71 research outputs found
Measurement and Analysis of Heterogenous Vehicle Following Behavior on Urban Freeways: Time Headways and Standstill Distances
No full textMicroscopic traffic modelling is a popular tool in the transportation field, but using such models comes with significant data needs in order to properly calibrate them. Two important driver behavior parameters in these models are the preferred time headways and standstill distances. In this paper, an economical method for collecting headways and standstill distances is presented and applied to urban freeways in Iowa, USA. The following time headways and standstill distances were categorized into four combinations of car and truck pairs. It was found that headway values largely depend on the following vehicle type-when a car was following the average headway was around 2 seconds, compared to around 3 seconds when a truck was following. Additionally, the car-car combination leaves much less space when stopped than when a pair involves trucks. In particular, the average standstill distance of a car following a car was found to be around 9 feet, while the average standstill distances are around 12 feet when a truck is involved. However, both headways and standstill distances follow fairly disperse distributions, due to the heterogeneity in driver behavior. Thus, microsimulation software should be improved to allow these parameters to follow distributions.This proceeding was published as Houchin, Andrew, Jing Dong, Neal Hawkins, and Skylar Knickerbocker. "Measurement and analysis of heterogenous vehicle following behavior on urban freeways: Time headways and standstill distances." In Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on (2015): 888-893. DOI: 10.1109/ITSC.2015.149. Posted with permission.</p
Forecasting Road Incident Duration Using Machine Learning Framework
No full textTraffic congestion caused by nonrecurring incidents such as vehicle crashes and debris is a key issue for Traffic Management Centers (TMCs). Clearing incidents in a timely manner is essential to improve safety and reduce delays and emissions for the traveling public. However, TMCs and other responders face a challenge in predicting the duration of incidents (until the roadway is clear), making decisions about what resources to deploy is difficult. To address this problem, this research developed an analytical framework and end-to-end machine learning solution to predict the duration of the incident based on the information available as soon as an incident report is received. Quality predictions of incident duration can help TMCs and other responders take a proactive approach in deploying responder services such as tow trucks, and maintenance crews, or activating alternative routes. The predictions use a combination of classification and regression machine learning modules. The performance of the developed solution has been evaluated based on the Mean Absolute Error (MAE), or deviation from the actual incident duration as well as Area Under the Curve (AUC) and Mean Absolute Percentage Error (MAPE). The results showed that the framework significantly improved the prediction of incident duration compared to previous research methods.This article is published as Ajit, Smrithi, Varsha R. Mouli, Skylar Knickerbocker, and Jonathan S. Wood. "Forecasting Road Incident Duration Using Machine Learning Framework." Journal of Transportation Technologies 15, no. 2 (2025): 222-251. doi: https://doi.org/10.4236/jtts.2025.152012
Traffic Incident Management Performance Measures: Ranking Agencies on Roadway Clearance Time
No full textThis study develops a procedure to rank agencies based on their incident responses using roadway clearance times for crashes. This analysis is not intended to grade agencies but to assist in identifying agencies requiring more training or resources for incident management. Previous NCHRP reports discussed usage of different factors including incident severity, roadway characteristics, number of lanes involved and time of incident separately for estimating the performance. However, it does not tell us how to incorporate all the factors at the same time. Thus, this study aims to account for multiple factors to ensure fair comparisons. This study used 149,174 crashes from Iowa that occurred from 2018 to 2021. A Tobit regression model was used to find the effect of different variables on roadway clearance time. Variables that cannot be controlled directly by agencies such as crash severity, roadway type, weather conditions, lighting conditions, etc., were included in the analysis as it helps to reduce bias in the ranking procedure. Then clearance time of each crash is normalized into a base condition using the regression coefficients. The normalization makes the process more efficient as the effect of uncontrollable factors has already been mitigated. Finally, the agencies were ranked by their average normalized roadway clearance time. This ranking process allows agencies to track their performance of previous crashes, can be used in identifying low performing agencies that could use additional resources and training, and can be used to identify high performing agencies to recognize for their efforts and performance.This article is published as Mumtarin, Maroa, Skylar Knickerbocker, Theresa Litteral, and Jonathan S. Wood. "Traffic incident management performance measures: ranking agencies on roadway clearance time." Journal of Transportation Technologies 13, no. 3 (2023): 353-368. doi: https://doi.org/10.4236/jtts.2023.133017
A Comprehensive Data Driven Evaluation of Wide Area Probe Data: Opportunities and Challenges.
No full textThere is a growing desire, among transportation organizations and state DOTs, to consider augmenting traditional traffic data collection with probe - based services for expanded coverage under constrained budgets. The nature of traffic data collection with probes is however dramatically different from traditional traffic data collection techniques. This affects how the new technology is applied and used to solve current traffic problems such as traffic incident management and roadway performance assessment. The current paper summarizes the experiences and lessons learned while using probe data for traffic operations and safety management and makes recommendations on opportunities to maximize the use of probe data in light of its limitations.This paper was peer-reviewed by TRB and presented at the Annual Meeting of the Transportation Research Board, Washington, D.C. and can be cited as Adu-Gyamfi, Yaw Okyere, Anuj Sharma, Skylar Knickerbocker, Neal Hawkins, and Michael Jackson. "Comprehensive Data Driven Evaluation of Wide Area Probe Data: Opportunities and Challenges." In Transportation Research Board 95th Annual Meeting, no. 16-6482. 2016. Posted with permission.</p
Unlocking Insights Addressing Alcohol Inference Mismatch through Database-Narrative Alignment
No full textRoad traffic crashes are a significant global cause of fatalities, emphasizing the urgent need for accurate crash data to enhance prevention strategies and inform policy development. This study addresses the challenge of alcohol inference mismatch (AIM) by employing database narrative alignment to identify AIM in crash data. A framework was developed to improve data quality in crash management systems and reduce the percentage of AIM crashes. Utilizing the BERT model, the analysis of 371,062 crash records from Iowa (2016-2022) revealed 2,767 AIM incidents, resulting in an overall AIM percentage of 24.03%. Statistical tools, including the Probit Logit model, were used to explore the crash characteristics affecting AIM patterns. The findings indicate that alcohol-related fatal crashes and nighttime incidents have a lower percentage of the mismatch, while crashes involving unknown vehicle types and older drivers are more susceptible to mismatch. The geospatial cluster as part of this study can identify the regions which have an increased need for education and training. These insights highlight the necessity for targeted training programs and data management teams to improve the accuracy of crash reporting and support evidence-based policymaking.This is a preprint from Bhagat, Sudesh, Raghupathi Kandiboina, Ibne Farabi Shihab, Skylar Knickerbocker, Neal Hawkins, and Anuj Sharma. "Unlocking Insights Addressing Alcohol Inference Mismatch through Database-Narrative Alignment." arXiv preprint arXiv:2506.19342 (2025). doi: https://doi.org/10.48550/arXiv.2506.19342
UAV-Based Automatic System for Seatbelt Compliance Detection at Stop-Controlled Intersections
No full textTransportation agencies often rely on manual surveys to monitor seatbelt compliance; however, these methods are limited by surveyor fatigue, reduced visibility due to tinted windows or low lighting, and restricted coverage to specific locations, making manual surveys prone to errors and unrepresentative of the broader driving population. This paper presents an automated seatbelt detection system leveraging the YOLO11 neural network on video footage from a tethered uncrewed aerial vehicle (UAV). The objectives are to (1) develop a robust system for detecting seatbelt use at stop-controlled intersections, (2) evaluate factors impacting detection accuracy, and (3) demonstrate the potential of UAV-based compliance monitoring. The model was evaluated in real-world applications at a single-lane and a complex multilane stop-controlled intersection in Iowa. Three studies examined key factors influencing detection accuracy: (i) seatbelt-shirt color contrast, (ii) sunlight direction, and (iii) vehicle type. The system’s performance was compared against manual video reviews and large language models (LLMs), with assessments focusing on detection accuracy, resource utilization, and computational efficiency. Overall, the model achieved a mean average precision (mAP) of 0.902, demonstrated high accuracy across the three studies and outperformed manual methods in reliability and efficiency while providing a scalable, cost-effective alternative to LLM-based solutions.This is a preprint from Owusu, Gideon Asare, Ashutosh Dumka, Kojo Adu-Gyamfi, Enoch Kwasi Asante, Rishab Jain, Skylar Knickerbocker, Neal Hawkins, and Anuj Sharma. "UAV-Based Automatic System for Seatbelt Compliance Detection at Stop-Controlled Intersections." (2025). doi: https://doi.org/10.20944/preprints202503.0114.v1
Evaluation of Transverse Markings as a Speed Transition Zone Countermeasures in Small, Rural Communities
No full textSmall rural communities located along major state or county roadways typically find most of the traffic along their main thoroughfares is pass-through rather than local traffic. Unfortunately, drivers passing through these communities often enter at high rates of speeds, which are often significantly higher than the speed limit of the local segment. Speed management in rural areas requires different considerations compared to urban areas and, within the US, rural speed management is not as advanced with little experience or guidance for agencies to draw on. This paper summarizes the results of a study that evaluated, in part, several different types of transverse pavement markings within the speed transition zones in small rural communities. Three different countermeasures were evaluated: converging chevrons, transverse lane markings, and optical speed bars.This article is published as Hallmark, S. , Hawkins, N. and Knickerbocker, S. (2021) Evaluation of Transverse Markings as a Speed Transition Zone Countermeasures in Small, Rural Communities. Journal of Transportation Technologies, 11, 61-77. https://doi.org/10.4236/jtts.2021.111004. Posted with permission
Evaluation of Sequential Dynamic Chevron Warning Systems on Rural Two-Lane Curves
No full textRoadway departure crashes are a significant safety concern. A majority of these crashes occur on rural two-lane roadways, with a disproportionate number occurring on horizontal curves. The average crash rate for horizontal curves is about three times that of other highway segments. Curve-related crashes involve a number of roadway and driver causative factors with speed being a preeminent factor. Implementing safety countermeasures on rural horizontal curves to address these crash types can improve the safety performance. Chevron alignment signs provide additional emphasis and guidance for drivers negotiating curves. To further emphasize the curve, some agencies have started using a Sequential Dynamic Chevron Warning System (SDCWS) which uses LED lights within each chevron sign to provide sequential lighted guidance through the curve.The research team evaluated eighteen rural horizontal curves where a SDCWS had been implemented on rural 2-lane curves. Reference sites with similar characteristics were selected and included in the study. Models were developed using an Empirical Bayes (EB) methodology for non-intersection (total) crashes and injury crashes. Additional countermeasures were present at some of the sites and were included in the model. Using these data, the study developed crash modification factors for SDCWS with a resulting Crash Modification Factor (CMF) of 0.34 for total crashes (non-intersection) and 0.49 for injury crashes.This is a manuscript of an article published as Hallmark, Shauna, Amrita Goswamy, Theresa Litteral, Neal Hawkins, Omar Smadi, and Skylar Knickerbocker. "Evaluation of sequential dynamic chevron warning systems on rural two-lane curves." Transportation research record 2674, no. 10 (2020): 648-657. doi: https://doi.org/10.1177/0361198120935872
Innovative Analysis for Reducing Data Using a Tracking Methodology
No full textEvery year the National Highway Traffic Safety Administration (NHTSA) publishes its finding of crash statistics and, in the latest data from 2010, speeding was a factor in 31% of the traffic fatalities in 2010(NHTSA Speeding, 2010). As a surrogate for speed safety, reductions in speeds statistics are used to determine whether treatments are effective at improving safety. The issue with this type of analysis is that the treatments are directed toward a specific user and by using all vehicles data, some vehicles not affected by the treatment are included in the analysis.
To mitigate these vehicles, tracking may be used to reduce the data collected to only the affected vehicles. This provides more accurate and precise data when evaluating the effectiveness of the treatment. Limited research has been completed for tracking, because of this it is unknown whether reducing the data will provide any statistical difference as well as indicators for when tracking should be used. The objective of this thesis is to determine difference using a standard method and tracking method as well as provide indicators of when tracking should be used. In addition, a speed reduction method will be analyzed as well to determine a separate safety surrogate measure.
Using two current research projects for the analysis, traffic calming and curve safety, the standard method and tracking method were compared. The results showed that the standard method both under- and over-estimated the effectiveness of the treatments depending on the site location. After reviewing the data the access points around the treatment provided an indicator for when the speed statistics were statistically different using the tracking method. This was expected because of turning movements created by such points that affect the vehicles speeds. Upstream speeds were the other indicator found that had an effect on the data. In this situation it affected the speed reduction statistics that were calculated with tracking vehicles. These statistics provided a detailed view of where vehicles speeds were being reduced that would not be capable with the standard method. Overall, the objectives of the thesis were met by showing that tracking vehicles does have an effect on speed statistics. Indicators were found but further research must be completed to determine other possible indicators as well as other possible ways to reduce data.</p
Exploring the Efficacy of Large-Scale Connected Vehicle Data in Real-Time Traffic Applications
No full textTransportation agencies strive to optimize their spending on data collection by exploring efficient techniques that provide reliable traffic data. In recent years, the automobile industry has experienced vast developments in wireless technology that enables agencies to collect valuable traffic data in large volumes from connected vehicles (CVs). Unlike traditional data collection techniques, the CV or probe data are economically feasible for wide-area coverage. Therefore, this study aims to explore the CV data provided by Wejo Connected Vehicle Data Solutions for their feasibility in real-time traffic applications. The large volumes of the CV data are compared against a ground reference sensor to assess their reliability. The performance metrics such as market penetration rates, speed bias, and latency are used to understand the efficacy of the data for their usage over infrastructure-mounted sensors in regular traffic operations. The analysis resulted in an average market penetration of 6.3% in the study area with a mean speed error of less than 1 mph. The data also expressed potential event detection capabilities with relatively lower latencies. Furthermore, latent class models are developed on the penetration rate and speed bias data sets to identify the unobserved groups within the data, resulting in five-class models for both data sets. The paper concludes by summarizing the potential benefits of the CV data concerning the assessed metrics and provides opportunities to replace or augment the data to existing infrastructure-mounted traffic sensors.This accepted article is published as Kandiboina, R., Knickerbocker, S., Bhagat, S., Hawkins, N., & Sharma, A. (2023). Exploring the Efficacy of Large-Scale Connected Vehicle Data in Real-Time Traffic Applications. Transportation Research Record, 0(0). https://doi.org/10.1177/03611981231191512. Posted with permission
- …
