Search

The nation's freeway systems are becoming increasingly congested. A major contribution to traffic congestion on freeways is due to traffic incidents. Traffic incidents are non-recurring events such as accidents or stranded vehicles that cause a temporary roadway capacity reduction, and they can account for as much as 60 percent of all traffic congestion on freeways. One major freeway incident management strategy involves diverting traffic to avoid incident locations by relaying timely information through Intelligent Transportation Systems (ITS) devices such as dynamic message signs or real-time traveler information systems. The decision to divert traffic depends foremost on the expected duration of an incident, which is difficult to predict. In addition, the duration of an incident is affected by many contributing factors. Determining and understanding these factors can help the process of identifying and developing better strategies to reduce incident durations and alleviate traffic congestion. A number of research studies have attempted to develop models to predict incident durations, yet with limited success. This dissertation research attempts to improve on this previous effort by applying data mining techniques to a comprehensive incident database maintained by the District 4 ITS Office of the Florida Department of Transportation (FDOT). Two categories of incident duration prediction models were developed: "offline" models designed for use in the performance evaluation of incident management programs, and "online" models for real-time prediction of incident duration to aid in the decision making of traffic diversion in the event of an ongoing incident. Multiple data mining analysis techniques were applied and evaluated in the research. The multiple linear regression analysis and decision tree based method were applied to develop the offline models, and the rule-based method and a tree algorithm called M5P were used to develop the online models. The results show

BDK80 TWO #977-03, Microscopic simulation can provide significant support to traffic management center (TMC) operations. However, traffic simulation applications require data that are expensive and time-consuming to collect. Data collected by TMCs can be used as a primary source for the provision of the required data. The goal of this project is to explore the development of methods and tools for the use of microscopic traffic simulation models to support the TMC software implementation, operation, and testing on one hand, and the use of Intelligent Transportation System (ITS) data to support the development and calibration of simulation models on the other., The project products include software utilities that use the existing TMC databases and other available information for the preparation and calibration of microscopic simulation tools. In addition, the products include utilities to support testing of the TMC software modules and data archiving processes, as demonstrated by use cases of the tools developed in this study.

BDK80 TWO #977-02, The goal of this project is to develop decision support tools to support traffic management operations based on collected intelligent transportation system (ITS) data. The project developments are in accordance with the needs of traffic management centers (TMCs) in Florida, as identified in this project. The project developments include new models to estimate travel time based on point detectors. These models were compared with existing travel time estimation methods including the one used in the SunGuide software. The results indicate that all of the tested methods perform at acceptable and comparable levels at low congestion levels. However, their performances vary with the increase in congestion levels. The comparison with other estimation methods shows that the developed models perform well in all cases., The developments of this study include a method to estimate traffic diversion based on the traffic detector and incident data. In addition, this study developed a method to determine the time lag between incident occurrence and the time it is recorded in the SunGuide database. This study also developed methods to estimate freeway secondary crashes, potential incident impacts on mobility, and a new method to allow incidents to be classified into categories based on primary incident attributes and impacts.

BDK80 977-11, This project has developed and implemented a software environment to utilize data collected by Traffic Management Centers (TMC) in Florida, in combination with data from other sources to support various applications. The environment allows capturing and fusing the data from multiple sources. The combined data can support the performance measurements of transportation system, transportation system modeling, assessment of the benefits of Intelligent Transportation System (ITS) applications such as incident management, ramp metering, and so on, and discovery of different relationships and associations of attributes through data mining and visualization methods. The developed modules are demonstrated in a series of use cases.

BDK80 977 - 09, Integrated Corridor Management (ICM) strategies have been proposed to address needs and provide solutions beyond those that can be provided when applying advanced strategies and technologies to one transportation subsystem at a time. The goal of this project was to investigate ICM strategies for implementation in Florida and to demonstrate the applications of these strategies. A Web-based system, referred to as Integrated Regional Information Sharing and Decision Support system (IRISDS), was developed to provide a platform to satisfy needs for ICM implementation, identified in this project. IRISDS receives information in real time from highway and transit agencies, communicates the information to the regional agencies, provides a platform for estimating and predicting the performance measures in real time, and utilizes the data to provide decision support to transportation agencies.