The application of a nonlinear time series model to the prediction of traffic parameters on a freeway network is investigated. The nonlinear time series approach is a statistical technique that has strong potential for on-line implementation. A new approach for predicting corridor travel times is developed and tested with travel-time data. The travel-time data are derived from observed speed data, which are collected from an 18-km (11.2-mi) freeway section in Orlando, Florida. The westbound Interstate-4 morning peak period (6:00 to 10:00 a.m.) for 20 incident-free days is tested with the goal of predicting recurrent congestion. The problem is addressed from the perspectives of single-variable and multiple-variable prediction of corridor travel times. In single-variable prediction, speed time-series data are used to forecast travel times along the freeway corridor. A calibrated single-variable prediction model is developed through the application of decay factors to smooth out the input data and the establishment of a threshold on the minimum speed prediction permitted. Multivariable prediction schemes are developed using speed, occupancy, and volume data provided by inductive loop detectors on the study section. The prediction performance of the calibrated single-variable model is shown to be superior to the multivariable prediction schemes. This new approach produces reasonable errors for short-term (5-min) travel-time predictions. The developed model can be implemented on-line with minimal effort.
Because wrong-way driving (WWD) crashes are often severe, it is important for transportation agencies to identify WWD hotspot segments appropriate for potential implementation of advanced WWD countermeasures. Two approaches to identify these hotspot segments were developed and applied to a case study of limited-access highways in Central Florida. The first approach used a Poisson regression model that predicted the number of WWD crashes in a roadway segment based on WWD citations, 911 calls, traffic volumes, and interchange designs. Combining this predicted crash value with the actual number of WWD crashes in the segment gave the WWD crash risk of the segment. Ranking roadway segments by WWD crash risk provided agencies with an understanding of which segments had high WWD crash frequencies and high potential for future WWD crashes. This approach was previously applied to South Florida; the research presented here extended this approach to Central Florida. The second approach was based on operational data collected in traffic management centers and could be used if accurate WWD 911 and citation data with GPS location were not available or as a supplement to the first approach. The approach identified and ranked WWD hotspots on the basis of the reported duration of WWD events. In Central Florida, the results of the two approaches agreed with each other and were used by agencies to decide where to implement advanced WWD countermeasures. Together, these approaches can help transportation agencies determine regional WWD hotspots and cooperate to implement advanced WWD countermeasures at these locations.
Wrong-way driving (WWD) is dangerous and poses a significant legal and safety risk when it occurs on limited access facilities. Most previous studies focused on WWD crashes to develop countermeasures. The combined risk of WWD citations and 911 calls, however, has been overlooked. Furthermore, because WWD crashes are rare and represent less than 3% of all crashes, such crashes are difficult to analyze. WWD prediction is an important assessment because it can help mitigate and reduce future occurrences. This paper builds on previous work pioneered by the authors in which WWD crashes were predicted with the use of WWD noncrash events (e.g., citations and 911 calls). These WWD noncrash events occur more frequently, and their data are widely available. The paper demonstrates how WWD 911 calls and citations, along with route characteristics, can be linked to WWD crashes and so target corridors for countermeasures. Two models were developed and applied in South Florida to identify WWD hot spots. The first model shows that WWD citations and 911 calls positively affect yearly crash prediction. The second model identifies hot spot segments in a route and predicts crashes during a 4-year period. This second model predicts crashes with the use of several variables, such as major interchanges per mile, directional interchanges per mile, and WWD 911 calls along the segment. The findings showed high WWD risk values on SR-821 (Homestead Extension) from Exits 20 to 39 and on SR-9 (I-95) from Exits 0 to 6B and Exits 7 to 14.
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.