Growing concern over traffic safety has led to research into prediction of freeway crashes in an advanced traffic management and information systems environment. A crash likelihood prediction model was developed by using real-time traffic flow variables (measured through a series of underground sensors) potentially associated with crash occurrence. The issues related to real-time application, including range of stations and time slice duration to be examined, were also addressed. The methodology used, matched case-control logistic regression, was adopted from epidemiological studies in which every crash is a case and corresponding noncrashes act as controls. The 5-min average occupancy observed at the upstream station during the 5 to 10 min before the crash, along with the 5-min coefficient of variation in speed at the downstream station during the same time, was found to affect crash occurrence most significantly and hence was used to calculate the corresponding log-odds ratio. A threshold value for this ratio may then be set to determine whether the location must be flagged as a potential crash location. It was shown that by using 1.0 as the threshold for the log-odds ratio, more than 69% crash identification was achieved.
This study aims at 'predicting' the occurrence of lane-change related freeway crashes using the traffic surveillance data collected from a pair of dual loop detectors. The approach adopted here involves developing classification models using the historical crash data and corresponding information on real-time traffic parameters obtained from loop detectors. The historical crash and loop detector data to calibrate the neural network models (corresponding to crash and non-crash cases to set up a binary classification problem) were collected from the Interstate-4 corridor in Orlando (FL) metropolitan area. Through a careful examination of crash data, it was concluded that all sideswipe collisions and the angle crashes that occur on the inner lanes (left most and center lanes) of the freeway may be attributed to lane-changing maneuvers. These crashes are referred to as lane-change related crashes in this study. The factors explored as independent variables include the parameters formulated to capture the overall measure of lane-changing and between-lane variations of speed, volume and occupancy at the station located upstream of crash locations. Classification tree based variable selection procedure showed that average speeds upstream and downstream of crash location, difference in occupancy on adjacent lanes and standard deviation of volume and speed downstream of the crash location were found to be significantly associated with the binary variable (crash versus non-crash). The classification models based on data mining approach achieved satisfactory classification accuracy over the validation dataset. The results indicate that these models may be applied for identifying real-time traffic conditions prone to lane-change related crashes.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.