JMJustin Mukai

Justin Mukai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Justin Mukai has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Work Zone Performance Measures Derived from Connected Vehicle Data for Safety and Mobility Assessment

    by Rahul Suryakant Sakhare, Jairaj Desai, Myles Overall, Justin Mukai, Juan Pava, John McGregor, Darcy M. Bullock

    On 1 November 2024, the Federal Highway Administration issued a final rule updating the 23 CFR Part 630 Subpart J on Work Zone Safety and Mobility, detailing performance measures and reporting requirements. The rule suggests that state agencies should define formal performance measures that can be tracked consistently for the continuity of work zone program management across states. The objective is to help identify work zones needing mobility or safety improvements, as well as provide quantitative feedback on the best practices. The emergence of connected vehicle data over the past few years provides a scalable approach for agencies to calculate and monitor the performance measures defined in the CFR, covering, but not limited to, speed, travel time, queue length and duration, hard braking events and speed differentials. This paper describes techniques that use connected vehicle data to estimate different measures that map into the performance measures defined in this rule. A 2024 work zone in Illinois along I-24 was chosen to demonstrate the utility of the measures. The paper concludes with a discussion of ongoing work applying these derived measures to 101 work zones across 9 states in 2025 to demonstrate scalability.

  • Open Access

    Measuring the Impact of Recovery Resource Delay on Traffic Incident Management Clearance Times

    by Myles W. Overall, Justin Mukai, Rahul Suryakant Sakhare, Jairaj Desai, Hillary Lowther, Darcy M. Bullock

    Traffic incident management (TIM) practices have been widely demonstrated to reduce congestion and secondary crashes. TIM performance measures have evolved over the years and have been a critical tool for agencies to benchmark their operations and identify opportunity for improvement. This paper discusses how the deployment of incident resources can be tracked to improve the fidelity of those performance measures to help guide their TIM program management. Specifically, the paper focuses on integrating a new TIM reference point that identifies when all necessary recovery resources are on scene (T4,ANRR). The value of this reference point is explained through four detailed case studies, and the ability to tabulate this value at scale is demonstrated for 128 incidents. Subsequently, statistics from 128 incidents are presented. Median recovery resource mobilization time for car crashes, semi crashes, car fires, and semi fires were 32, 42, 45, and 66 min, respectively. However, the upper quartile values for those same types of incidents increased to 55, 66, 69, and 105 min, respectively. Of particular note, the paper demonstrates the importance of careful proactive planning for response resources on incidents involving large vehicles that require significant recovery resources and how those response times extend incident clearance times. Tracking T4,ANRR is a first step toward identifying training and perhaps incentive programs to mitigate delays in obtaining all of the needed recovery resources on scene.


  • Connected Vehicle Trajectory Data to Screen Network for Hard-Braking and Hard-Acceleration Events

    by Rahul S. Sakhare, Jairaj Desai, Christopher Gartner, Justin Mukai, Nathan Sturdevant, Nathaniel Shellhamer, Taylor Ruble, Daniel McCoy, Darcy M. Bullock

    Hard-braking and hard-acceleration data has been demonstrated as an important emerging data source that provides quicker feedback than crash data. In fact, a strong correlation between hard braking on the interstate and crash rates has been reported in previous studies. A previous study has shown that there are approximately 147 hard-braking events in a work zone for every crash. However, there have been subtle changes in acceleration thresholds as well as techniques automotive companies and third-party vendors use to compute hard braking. The motivation of this study is to define scalable and sustainable procedures for obtaining consistent hard-braking data. That data can then be used to develop a statewide system for longitudinal monitoring of hard-braking trends to assist in identifying and prioritizing roadways for more detailed safety studies. This study developed 0.1-mi “smart polygons” (linear-referenced geofencing features) that provide a directional base map for the entire system of Interstates, U.S. routes and state routes across the state of Indiana. Approximately 100 billion connected vehicle records were analyzed to derive hard braking statistics for the smart polygons.

  • Case Studies Documenting Lessons Learned and Identifying Opportunities for Maintenance of Traffic (MOT) Improvements

    by Myles W. Overall, Justin Mukai, Rahul S. Sakhare, Jairaj Desai, Deborah Horton, Darcy M. Bullock

    From July 2023 to July 2025, the team has performed several dozen after-action reviews of interstate work zones and the associated maintenance of traffic (MOT). These after-action reports generally contain the following information: Date, location, visual images, connected vehicle summary graphics, qualitative discussion of activity, and in some cases press releases or media posts. In general, these themes emerged: 1. MOT plans in some cases do not accurately capture the geometry constraints placed by bridges, guardrail and or barrier wall. It is important that design reviews place careful focus on ensuring lane widths, shoulders, and shoulder treatments fit across the entire cross section of each phase or requests for design exceptions be initiated. In some cases, performing some type of LiDAR survey prior to design may assist MOT designers in effectively capturing more accurate location and dimensions of existing geometrics, particularly edge of pavement, edge of bridge, guardrails, and embankments. 2. When lane shifts are initiated, the designers should examine the path of the vehicle at both the start and end of the transition. In some cases, the end of the transition occurs quite close to either a guardrail or narrow section of pavement. In some cases, either gentler transitions or additional horizontal clearance should be considered. 3. There is relatively little dialog between the temporary traffic control contractors and designers on what are the best practices and requirements for implementing a change in MOT. 4. To sustain this engagement between designers, and MOT contractors, it is recommended that selected projects include MOT review with design engineers, and contractor as part of the close out process to document lessons learned. 5. Rolling slows downs have a role in MOT, but there appears to be inconsistent use of rolling slowdowns for short term closures. It is recommended that requirements for rolling slowdowns be identified in the MOT plans. If contractors are required to use rolling slowdowns not documented in MOT plans, they should be required to obtain approval from the Indiana Department of Transportation and notify the Traffic Management Center. 6. Barrier walls are an important tool for MOT. However, their set up can have significant impact on traffic capacity and create queues. Project plans should define days/time periods these are permitted to be installed and/or removed.

  • Continued Deployment of Indiana Work Zone Analytics

    by Myles W. Overall, Justin Mukai, Jairaj C. Desai, Rahul S. Sakhare, Mischa Kachler, John McGregor, Darcy M. Bullock

    Work zones along interstates often have increased congestion and crash rates when locations are close to or over capacity. Having agile monitoring methods to identifying emerging issues and challenges can provide data to transportation agency decision makers to refine maintenance of traffic plans and inform future designs. This study developed techniques to fuse a multitude of data sources including connected vehicle speeds, connected vehicle hard-braking events, crash reports, digital alerts, commercial vehicle dash camera images, into a weekly interstate work zone report that gives stakeholders a holistic overview of their work zone operations and allowed for easy identification of opportunities for improvement. Approximately 249 weekly work zone reports were generated and distributed to approximately 100 stakeholders across the state on an approximately weekly basis. These reports provide an at-a-glance view of statewide, district, and route mobility, crash data, hard-braking, and most recently dash camera images to contextualize the heatmaps. Outside of operational value within the state, these types of weekly reports have been developed for other states through a Transportation Pooled Fund Study on Work Zone Analytics with participation from the Federal Highway Administration and 8 other states, and helping shape USDOT’s 23 CFR Part 630 Subpart J that was released on November 1, 2024. The methodologies developed in this study serve as a framework for transportation agencies, practitioners, and other stakeholders looking to use emerging connected vehicle data, smart work zone data, among others, to monitor the performance of their work zones on a regular basis. The practice of estimating hard-braking events from raw connected vehicle data instead of relying on instantaneous hard-braking events with opaque vendor-defined braking thresholds now allows for greater freedom to tweak acceleration thresholds based on the roadway class being analyzed, and opens opportunities for dialogue among practitioners on determining ideal custom thresholds for freeways, arterials, or other facilities.

  • Development of Incident Management Performance Measures Database and Supporting Training Material

    by Myles W. Overall, Justin Mukai, Rahul S. Sakhare, Jairaj Desai, Hillary Lowther, Edward Cox, James Sturdevant, Darcy M. Bullock

    Secondary crashes resulting from traffic queues are a significant national safety concern. Traffic Incident Management (TIM), which involves coordinated multi-agency response to roadway incidents, is widely recognized as an effective approach to mitigating these crashes. This study aimed to develop a library of after-action case studies to support TIM training and evaluate current practices. Leveraging connected vehicle data alongside crash reports, camera footage, and dispatch audio, the research compiled 267 comprehensive after-action review reports for incidents across Indiana from June 2020 to March 2025. These reports, indexed by key attributes such as date, location, and incident type, form what is believed to be the most extensive archive of TIM case studies in the U.S. Key recommendations emphasize the value of integrating camera imagery, connected vehicle data, and dispatch audio to enhance responder training, promote peer learning, and improve situational awareness. This resource serves as both a training tool and a model for developing future TIM documentation nationwide.

  • Open Access

    Impact of Privacy Filters and Fleet Changes on Connected Vehicle Trajectory Datasets for Intersection and Freeway Use Cases

    by Enrique D. Saldivar-Carranza, Rahul Suryakant Sakhare, Jairaj Desai, Jijo K. Mathew, Ashmitha Jaysi Sivakumar, Justin Mukai, Darcy M. Bullock

    Commercially available crowdsourced connected vehicle (CV) trajectory data have recently been used to provide stakeholders with actionable and scalable roadway mobility infrastructure performance measures. Transportation agencies and automotive original equipment manufacturers (OEMs) share a common vision of ensuring the privacy of motorists that anonymously provide their journey information. As this market has evolved, the fleet mix has changed, and some OEMs have introduced additional fuzzification of CV data around 0.5 miles of frequently visited locations. This study compared the estimated Indiana market penetration rates (MPRs) between historic non-fuzzified CV datasets from 2020 to 2023 and a 5–11 May 2024, CV dataset with fuzzified records and a reduced fleet. At selected permanent interstate and non-interstate count stations, overall CV MPRs decreased by 0.5% and 0.3% compared to 2023, respectively. However, the trend in previous years was upward. Additionally, this paper evaluated the impact on data characteristics at freeways and intersections between the 5–11 May 2024, fuzzified CV dataset and a non-fuzzified 7–13 May 2023, CV dataset. The analysis found that the total number of GPS samples decreased 10% statewide. Of the evaluated 54,284 0.1-mile Indiana freeway, US Route, and State Route segments, the number of CV samples increased for 33.8% and decreased for 65.9%. This study also evaluated 26,291 movements at 3289 intersections and found that the number of available trajectories increased for 28.3% and decreased for 70.4%. This paper concludes that data representativeness is enough to derive most relevant mobility performance measures. However, since the change in available trajectories is not uniformly distributed among intersection movements, an unintended sample bias may be introduced when computing performance measures. This may affect signal retiming or capital investment opportunity identification algorithms.