Scholarly Works, Virginia Tech Transportation Institute

Permanent URI for this collection

https://hdl.handle.net/10919/89575

Browse

Now showing 1 - 20 of 87

On-Road Evaluation of an Unobtrusive In-Vehicle Pressure-Based Driver Respiration Monitoring System
Jain, Sparsh; Perez, Miguel A. (MDPI, 2025-04-26)
In-vehicle physiological sensing is emerging as a vital approach to enhancing driver monitoring and overall automotive safety. This pilot study explores the feasibility of a pressure-based system, repurposing commonplace occupant classification electronics to capture respiration signals during real-world driving. Data were collected from a driver-seat-embedded, fluid-filled pressure bladder sensor during normal on-road driving. The sensor output was processed using simple filtering techniques to isolate low-amplitude respiratory signals from substantial background noise and motion artifacts. The experimental results indicate that the system reliably detects the respiration rate despite the dynamic environment, achieving a mean absolute error of 1.5 breaths per minute with a standard deviation of 1.87 breaths per minute (9.2% of the mean true respiration rate), thereby bridging the gap between controlled laboratory tests and real-world automotive deployment. These findings support the potential integration of unobtrusive physiological monitoring into driver state monitoring systems, which can aid in the early detection of fatigue and impairment, enhance post-crash triage through timely vital sign transmission, and extend to monitoring other vehicle occupants. This study contributes to the development of robust and cost-effective in-cabin sensor systems that have the potential to improve road safety and health monitoring in automotive settings.
Machine Learning–Based Prediction and Optimization of Balanced Mixture Design Performance Indices
Tong, Bilin; Huang, Wenjiang; Habbouche, Jhony; Boz, Ilker; Guo, Qing; Diefenderfer, Stacey D.; Flintsch, Gerardo W. (SAGE Publications, 2025-04-26)
The balanced mix design (BMD) concept is an emerging methodology that facilitates the design of engineered asphalt mixtures. This approach is particularly beneficial for mixtures containing conventional and high reclaimed asphalt pavement, for which the traditional volumetric design methods may fail to effectively address the performance characteristics. However, given production variability, these engineered mixtures can still fail to meet the required thresholds. Additionally, identifying the cause of this imbalance is challenging. To maximize the benefits of BMD implementation, this study introduces machine learning (ML) algorithms including linear regression (LR), random forest (RF), extreme gradient boosting (XGB), and support vector regression (SVR) as strategic tools to predict mixtures’ BMD performance indices. 648 specimens fabricated for quality acceptance as part of the 2020 Virginia Accelerated Pavement Testing Program is used for the modeling and analysis. The durability, cracking, and rutting susceptibility of the specimens were evaluated using the Cantabro test, the indirect tensile cracking test (IDT-CT), and the asphalt pavement analyzer (APA) rut test. Key outcomes include: a) ML models, including RF, XGB, and SVR, demonstrated superior performance compared with LR; b) feature importance analysis from ML models identified dominant factors for each BMD test, also highlighting the reheating process; and c) a pseudo in situ deployment was simulated to optimize BMD implementation. The dimensionality reduction analysis—uniform manifold approximation and projection—highlighted the practical challenges associated with concurrently improving multiple performance metrics. Ultimately, the pivotal role of ML in advancing both the design and production phases was emphasized.
ShipNetSim: An Open-Source Simulator for Real-Time Energy Consumption and Emission Analysis in Large-Scale Maritime Networks
Aredah, Ahmed; Rakha, Hesham A. (MDPI, 2025-03-08)
The imperative of decarbonization in maritime shipping is underscored by the sector’s sizeable contribution to worldwide greenhouse gas emissions. ShipNetSim, an open-source multi-ship simulator created in this study, combines state-of-the-art hydrodynamic modeling, dynamic ship-following techniques, real-time environmental data, and cybersecurity threat simulation to quantify and evaluate marine fuel consumption and CO₂ emissions. ShipNetSim uses well-validated approaches, such as the Holtrop resistance and B-Series propeller analysis with a ship-following model inspired by traffic flow theory, augmented with a novel module simulating cyber threats (e.g., GPS spoofing) to evaluate operational efficiency and resilience. In a case study simulation of the journey of an S175 container vessel from Savannah to Algeciras, the simulator estimated the total fuel consumption to be 478 tons of heavy fuel oil and approximately 1495 tons of CO₂ emissions for a trip of 7 days and 15 h within 13.1% of reported operational estimates. A twelve-month sensitivity analysis revealed a marginal 1.5% range of fuel consumption variation, demonstrating limiting variability for different environmental conditions. ShipNetSim not only yields realistic predictions of energy consumption and emissions but is also demonstrated to be a credible framework for the evaluation of operational scenarios—including speed adjustment, optimized routing, and alternative fuel strategies—that directly contribute to reducing the marine carbon footprint. This capability supports industry stakeholders and policymakers in achieving compliance with global decarbonization targets, such as those established by the International Maritime Organization (IMO).
Motor vehicle traffic fatalities by race and ethnicity (2010 – 2021)
Chavez Orellana, Jacqueline; Witcher, Christina; Perez, Miguel (Elsevier, 2024-07-08)
Motor vehicle traffic fatalities (MVTFs) are a public health issue that substantially affects the growing Black or African American, Indigenous, and People of Color (BIPOC) population. To further understand the racial discrepancies that exist in MVTFs, data from the Fatality Analysis Reporting System (FARS) and U.S. Census were utilized to explore factors such as rurality, urbanicity, restraint use, and alcohol-impairment. Calculations considered yearly driver and occupant fatality rates per 100,000 population for each race and ethnicity from 2010 through 2021. A Poisson regression model was used to quantify the relationship between the MVTF rates and the factors of interest. Results demonstrated that the American Indian or Alaska Native population was statistically the most overrepresented group in fatality rates across all factors explored. Additionally, the American Indian or Alaska Native population and Black or African American populations were the only groups to have statistically significant increases in fatality rates in recent years when accounting for factors such as unrestrained vehicle driver/occupants and alcohol-impaired fatality rate. In contrast, the Native Hawaiian or Pacific Islander population has consistently experienced one of the largest statistically significant reductions in driver and occupant fatality rates over time. Further analysis is necessary to develop and implement countermeasures that may reduce the increasing fatality rates of the most vulnerable populations while continuing to decrease rates for others as well. Despite limitations of FARS and population data, these results provide a pathway to reducing MVTFs and associated racial inequities that exist in the nation, particularly as the BIPOC population continues to grow.
Simple Energy Model for Hydrogen Fuel Cell Vehicles: Model Development and Testing
Ahn, Kyoungho; Rakha, Hesham A. (MDPI, 2024-12-18)
Hydrogen fuel cell vehicles (HFCVs) are a promising technology for reducing vehicle emissions and improving energy efficiency. Due to the ongoing evolution of this technology, there is limited comprehensive research and documentation regarding the energy modeling of HFCVs. To address this gap, the paper develops a simple HFCV energy consumption model using new fuel cell efficiency estimation methods. Our HFCV energy model leverages real-time vehicle speed, acceleration, and roadway grade data to determine instantaneous power exertion for the computation of hydrogen fuel consumption, battery energy usage, and overall energy consumption. The results suggest that the model’s forecasts align well with real-world data, demonstrating average error rates of 0.0% and −0.1% for fuel cell energy and total energy consumption across all four cycles. However, it is observed that the error rate for the UDDS drive cycle can be as high as 13.1%. Moreover, the study confirms the reliability of the proposed model through validation with independent data. The findings indicate that the model precisely predicts energy consumption, with an error rate of 6.7% for fuel cell estimation and 0.2% for total energy estimation compared to empirical data. Furthermore, the model is compared to FASTSim, which was developed by the National Renewable Energy Laboratory (NREL), and the difference between the two models is found to be around 2.5%. Additionally, instantaneous battery state of charge (SOC) predictions from the model closely match observed instantaneous SOC measurements, highlighting the model’s effectiveness in estimating real-time changes in the battery SOC. The study investigates the energy impact of various intersection controls to assess the applicability of the proposed energy model. The proposed HFCV energy model offers a practical, versatile alternative, leveraging simplicity without compromising accuracy. Its simplified structure reduces computational requirements, making it ideal for real-time applications, smartphone apps, in-vehicle systems, and transportation simulation tools, while maintaining accuracy and addressing limitations of more complex models.
Assessment of the Production Variability and Composite Performance Index for Conventional and High Reclaimed Asphalt Pavement Balanced Mix Design Mixtures
Tong, Bilin; Habbouche, Jhony; Diefenderfer, Stacey D.; Flintsch, Gerardo W.; Boz, Ilker (Sage, 2024-11-08)
The balanced mix design (BMD) concept enables the design of engineered mixtures containing conventional and high reclaimed asphalt pavement (HRAP) contents, moving beyond the constraints of traditional volumetric design methodologies. During production, the designed mixture undergoes verification and potential modifications at the plant to accommodate actual production and field circumstances, regardless of the mix design method. This study assessed the impact of production and associated performance variability on a volumetrically designed control mixture and five mixtures designed with the BMD concept. This investigation showed relatively precise gradation control, but exceedances of volumetric property tolerances were observed in BMD-optimized mixtures during production. Performance, including durability, cracking, and rutting susceptibility, was evaluated using the Cantabro test, indirect tensile cracking test (IDT-CT), and asphalt pavement analyzer (APA) test, respectively. Test results uncovered that produced mixtures may become unbalanced. Observations from the Cantabro test and IDT-CT highlighted the necessity and effectiveness of employing the BMD for HRAP mixtures. The potential aging effect introduced during the reheating process may compromise durability and cracking resistance. In addition, a three-dimensional plot with a revised composite performance index (CPIR) was used to optimize the process of evaluating the mixture “balance” status among multiple primary performances. It revealed that almost all produced HRAP mixtures demonstrated a well-balanced status. Finally, agencies can use the CPIR as part of their acceptance program for BMD mixtures to determine a pay factor for possible bonuses or penalties.
Multi-level performance evaluation of BMD surface mixtures with conventional and high RAP contents: a case study in Virginia
Tong, Bilin; Habbouche, Jhony; Diefenderfer, Stacey D.; Flintsch, Gerardo W. (Taylor & Francis, 2024-03-07)
This study investigated one control and five Balanced Mix Design (BMD) optimised asphalt surface mixtures, four of which had high reclaimed asphalt pavement (RAP) contents (HRAP mixtures), using laboratory performance tests characterised with different levels of complexity. The performance of the evaluated mixtures was assessed based on durability, rutting resistance, and cracking resistance as emphasized by BMD. The study explored the ranking of a single index and correlations among various indices. Assisted by 3-Dimensional and ternary plots, this study also proposed a novel composite performance index [CPI] that combines major indices (durability, cracking, and rutting) to evaluate the performance of BMD optimised mixtures. The results revealed discrepancies between basic/intermediate performance test results and advanced performance test results. The comparisons conducted also underscored the beneficial impacts derived from using softer binders and/or recycling agents in HRAP mixtures. Furthermore, the findings indicated that the BMD approach can serve as an effective framework for designing asphalt mixtures that simultaneously enhance both fatigue and rutting performance. Moreover, the study revealed HRAP BMD surface mixtures can exhibit superior overall performance when compared to conventionally designed control mixtures.
Electric versus Gasoline Vehicle Particulate Matter and Greenhouse Gas Emissions: Large-scale Analysis
Rakha, Hesham A.; Farag, Mohamed; Foroutan, Hosein (2024-07-31)
This study addresses the contentious issue of non-exhaust particulate matter (PM) emissions from battery electric vehicles (BEVs) compared to internal combustion engine vehicles (ICEVs) by developing models to quantify tire and brake PM emissions and incorporate them in a microscopic traffic simulation environment. Furthermore, exhaust greenhouse gas (GHG) emissions are quantified to develop a comprehensive picture of vehicle network emissions. The key findings are: 1) BEVs emit more tire and less brake PM emissions, thus necessitating a comprehensive analysis to avoid erroneous conclusions. 2) If at least 15% of travel is city driving, BEVs produce less non-exhaust PM emissions. 3) For the freeway section analyzed, a volume-to-capacity ratio of at least 0.25 is required for BEVs to produce less non-exhaust PM emissions. By incorporating these detailed models into traffic simulations, the study provides a tool for policymakers to better understand and manage vehicle emissions at a city level.
Field Study of Asphalt Pavement Texture and Skid Resistance under Traffic Polishing Using 0.01 mm 3D Images
Yang, Guangwei; Chen, Kuan-Ting; Wang, Kelvin; Li, Joshua; Zou, Yiwen (MDPI, 2024-07-17)
Pavement texture and skid resistance are pivotal surface features of roadway to traffic safety, especially under wet weather. Engineering interventions should be scheduled periodically to restore these features as they deteriorate over time under traffic polishing. While many studies have investigated the effects of traffic polishing on pavement texture and skid resistance through laboratory experiments, the absence of real-world traffic and environmental factors in these studies may limit the generalization of their findings. This study addresses this research gap by conducting a comprehensive field study of pavement texture and skid resistance under traffic polishing in the real world. A total of thirty pairs of pavement texture and friction data were systematically collected from three distinct locations with different levels of traffic polishing (middle, right wheel path, and edge) along an asphalt pavement in Oklahoma, USA. Data acquisition utilized a laser imaging device to reconstruct 0.01 mm 3D images to characterize pavement texture and a Dynamic Friction Tester to evaluate pavement friction at different speeds. Twenty 3D areal parameters were calculated on whole images, macrotexture images, and microtexture images to investigate the effects of traffic polishing on pavement texture from different perspectives. Then, texture parameters and testing speeds were combined to develop friction prediction models via linear and nonlinear methodologies. The results indicate that Random Forest models with identified inputs achieved excellent performance for non-contact friction evaluation. Last, the friction decrease rate was discussed to estimate the timing of future maintenance to restore skid resistance. This study provides more insights into how engineers should plan maintenance to restore pavement texture and friction considering real-world traffic polishing.
Comprehensive Assessment of Artificial Intelligence Tools for Driver Monitoring and Analyzing Safety Critical Events in Vehicles
Yang, Guangwei; Ridgeway, Christie; Miller, Andrew M.; 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.
Human-Centric Lighting Design: A Framework for Supporting Healthy Circadian Rhythm Grounded in Established Knowledge in Interior Spaces
Jalali, Mansoureh Sadat; Jones, James R.; Tural, Elif; Gibbons, Ronald B. (MDPI, 2024-04-17)
Over the past 300 years, scientific observations have revealed the significant influence of circadian rhythms on various human functions, including sleep, digestion, and immune system regulation. Access to natural daylight is crucial for maintaining these rhythms, but modern lifestyles often limit its availability. Despite its importance, there is a lack of a comprehensive design framework to assist designers. This study proposes an architectural design framework based on the review of literature, lighting-related codes and standards, and available design and analysis tools that guides the creation of lighting systems supporting healthy circadian rhythms. The framework outlines key decision-making stages, incorporates relevant knowledge, and promotes the integration of dynamic lighting techniques into building design. The proposed framework was presented to a group of design professionals as a focus group and their feedback on the relevance and usability of the tool was obtained through a survey (n = 10). By empowering designers with practical tools and processes, this research bridges the gap between scientific understanding and design implementation, ensuring informed decisions that positively impact human health. This research contributes to the ongoing pursuit of creating lighting environments that support healthy circadian rhythms and promote human well-being.
An Econometric Analysis to Explore the Temporal Variability of the Factors Affecting Crash Severity Due to COVID-19
Alrumaidhi, Mubarak; Rakha, Hesham A. (MDPI, 2024-02-01)
This study utilizes multilevel ordinal logistic regression (M-OLR), an approach that accounts for spatial heterogeneity, to assess the dynamics of crash severity in Virginia, USA, over the years 2018 to 2023. This period was notably influenced by the COVID-19 pandemic and its associated stay-at-home orders, which significantly altered traffic behaviors and crash severity patterns. This study aims to evaluate the pandemic’s impact on crash severity and examine the consequent changes in driver behaviors. Despite a reduction in total crashes, a worrying increase in the proportion of severe injuries is observed, suggesting that less congested roads during the pandemic led to riskier driving behaviors, notably increased speed violations. This research also highlights heightened risks for vulnerable road users such as pedestrians, cyclists, and motorcyclists, with changes in transportation habits during the pandemic leading to more severe crashes involving these groups. Additionally, this study emphasizes the consistent influence of environmental and roadway features, like weather conditions and traffic signals, in determining crash outcomes. These findings offer vital insights for road safety policymakers and urban planners, indicating the necessity of adaptive road safety strategies in response to changing societal norms and behaviors. The research underscores the critical role of individual behaviors and mental states in traffic safety management and advocates for holistic approaches to ensure road safety in a rapidly evolving post-pandemic landscape.
Impacts of Vehicle-to-Everything Enabled Applications: Literature Review of Existing Studies
Du, Jianhe; Ahn, Kyoungho; Farag, Mohamed; Rakha, Hesham A. (Universal Wiser Publisher, 2023-03-10)
As communication technology is developing at a rapid pace, connected vehicles (CVs) can potentially enhance vehicle safety while reducing vehicle energy consumption and emissions via data sharing. Many researchers have attempted to quantify the impacts of such CV applications and vehicle-to-everything (V2X) communication, or the instant and accurate communication among vehicles, devices, pedestrians, infrastructure, network, cloud, and grid. Cellular V2X (C-V2X) has gained interest as an efficient method for this data sharing. In releases 14 and 15, C-V2X uses 4G LTE technology, and in release 16, it uses the latest 5G new radio (NR) technology. Among its benefits, C-V2X can function even with no network infrastructure coverage; in addition, C-V2X surpasses older technologies in terms of communication range, latency, and data rates. Highly efficient information interchange in a CV environment can provide timely data to enhance the transportation system's capacity, and it can support applications that improve vehicle safety and minimize negative impacts on the environment. Achieving the full benefits of CVs requires rigorous investigation into the effectiveness, strengths, and weaknesses of different CV applications. It also calls for deeper understanding of the communication protocols, results with different CV market penetration rates (MPRs), CV- and human-driven vehicle interactions, integration of multiple applications, and errors and latencies associated with data communication. This paper includes a review of existing literature on the safety, mobility, and environmental impacts of CV applications; gaps in current CV research; and recommended directions for future research. The results of this paper will help shape future research for CV applications to realize their full potential.
Rutting Performance Evaluation of BMD Surface Mixtures with Conventional and High RAP Contents under Full-Scale Accelerated Testing
Tong, Bilin; Habbouche, Jhony; Flintsch, Gerardo W.; Diefenderfer, Brian K. (MDPI, 2023-12-12)
The balanced mix design (BMD) constitutes a significant step forward in the pursuit of better-performing asphalt mixtures. This approach/framework offers increased innovative opportunities for the proper design and production of engineered asphalt mixtures without the need to strictly adhere to traditional volumetric requirements. The primary objective of this paper is to conduct a comprehensive investigation of the permanent deformation (rutting) behavior of surface mixtures (SMs) with conventional and high reclaimed asphalt pavement (HRAP) contents through full-scale accelerated testing under incremental loading conditions while accounting for the environmental aging effect. HRAP SMs were designed in this study, marking the initial application of Virginia Department of Transportation (VDOT) BMD special provisions, with attempts to incorporate 45% and even 60% RAP. Results showed that all BMD HRAP mixtures exhibited higher rut depths compared to the control mixture, which can be attributed to the inclusion of high binder contents aimed at enhancing cracking resistance. The asphalt pavement analyzer (APA) rut test and the stress sweep rutting tests were performed on mixtures sampled during production. Correlation analysis revealed significant and strong positive correlations between accelerated pavement testing (APT) and the multilevel laboratory rutting performance tests considered in this study. Finally, while acknowledging the limitations and all the assumptions considered in this study, the correlation analysis recommended refining the VDOT BMD APA rut depth threshold by lowering the current limit of 8 mm to 7 mm to ensure good performing mixtures from a rutting point of view.
The Impact of Line-of-Sight and Connected Vehicle Technology on Mitigating and Preventing Crash and Near-Crash Events
Herbers, Eileen; Doerzaph, Zachary; Stowe, Loren (MDPI, 2024-01-12)
Line-of-sight (LOS) sensors developed in newer vehicles have the potential to help avoid crash and near-crash scenarios with advanced driving-assistance systems; furthermore, connected vehicle technologies (CVT) also have a promising role in advancing vehicle safety. This study used crash and near-crash events from the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP2 NDS) to reconstruct crash events so that the applicable benefit of sensors in LOS systems and CVT can be compared. The benefits of CVT over LOS systems include additional reaction time before a predicted crash, as well as a lower deceleration value needed to prevent a crash. This work acts as a baseline effort to determine the potential safety benefits of CVT-enabled systems over LOS sensors alone.
Exploratory Development of Algorithms for Determining Driver Attention Status
Herbers, Eileen; Miller, Marty; Neurauter, Luke; Walters, Jacob; Glaser, Daniel (SAGE, 2023-09)
Objective: Varying driver distraction algorithms were developed using vehicle kinematics and driver gaze data obtained from a camera-based driver monitoring system (DMS). Background: Distracted driving characteristics can be difficult to accurately detect due to wide variation in driver behavior across driving environments. The growing availability of information about drivers and their involvement in the driving task increases the opportunity for accurately recognizing attention state. Method: A baseline for driver distraction levels was developed using a video feed of 24 separate drivers in varying naturalistic driving conditions. This initial assessment was used to develop four buffer-based algorithms that aimed to determine a driver's real-time attentiveness, via a variety of metrics and combinations thereof. Results: Of those tested, the optimal algorithm included ungrouped glance locations and speed. Notably, as an algorithm's performance of detecting very distracted drivers improved, its accuracy for correctly identifying attentive drivers decreased. Conclusion: At a minimum, drivers' gaze position and vehicle speed should be included when designing driver distraction algorithms to delineate between glance patterns observed at high and low speeds. Distraction algorithms should be designed with an understanding of their limitations, including instances in which they may fail to detect distracted drivers, or falsely notify attentive drivers. Application: This research adds to the body of knowledge related to driver distraction and contributes to available methods to potentially address and reduce occurrences. Machine learning algorithms can build on the data elements discussed to increase distraction detection accuracy using robust artificial intelligence.
WIP: The Feasibility of High-performance Message Authentication in Automotive Ethernet Networks
Allen, Evan; Bowden, Zeb; Marchany, Randy; Ransbottom, J. Scot (2023-02-27)
Modern vehicles are increasingly connected systems that expose a wide variety of security risks to their users. Message authentication prevents entire classes of these attacks, such as message spoofing and electronic control unit impersonation, but current in-vehicle networks do not include message authentication features. Latency and throughput requirements for vehicle traffic can be very stringent (<0.1 ms and >100 Mbps in cases), making it difficult to implement message authentication with cryptography due to the overheads required. This work investigates the feasibility of implementing cryptography-based message authentication in Automotive Ethernet networks that is fast enough to comply with these performance requirements. We find that it is infeasible to include Message Authentication Codes in all traffic without costly hardware accelerators and propose alternate approaches for future research.
What factors contribute to e-scooter crashes: A first look using a naturalistic riding approach
White, Elizabeth; Guo, Feng; Han, Shu; Mollenhauer, Michael A.; Broaddus, Andrea; Sweeney, Ted; Robinson, Sarah; Novotny, Adam; Buehler, Ralph (Elsevier, 2023-06)
Introduction: Shared dockless electric scooters (e-scooters) are a popular shared mobility service providing an accessible last-mile transportation option in urban and campus environments. However, city and campus stakeholders may hesitate to introduce these scooters due to safety concerns. While prior e-scooter safety studies have collected injury data from hospitals or riding data under controlled or naturalistic conditions, these datasets are limited and did not identify risk factors associated with e-scooter riding safety. To address this gap in e-scooter safety research, this study collected the largest naturalistic e-scooter dataset to date and quantified the safety risks associated with behavioral, infrastructure, and environmental factors. Method: A fleet of 200 e-scooters was deployed on Virginia Tech’s campus in Blacksburg, VA for a 6-month period. Fifty were equipped with a unique onboard data acquisition system, using sensors and video to capture e-scooter trips in their entirety. The resulting dataset consisted of 3,500 hours of data spanning over 8,500 trips. Algorithms were developed to identify safety critical events (SCEs) in the dataset and analyses were conducted to determine the prevalence of various SCE risk factors and associated odds ratios. Results: Results from this study indicate that infrastructure-related factors, behavior of e-scooter riders and other actors, and environmental factors all contributed to the SCE risk for e-scooter riders in Virginia Tech’s pedestrian-dense campus environment. Conclusions: To help mitigate unsafe rider behavior, educational outreach programs should quantify the significant risks associated with infrastructure, behavioral, and environmental risk factors and provide clear recommendations to riders. Improved infrastructure maintenance and design may also improve safety for e-scooter riders. Practical Applications: The infrastructure, behavioral, and environmental risk factors quantified in this study can be applied by e-scooter service providers, municipalities, and campus administrators to develop mitigation strategies to reduce the safety risks associated with e-scooter deployments in the future.
Comparative Analysis of Parametric and Non-Parametric Data-Driven Models to Predict Road Crash Severity among Elderly Drivers Using Synthetic Resampling Techniques
Alrumaidhi, Mubarak; Farag, Mohamed M. G.; Rakha, Hesham A. (MDPI, 2023-06-21)
As the global elderly population continues to rise, the risk of severe crashes among elderly drivers has become a pressing concern. This study presents a comprehensive examination of crash severity among this demographic, employing machine learning models and data gathered from Virginia, United States of America, between 2014 and 2021. The analysis integrates parametric models, namely logistic regression and linear discriminant analysis (LDA), as well as non-parametric models like random forest (RF) and extreme gradient boosting (XGBoost). Central to this study is the application of resampling techniques, specifically, random over-sampling examples (ROSE) and the synthetic minority over-sampling technique (SMOTE), to address the dataset’s inherent imbalance and enhance the models’ predictive performance. Our findings reveal that the inclusion of these resampling techniques significantly improves the predictive power of parametric models, notably increasing the true positive rate for severe crash prediction from 6% to 60% and boosting the geometric mean from 25% to 69% in logistic regression. Likewise, employing SMOTE resulted in a notable improvement in the non-parametric models’ performance, leading to a true positive rate increase from 8% to 36% in XGBoost. Moreover, the study established the superiority of parametric models over non-parametric counterparts when balanced resampling techniques are utilized. Beyond predictive modeling, the study delves into the effects of various contributing factors on crash severity, enhancing the understanding of how these factors influence elderly road safety. Ultimately, these findings underscore the immense potential of machine learning models in analyzing complex crash data, pinpointing factors that heighten crash severity, and informing targeted interventions to mitigate the risks of elderly driving.
Infrastructure-Based Performance Evaluation for Low-Speed Automated Vehicle (LSAV)
Klauer, Charlie; Hong, Yubin; Mollenhauer, Michael A.; Vilela, Jean Paul Talledo (MDPI, 2023-05-05)
This study assessed the limitations of the EasyMile EZ10 Gen 3 low-speed automated vehicle (LSAV) while operating on public roadways. The primary interest was to evaluate the infrastructure elements that posed the greatest challenges for the LSAV. A route was chosen that would satisfy a legitimate transit need. This route included more operational complexity and higher traffic volumes than a typical EasyMile LSAV deployment. The results indicate that the LSAV operated at a lower-than-expected speed (6 to 8 mph), with a high frequency of disengagements, and a regular need for safety operator intervention. Four-way stop-sign controlled intersections, three-lane roads with a shared turning lane in the middle, open areas, and areas without clear markings were the most challenging for the LSAV. Some important considerations include the need to have LSAVs operate on roadways where other vehicles may pass more safely, or on streets with slower posted speed limits. Additionally, the low passenger capacity and inability to understand where passengers are located onboard make it hard for the LSAV to replace bus transits. Currently, the LSAV is best suited to provide first/last-mile services, short routes within a controlled access area, and fill in gaps in conventional transits.

Browse

Recent Submissions