded analytical hierarchy process structure and optimal corridor detour model, allows potential users to rank by priority all essential decision criteria (on the basis of either resource constraints or the demand of the general public) and to make the critical decision that can best manage any nonrecurrent congestion and maximize the total resultant socioeconomic benefits.

Design of Real-Time Emergency Response System for Highway Networks: Application for High Frequency of Traffic Emergency Events During Peak Hours

This paper proposes a general framework of real-time emergency response operations for highway networks experiencing a high frequency of concurrent traffic emergency events. The proposed system consists of three principal models working collectively to optimize the location assignment of available response units, to estimate the probabilities of event occurrences, and to project the incident clearance time. This system was designed to assist responsible agencies in assessing the need to relocate available incident response units in real-time operations on the basis of the available resources and detected traffic information. Because the proposed system was designed mainly for the traffic incident management teams to respond to the traffic emergency events, it aimed to improve the networkwide traffic condition and the service performance by solving multiple conflicting objectives. This aim is different from most existing studies that target mainly emergency medical service. The empirical evaluation results using the incident data from I-695–MD-695 in Maryland showed that the dynamic real-time dispatch strategy could outperform the static dispatch and state-of-the-practice patrolling strategies with respect to minimizing the total delays induced by incidents. Furthermore, the dynamic dispatch strategy will enable the operating agency to use the available resources better than will the static dispatch strategy, especially when many traffic emergency events in congested corridors may occur in a relatively short time period.

Design and Evaluation of Operational Strategies for Deploying Emergency Response Teams: Dispatching or Patrolling

AbstractBoth patrolling and prepositioned strategies for allocating emergency traffic response units have been implemented in practice. To compare the performance of both response strategies, this study has conducted an efficiency comparison based on the field data from the I-495/I-95 Capital Beltway. The extensive experimental results have revealed that the effectiveness of those response strategies varies with some critical factors, including the spatial distribution of incident frequency over different times of a day, the fleet size of the response team, the congestion level, and the available detection sources. In view of the resource constraints, the study has further presented a methodology to determine the most cost-beneficial fleet size operated with the proposed strategies, considering the marginal cost and the benefit of an additional response unit on the resulting total social benefits. The analysis results with the data from the Capital Beltway could serve as the basis for highway agencies to ...