Browsing by Author "Miller, Andrew"

Now showing 1 - 11 of 11
  • Thumbnail Image
    Behavior-based Predictive Safety Analytics – Pilot Study
    Engström, Johan; Miller, Andrew; Huang, Wenyan; Soccolich, Susan A.; Machiani, Sahar Ghanipoor; Jahangiri, Arash; Dreger, Felix; de Winter, Joost (SAFE-D: Safety Through Disruption National University Transportation Center, 2019-04)
    This report gives an overview of the main findings from the Behavior-based Predictive Safety Analytics – Pilot Study project. The main objective of the project was to investigate the possibilities of developing statistical models predicting individual driver crash involvement based on individual driving style, demographic and behavioral history variables, using large sets of naturalistic driving data. The project was designed as a pilot project with the objective of providing the basis for a future more comprehensive research effort. Based on Second Strategic Highway Research Program (SHRP2) data, a subset of behavior and crash data including 2,458 drivers was created for analysis. The data were analyzed to investigate to what extent these drivers were differentially involved in crashes and near crashes, to what extent this was associated with individual characteristics, and if it is possible to predict individual drivers’ crash and near crash involvement based on variables representing individual characteristics. The results clearly demonstrated the presence of differential crash and near crash involvement and showed significant associations between enduring personal factors and crash involvement. Moreover, logistic regression and random forest classifiers were relatively successful in predicting crash and near crash involvement based on individual characteristics, but the ability to specifically predict involvement in crashes was more limited.
  • Thumbnail Image
    Challenges in Conducting Empirical Epidemiological Research with Truck and Bus Drivers in Diverse Settings in North America
    Soccolich, Susan A.; Ridgeway, Christie; Mabry, J. Erin; Camden, Matthew C.; Miller, Andrew; Iridiastadi, Hardianto; Hanowski, Richard J. (MDPI, 2022-09-30)
    Over 6.5 million commercial vehicle drivers were operating a large truck or bus in the United States in 2020. This career often has high stress and long working hours, with few opportunities for physical activity. Previous research has linked these factors to adverse health conditions. Adverse health conditions affect not only the professional drivers’ wellbeing but potentially also commercial motor vehicle (CMV) operators’ safe driving ability and public safety for others sharing the roadway. The prevalence of health conditions with high impact on roadway safety in North American CMV drivers necessitates empirical epidemiological research to better understand and improve driver health. The paper presents four challenges in conducting epidemiological research with truck and bus drivers in North America and potential resolutions identified in past and current research. These challenges include (1) the correlation between driving performance, driving experience, and driver demographic factors; (2) the impact of medical treatment status on the relationship between health conditions and driver risk; (3) capturing accurate data in self-report data collection methods; and (4) reaching the CMV population for research. These challenges are common and influential in epidemiological research of this population, as drivers face severe health issues, health-related federal regulations, and the impact of vehicle operation on the safety of themselves and others using the roadways.
  • Thumbnail Image
    The Chesapeake Bay program modeling system: Overview and recommendations for future development
    Hood, Raleigh R.; Shenk, Gary W.; Dixon, Rachel L.; Smith, Sean M. C.; Ball, William P.; Bash, Jesse O.; Batiuk, Rich; Boomer, Kathy; Brady, Damian C.; Cerco, Carl; Claggett, Peter; de Mutsert, Kim; Easton, Zachary M.; Elmore, Andrew J.; Friedrichs, Marjorie A. M.; Harris, Lora A.; Ihde, Thomas F.; Lacher, Lara; Li, Li; Linker, Lewis C.; Miller, Andrew; Moriarty, Julia; Noe, Gregory B.; Onyullo, George E.; Rose, Kenneth; Skalak, Katie; Tian, Richard; Veith, Tamie L.; Wainger, Lisa A.; Weller, Donald; Zhang, Yinglong Joseph (2021-09-15)
    The Chesapeake Bay is the largest, most productive, and most biologically diverse estuary in the continental United States providing crucial habitat and natural resources for culturally and economically important species. Pressures from human population growth and associated development and agricultural intensification have led to excessive nutrient and sediment inputs entering the Bay, negatively affecting the health of the Bay ecosystem and the economic services it provides. The Chesapeake Bay Program (CBP) is a unique program formally created in 1983 as a multi-stakeholder partnership to guide and foster restoration of the Chesapeake Bay and its watershed. Since its inception, the CBP Partnership has been developing, updating, and applying a complex linked modeling system of watershed, airshed, and estuary models as a planning tool to inform strategic management decisions and Bay restoration efforts. This paper provides a description of the 2017 CBP Modeling System and the higher trophic level models developed by the NOAA Chesapeake Bay Office, along with specific recommendations that emerged from a 2018 workshop designed to inform future model development. Recom-mendations highlight the need for simulation of watershed inputs, conditions, processes, and practices at higher resolution to provide improved information to guide local nutrient and sediment management plans. More explicit and extensive modeling of connectivity between watershed landforms and estuary sub-areas, estuarine hydrodynamics, watershed and estuarine water quality, the estuarine-watershed socioecological system, and living resources will be important to broaden and improve characterization of responses to targeted nutrient and sediment load reductions. Finally, the value and importance of maintaining effective collaborations among jurisdictional managers, scientists, modelers, support staff, and stakeholder communities is emphasized. An open collaborative and transparent process has been a key element of successes to date and is vitally important as the CBP Partnership moves forward with modeling system improvements that help stakeholders evolve new knowledge, improve management strategies, and better communicate outcomes.
  • Thumbnail Image
    Comprehensive Assessment of Artificial Intelligence Tools for Driver Monitoring and Analyzing Safety Critical Events in Vehicles
    Yang, Guangwei; Ridgeway, Christie; Miller, Andrew; Sarkar, Abhijit (MDPI, 2024-04-12)
    Human factors are a primary cause of vehicle accidents. Driver monitoring systems, utilizing a range of sensors and techniques, offer an effective method to monitor and alert drivers to minimize driver error and reduce risky driving behaviors, thus helping to avoid Safety Critical Events (SCEs) and enhance overall driving safety. Artificial Intelligence (AI) tools, in particular, have been widely investigated to improve the efficiency and accuracy of driver monitoring or analysis of SCEs. To better understand the state-of-the-art practices and potential directions for AI tools in this domain, this work is an inaugural attempt to consolidate AI-related tools from academic and industry perspectives. We include an extensive review of AI models and sensors used in driver gaze analysis, driver state monitoring, and analyzing SCEs. Furthermore, researchers identified essential AI tools, both in academia and industry, utilized for camera-based driver monitoring and SCE analysis, in the market. Recommendations for future research directions are presented based on the identified tools and the discrepancies between academia and industry in previous studies. This effort provides a valuable resource for researchers and practitioners seeking a deeper understanding of leveraging AI tools to minimize driver errors, avoid SCEs, and increase driving safety.
  • Thumbnail Image
    Do Maryland's Stormwater Management Regulations Protect Channel Stability?
    Thompson, Theresa M.; Sample, David J.; Al-Samdi, Mohammad; Towsif Khan, Sami; Shahed Behrouz, Mina; Miller, Andrew; Butcher, Jon (2024-06-20)
    Webinar for the Maryland Stream Restoration Association. 84 participants
  • Thumbnail Image
    Effectiveness of environmental site design in protecting stream channel stability
    Thompson, Theresa M.; Sample, David J.; Al-Smadi, Mohammad; Towsif Khan, Sami; Shahed Behrouz, Mina; Miller, Andrew (2023-05-08)
  • Thumbnail Image
    Effectiveness of stormwater management practices in protecting stream channel stability
    Thompson, Theresa M.; Sample, David J.; Al-Smadi, Mohammad; Towsif Khan, Sami; Shahed Behrouz, Mina; Miller, Andrew (2024-06-11)
    Presentation made as part of the Stream Restoration Webinar Series: Finding Common Ground. Webinar had 284 participants.
  • Thumbnail Image
    Effectiveness of stormwater management practices in protecting stream channel stability
    Alsmadi, Mohammad; Sample, David J.; Thompson, Theresa M.; Miller, Andrew (2021-06-16)
    Hypotheses
    1. Channel instability in Minebank Run is caused by high shear stresses generated during even relatively frequent storm events.
    2. Retrofitting the Minebank Run watershed with additional watershed stormwater controls will reduce channel incision and bank failure (will compare environmental site design (ESD) only, traditional downstream controls only, and combination of both).
    3. Had Minebank Run been developed with ESD channel incision and degradation would have 1) been prevented, or 2) been reduced.
    4. Current channel degradation in tributaries to Little Seneca Creek are the result of recent large magnitude storm events, which are typically not well controlled by ESD.
    5. Had the Clarksburg watershed been developed using traditional stormwater control measures (SCMs), more extensive channel degradation would have occurred.
    6. A combination of ESD controlling small storms and SCMs controlling larger events is necessary to protect stream channels against erosion.
  • Thumbnail Image
    Evaluation of an In-vehicle Monitoring System Among an Oil and Gas Well Servicing Fleet
    Krum, Andrew; Miller, Andrew; Soccolich, Susan A. (National Surface Transportation Safety Center for Excellence, 2020-05-01)
    A pilot study of an in-vehicle monitoring system (IVMS) was conducted among a fleet of oil and gas well servicing vehicles. Data collected from the fleet were handled anonymously across 21 IVMS-instrumented light vehicle pickup trucks. Data were also collected on a sample of four participating drivers, one manager and three site workers, whose vehicles were instrumented with an IVMS and a miniature data acquisition system (MiniDAS). Among the 21 IVMS-instrumented trucks, there was a 60% reduction in speeding events and a 50% reduction in aggressive driving events. Questionnaires on the IVMS showed that drivers remained neutral to positive after the study was completed and rated the functionality of the IVMS positively. Analysis of the driving patterns of the four participants with MiniDAS-equipped vehicles showed long hours (average daily on-duty and commute time of 15.4 hours for the three site workers) and significant driving time on unimproved roads, which offer their own sets of hazards distinct from highway driving.
  • Thumbnail Image
    Examining the Effects of Horizontal Conflict in Regulatory Fit Theory in the Context of Performance Feedback
    Miller, Andrew (Virginia Tech, 2013-12-11)
    This study extends Regulatory Fit Theory (Higgins, 2000) to examine horizontal regulatory fit (Scholer & Higgins, 2010) in the context of performance feedback. Participants completed the Regulatory Focus Questionnaire (Higgins et al., 2001) to measure their chronic motivational orientation, then worked on an adapted version of an in-basket task (Holmes & Hauenstein, 2012) across two sessions. Hypotheses predicted that compared to instances of non-fit, conditions of regulatory fit between chronic and situational and motivational orientations (Promotion vs. Prevention) would have a significantly greater impact on the following three outcomes: 1) Variety and Frequency of Feedback Use, 2) Feedback Recall, and 3) Attitudes toward both Feedback and the In-basket Task. Overall results supported this assertion. Participants in condition of regulatory fit engaged in a significantly greater variety of behaviors and did so more frequently than those in non-fit conditions. Additionally, participants in regulatory fit conditions had stronger positive attitudes toward feedback than those in non-fit conditions. Counter to previous research, regulatory fit did not have significant impact on feedback recall in the current study, nor did regulatory fit have a significant impact on the attitudes toward in-basket task.
  • Thumbnail Image
    Unravelling the Complexity of Irregular Shiftwork, Fatigue and Sleep Health for Commercial Drivers and the Associated Implications for Roadway Safety
    Mabry, J. Erin; Camden, Matthew C.; Miller, Andrew; Sarkar, Abhijit; Manke, Aditi; Ridgeway, Christiana; Iridiastadi, Hardianto; Crowder, Tarah; Islam, Mouyid; Soccolich, Susan A.; Hanowski, Richard J. (MDPI, 2022-11-10)
    Fatigue can be a significant problem for commercial motor vehicle (CMV) drivers. The lifestyle of a long-haul CMV driver may include long and irregular work hours, inconsistent sleep schedules, poor eating and exercise habits, and mental and physical stress, all contributors to fatigue. Shiftwork is associated with lacking, restricted, and poor-quality sleep and variations in circadian rhythms, all shown to negatively affect driving performance through impaired in judgment and coordination, longer reaction times, and cognitive impairment. Overweight and obesity may be as high as 90% in CMV drivers, and are associated with prevalent comorbidities, including obstructive sleep apnea, hypertension, and cardiovascular and metabolic disorders. As cognitive and motor processing declines with fatigue, driver performance decreases, and the risk of errors, near crashes, and crashes increases. Tools and assessments to determine and quantify the nature, severity, and impact of fatigue and sleep disorders across a variety of environments and populations have been developed and should be critically examined before being employed with CMV drivers. Strategies to mitigate fatigue in CMV operations include addressing the numerous personal, health, and work factors contributing to fatigue and sleepiness. Further research is needed across these areas to better understand implications for roadway safety.