Driver Risk Research Articles

Dual-V-Sense-Net (DVN): Multisensor Recommendation Engine for Distraction Analysis and Chaotic Driving Conditions

The Advanced Driver Assistance System (ADAS) features provide better safe driving dynamics reducing road accidents and collisions. Typically, these include lane assist, automatic night vision, adaptive cruise control, driver risk analysis primarily seen in high-end vehicles. Furthermore, such a proactive mechanism alerts the drivers in unsafe/ dangerous situations and enable drivers to respond with immediate actions. However, such ADAS-based solutions do not work very well in heterogeneous, less-disciplined, and chaotic road traffic environments, as seen in Asian countries such as India, Bangladesh, Burma, Nepal, etc. In this regard, this paper aims to propose an advanced integrated deep learning framework <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dual-V-sense-Net (DVN)</i> to provide recommendations for safe driving. A new dataset - Behavioral Understanding of Driver’s-Distraction Dataset for India (BUDDI), is proposed for the behavioral understanding of driver’s distraction. This proposed recommendation framework is designed in a two-step manner. The first step involves an in-vehicle driver distraction analysis with real-time frontal and cross-view naturalistic driver data for driver distraction analysis. Second step is to perform an exhaustive experimental evaluation is carried out for the tasks such as road traffic scene perception, road navigable area prediction with vehicular temporal dynamics, lane assist, safe drivable area navigation and driver distraction alert. A decision block modeling helps in safe/unsafe driving predictions considering the feature importance. We present comprehensive experimental results for road segmentation, vehicular road lane categorization, obstacle recognition, and driver behavioral pattern prediction using the BUDDI and Indian Driving Dataset (IDD) datasets.

Commuter welfare-based probabilistic seismic risk assessment of regional road networks

This study integrates welfare, a measure of the impact of road network disruption on individual commuters’ well-being, with a probabilistic seismic risk assessment framework in a computationally tractable way. Welfare is a network performance measure that reflects the differential impacts of changes in commute time on various groups. For a case study of the San Francisco Bay Area, welfare loss is computed by augmenting an origin–destination matrix with publicly available information about commuters’ income levels, residences, and workplaces. While commuters from all income groups have similar risk of drivers’ delay due to road network disruption, commuters with low incomes have a substantially higher risk of welfare loss than those with high incomes. A comparison of bridge retrofit policies shows that disaggregation of welfare loss by income group is necessary to examine whether such policies reduce risk equitably. While a retrofit policy determined using drivers’ delay reduces the expected drivers’ delay, it increases the disparity in the per-capita welfare loss of commuters with low and high incomes relative to the network’s baseline state. In contrast, a retrofit policy that prioritizes low-income commuters reduces the difference in welfare loss of commuters with low and high incomes compared to the baseline network state.

Can't drive, I'm drunk – Exploring factors influencing the intention to drink and drive among Indian drivers

The crash risk of drivers increases significantly while driving under the influence of alcohol. However, the drivers' intention to drink and drive has not been explored yet in the context of a developing country like India. The present study applied an extended version of the theory of planned behaviour (TPB) to investigate the psychosocial predictors of drunk driving intentions of Indian drivers. 252 drivers participated in a self-reported survey designed for the study. Apart from the standard TPB components (attitudes, subjective norms, and perceived behavioural control), the survey also captured the extension measures such as risk perceptions, moral norms, traffic fatalism, sensation-seeking, conformity tendency, past engagement in drunk driving, crash history and driver demographics. The standard TPB model was successful in explaining 68.6% of the variance in the intention to drink and drive. The attitudes displayed the strongest influence on the intention (β = 0.696, p < 0.001), followed by perceived behavioural control (β = 0.180, p < 0.001); whereas subjective norms showed a moderate significance in influencing the intention (β = 0.062, p < 0.1). Among the extension variables, past behaviour showed the strongest influence on the intention to drink and drive (β = 0.123, p < 0.05), followed by sensation-seeking (β = 0.080, p < 0.05) and traffic fatalism (β = 0.072, p < 0.1). The extended TPB model explained 72% of the variance in the intention to drink and drive. The study findings can assist in the development of strategies/interventions to reduce drunk driving incidences.An earlier version of the paper was presented at the TRB 101st Annual Meeting, Washington, D. C., 2022.

ManGuard an eHealth intervention to reduce cardiovascular risk in male taxi drivers: a pilot randomised controlled trial protocol

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Department for the Economy, Northern Ireland Background Men are at higher risk then women of developing cardiovascular disease (CVD) and male taxi drivers are a particularly high risk group because of their typically unhealthy behaviours, such as poor eating habits, smoking and a sedentary lifestyle. However, only two studies of behavioural interventions targeting taxi drivers have been identified, one of which had a high attrition rate. Therefore, an eHealth intervention co-designed by taxi drivers may prove more user-friendly and effective. Purpose The aim of this study is to assess the feasibility of a randomised controlled trial (RCT) of an eHealth intervention – ManGuard – to reduce CVD risk in male taxi drivers. Methods A wait-list controlled trial of 30 male taxi drivers in Belfast, Northern Ireland, will be assigned randomly to an intervention or usual care group. The ManGuard Application comprises seven modules: i) introduction and goal setting, ii) being active iii) eating well, iv) managing stress, v) smoking, vi) alcohol and vii) keep accelerating, the latter to be used as a re-cap module. This trial will establish feasibility, including recruitment, engagement and retention rates, program usability and participant satisfaction, as well as preliminary efficacy of ManGuard in improving key outcomes. Primary outcome is to determine the feasibility of an eHealth intervention for reducing CVD risk in male taxi drivers by assessing the following outcome measures: o Acceptability, recruitment, retention and engagement rates o Usability and participant satisfaction, process evaluation and survey The secondary outcome is to evaluate the preliminary efficacy of ManGuard compared to usual care in improving the following outcomes: o Clinical indices: CVD biomarkers (cholesterol, glucose), blood pressure, anthropometry (BMI, waist circumference, body fat percentage) o Physical activity o Psychosocial status: health related quality of life, self-efficacy, social support An in-depth qualitative process evaluation to explore acceptability of the intervention will also be conducted. Trial registration: This trial has been registered prospectively on the ISRCTN registry on 5 January 2022 Conclusion eHealth interventions have been shown to promote behaviour change and reduce CVD risk in men, but there is a lack of robust evidence for this in male taxi drivers, a high-risk group. This study aims to assess the feasibility of a future RCT assessing the impact of ManGuard on CVD risk in male taxi drivers. This study will inform a fully-powered trial that will provide robust evidence for eHealth interventions for this underserved population.

Evaluating Large Bank Risk Using Stock Market Measures in the Basel III Period

AbstractThere is a puzzle in the literature which seems to indicate that high capital levels introduced by Basel III increase bank risk. This paper attempts to solve this puzzle by investigating whether the risk of the eight U.S. global systemically important banks (GSIBs) increased in the Basel III period from previous periods. This paper uses case studies of the eight U.S. GSIBs to evaluate whether Basel III has changed their risk perceived by the market. Basel III has reduced the systematic risk of equity of U.S. GSIBs perceived by the stock market, and it does not explain the decline in return on equity (ROE) which may indicate some increase in large bank financial risk. The paper breaks down stock market measures into drivers which capture systematic risk of equity and other drivers which capture financial risk, and it finds new evidence which solves the puzzle in the literature on large bank risk. The findings of the paper help investors, creditors and regulators to have a clear understanding of the market perception of large bank risk. The paper provides new methods and evidence which could help regulators to assess the impact of Basel III on bank risk perceived by the market.

Does hearing loss affect the risk of involvement in a motor vehicle crash?

AimThis study systematically reviewed the literature on motor vehicle crash (MVC) risk for drivers with hearing loss in medicine, psychology, and transport databases, that quantify its effect on MVC to enable licensing agencies to make evidence-based decisions on fitness-to-drive hearing standards. Results1717 articles were identified of which 563 were duplicates. Twelve studies were retained for full-text review of which four published between 1968 and 2016 were judged to have met all the selection criteria. Three studies demonstrated no significant increase in MVC risk, while one reported a decrease in risk. ConclusionsAlthough the small number of studies that met all the inclusion criteria is a limitation, the expert panel concluded that the quality of the studies permitted the conclusion that the evidence does not support a relationship between hearing impairment and the risk of an MVC. Driver fitness standards recognise this fact implicitly in that none of the national fitness-to-drive standards selected for comparison applied licence restrictions to non-commercial drivers.

How Gender Affects Motor Vehicle Crashes: A Case Study from San Antonio, Texas

Traffic crashes are among the leading causes of injuries and fatalities worldwide. The main assumption of this study is that traffic crash rates, injury severity, and driving behaviors differ by the driver’s gender. Utilizing ten years (2011–2020) of data from the Texas Crash Record and Information System database, this study investigates how some of the most prominent driving behaviors leading to crashes and severe injuries (distracted driving, speeding, lane departure, and driving under influence) vary by gender in San Antonio, Texas. The spatial distribution of crashes associated with these driving behaviors by gender is also investigated, as well as the influence of some environmental and temporal variables on crash frequency and injury severity. This study adopted bivariate analysis and logistic regression modeling to identify the effect of different variables on crash occurrence and severity by gender. Male drivers were more likely to be involved in a speeding/DUI/lane departure-related crash and subsequent severe injuries. However, female drivers were slightly more associated with distracted-driving crashes and subsequent injuries. Nighttime, interstate/highway roads, the weekend period, and divider/marked lanes as the primary traffic control significantly increased the crash and injury risk of male drivers. Driving behavior-related crashes were mostly concentrated on some interstate road segments, major intersections, and interchanges. The results from this study can be used by authorities and policy-makers to prioritize the use of limited resources, and to run more effective education campaigns to a targeted audience.

Factors of Cardiovascular Risk in Drivers of Locomotive Crews of Railway Transport with Ventricular Arrhythmias

AIM: This study aimed to assess cardiovascular risk factors in drivers and assistant drivers of railway engine crews with ventricular rhythm disorders.&#x0D; MATERIALS AND METHODS: The study included 120 patients aged 39 to 61 years (mean age M SD: 50.4 4 years), who were distributed into two groups with and without ventricular rhythm disorders. All participants underwent 12-lead daily ECG monitoring with assessment of noninvasive markers of myocardial electrical instability (circadian profile, QT interval, late ventricular potentials, T-wave alternation, rhythm variability). Traditional factors of cardiovascular risk, the employment period in the profession, and the level of personal and situational anxiety on Spielbergers state-trait anxiety inventory (STAI) were evaluated.&#x0D; RESULTS: In Group 1, in comparison with Group 2, significant differences were revealed in the duration of the PQ interval (during the day and at night) and the indicators of late ventricular potentials (RMS 40 and TotQRSF). When analyzing risk factors, elevated indices of total blood cholesterol were registered in both groups, and the risk on the SCORE scale was at a moderate level. In the group of workers with ventricular rhythm disorders, higher indicators of total blood cholesterol and the frequency of smoking and alcohol consumption were established. In individuals with ventricular rhythm disorders, a significant relationship was detected between the number of registered single monomorphic ventricular extrasystoles and the age of the employee (r = 0.3, р 0.05), and blood pressure level (r = 0.3, р 0.05), and the relationship between the level of anxiety and the registration of single supraventricular extrasystoles was established (r = 0.3, р 0.05). In the Group 2, a significant correlation was revealed between the number of registered single supraventricular extrasystoles and age (r = 0.2, р 0.05), the employment period in the profession of a driver (r = 0.2, р 0.05), the blood pressure level (r = 0.2, р 0.05), and the level of anxiety on the STAI (r = 0.3, р 0.05).&#x0D; CONCLUSIONS: Drivers of railway engine crews with ventricular rhythm disorders are characterized by a higher level of total blood cholesterol and a higher frequency of smoking and alcohol consumption. They have significant changes in the duration of the PQ interval (during the day and at night) and indicators of late ventricular potentials (RMS 40 and TotQRSF) according to Holter monitoring. The relationship of the number of ventricular rhythm disorders with age and the office values of systolic and diastolic blood pressure is noted in drivers of engine crews of railway transport.

Impact of rule-violating behaviors on the risk of bus drivers being at-fault in crashes

Objective The objectives of this study are (1) to examine the effects of different rule-violating behaviors on the risk of bus drivers being at fault in crashes, and (2) to identify the randomness and heterogeneity generated by the significant factors. Methods This study proposes a random parameter logit model based on the bus crash data obtained from the bus safety management system in Xi’an, China. The model considers crashes where bus drivers were at fault as the dependent variables and 16 factors as independent variables. These factors include a history of previous rule violations, a history of past crashes, the characteristics of the driver, the route length, and the characteristics of crashes. Results According to the results of the study, irregular behavior when entering and exiting bus stations had a significant effect on the likelihood of being at fault, as well as the driver's gender, during the probationary period, any complaints received, and reports of crashes. Moreover, the unobserved heterogeneity is determined by considering three variables, such as return trips, crashes at the intersection, and crash records of non-at-fault bus drivers. Conclusions The study results offer empirical evidence for the relationship between bus driver violations and being at fault in the crash, which has only previously been obtained through stated questionnaires. Further, we found that there was heterogeneity across cases in terms of the effect of previous crashes, meaning that following some crashes, drivers might be more cautious, while following others they may not. The findings provide additional insight into crashes and driver differences. Additionally, In light of our findings, we recommend practical measures to improve the safety management of bus companies.

Does age matter? Examining age-dependent differences in at-fault collisions after attending a refresher course for older drivers

The “Driver 65+” course is a voluntary refresher course offered to all drivers aged 65 years or older in Norway. The current study estimated differences in at-fault motor vehicle collisions (MVCs) between older drivers who had attended in the course and older drivers who had not attended the course. MethodsTwo samples of drivers were selected from the database of an insurance company and were sent a questionnaire in the mail. The first sample consisted of 2039 car owners aged 70 years or older who had reported a collision to the insurance company during the last 24 months. The second sample consisted of 1569 drivers aged 70 or older who had not reported any collisions during the last 24 months. ResultsThe results indicated an age-dependent effect; drivers attending the course before 75 years of age had a significantly lower risk of being the at-fault driver in a multi-MVC than older drivers who did not attend the course. ConclusionThe results indicate that the refresher course had a beneficial effect on collision risk for drivers who attended the course before reaching 75 years of age. One possible explanation of this age-dependent effect is that a certain level of visual, cognitive, and motor functioning is needed to implement the strategies learned in the course. However, the design of the study makes it difficult to draw definite conclusions about the causal relationship between course attendance and later collision involvement.

A Computational Model for Driver Risk Evaluation and Crash Prediction Using Contextual Data from On-board Telematics

Introduction: Vehicle crashes can be hazardous to public safety and may cause infrastructure damage. Risky driving significantly raises the possibility of the occurrence of a vehicle crash. As per statistics by the World Health Organization (WHO), approximately 1.35 million people are involved in road traffic crashes resulting in loss of life or physical disability. WHO attributes events like over-speeding, drunken driving, distracted driving, dilapidated road infrastructure and unsafe practices such as non-use of helmets and seatbelts to road traffic accidents. As these driving events negatively affect driving quality and enhance the risk of a vehicle crash, they are termed as negative driving attributes. Methods: A multi-level hierarchical fuzzy rules-based computational model has been designed to capture risky driving by a driver as a driving risk index. Data from the onboard telematics device and vehicle controller area network is used for capturing the required information in a naturalistic way during actual driving conditions. Fuzzy rules-based aggregation and inference mechanisms have been designed to alert about the possibility of a crash due to the onset of risky driving. Results: On-board telematics data of 3213 sub-trips of 19 drivers has been utilized to learn long term risky driving attributes. Furthermore, the current trip assessment of these drivers demonstrates the efficacy of the proposed model in correctly modeling the driving risk index of all of them, including 7 drivers who were involved in a crash after the monitored trip. Conclusions: In this work, risky driving behavior has been associated not just with rash driving but also other contextual data like driver’s long-term risk aptitude and environmental context such as type of roads, traffic volume and weather conditions. Trip-wise risky driving behavior of six out of seven drivers, who had met with a crash during that trip, was correctly predicted during evaluation. Similarly, for the other 12 drivers, the model accurately predicted safe driving behavior as these drivers did not meet with any vehicle crash. The proposed model can be used as an alert mechanism to indicate potential crash scenarios to the driver. The current study did not study lane changing behavior in detail due to difficulty in capturing road lanes in the Indian context.

Safe speeds: fatality and injury risks of pedestrians, cyclists, motorcyclists, and car drivers impacting the front of another passenger car as a function of closing speed and age

As crash speed increases, so does the probability of injury. The vulnerability of different road users varies greatly, in part due to differences in their protective equipment. Therefore, for the same speed, their injury probabilities are different. The objective of this study is to define injury risk curves, mathematical relations between closing speed (the relative speed between two crash partners) and injury outcome, for different road users. These risk curves can be used to rank road user vulnerability and define safe speeds, i.e. speeds not exceeding tolerable injury probabilities. Crashes involving pedestrians, cyclists, motorcyclists, and car drivers impacting the front of another passenger car (i.e. frontal impacts from the other car’s perspective) were extracted from the German in-depth accident study (GIDAS). The injuries were modelled as a function of closing speed and road user age using a weighted binary logistic regression. In accordance with the Abbreviated Injury Scale 2015 revision, three injury severities were modelled: at-least-moderate injury severities, at-least-serious injury severities, and fatal injuries. The constructed risk curves predicted injury outcomes with an average Area under the Curve ranging from 0.66 to 0.94 in cross-validation. A 10% risk of sustaining at-least-serious injuries corresponds to a closing speed of 29 km/h for pedestrians, 44 km/h for cyclists, 48 km/h for motorcyclists, and 112 km/h for car drivers. If a 10% risk of serious injury is acceptable, the closing speeds can be translated into safe speed limits of 25 km/h for cars with pedestrian encounters; 20 to 25 km/h for cyclists, motorcyclists, and cars when they encounter each other; and 55 km/h for cars in head-on impacts. These safe speeds align with current speed limits of 20 to 30 km/h in urban centers but bring into question the current practices of much higher speed limits on rural roads shared by bicycles, motorcycles, and cars. However, safe speed limits could be increased (maintaining a 10% serious injury risk) if road users have more protective equipment and Automated Emergency Braking reliably reduces impact speeds in all crash types.

Influence of shift work on cardiovascular disease risk in Southern African long-distance truck drivers: a cross-sectional study

ObjectivesCardiovascular disease (CVD) is a major problem globally. Truck drivers have an increased risk of CVD due to a sedentary lifestyle, irregular working hours and behavioural choices. We aimed to...

Safety assessment of trucks based on GPS and in-vehicle monitoring data

Increasingly, drivers are choosing to buy usage-based automobile insurance (UBI). Manage-how-you-drive (MHYD) insurance, a new type of UBI, incorporates active safety management to monitor driver behavior and issue warnings as needed. While researchers have introduced telematics data into automobile insurance pricing, the specific effect of in-vehicle active safety management on driver risk assessment has been neglected, especially for truck drivers, whose crashes have more serious consequences. This study uses telematics and in-vehicle monitoring features to examine the key factors underlying large commercial truck crashes, and quantifies the effect of these factors on crash risk. Data from 2,185 trucks in Shanghai, China, were collected for a total of 105,786 trips and 465,555 in-vehicle warnings to investigate three types of factors affecting risk: travel characteristics, driving behavior, and in-vehicle warnings. A zero-inflated Poisson (ZIP) regression model was built, and a ZIP model without the warning variables as well as a basic Poisson model with warnings were considered for comparison. It was found that the ZIP model considering in-vehicle warning information performed significantly better than the other models. The standardized regression coefficient method was used to identify the most important variables. In-vehicle yawn and smoking warnings had significantly more association with the number of crashes than did the travel characteristics and driving behavior variables, though freeway distance traveled, average freeway speed, percentage of trips on sunny days, and percentage of trips at night also correlated significantly with crash risk. These results can provide a reference for UBI insurance professionals considering in-vehicle active safety management, as well as support freight companies in drafting appropriate working regulations.

Driving risks of young drivers with symptoms of attention deficit hyperactivity disorder: association with the dopamine transporter gene VNTR polymorphism

Background Road traffic injuries are a leading cause of death for young adults, and young drivers with higher expression of symptoms of attention deficit-hyperactivity disorder (ADHD) could pose an even greater risk in traffic. Dopaminergic dysfunction has been found to occur in ADHD, with the dopamine transporter (DAT) gene VNTR polymorphism (DAT1 VNTR; rs28363170) being one of the most consistent genetic markers. Thus, we aimed at clarifying how the ADHD symptoms and the DAT1 VNTR relate to risk-taking behaviour in traffic, impulsivity and driving anger in young drivers. Method We used data of two traffic behaviour study samples (n = 741, mean age = 23.3 ± 7.2 years; n = 995, mean age = 22.9 ± 8.1 years) and the Estonian Children Personality Behaviour and Health Study (ECPBHS; traffic behaviour data n = 1,016, mean age = 25.2 ± 2.1 years). ADHD symptoms were assessed by self-report with the Adult ADHD Self-Report Scale (ASRS v1.1) and impulsivity with the Adaptive and Maladaptive Impulsivity Scale. Traffic behavioural measures were either self-reported (Driver Behaviour Questionnaire, Driving Anger Scale) or obtained from databases (registered accidents and violations). Results Drivers with more self-reported ADHD symptoms also reported more risk-taking in traffic and had more of recorded traffic accidents and violations. DAT1 9 R carriers had a higher probability of high traffic risk behaviour only if they also had ADHD symptoms. Conclusion Higher level of ADHD symptoms is a significant risk factor in traffic, and carrying of the DAT1 9 R allele appears to aggravate these risks.

Predicting individuals' car accident risk by trajectory, driving events, and geographical context

With the prevalence of GPS tracking technologiees, car insurance companies have started to adopt usage-based insurance policies, which adapt insurance premiums according to the customers' driving behavior. Although many risk models for assessing an individual driver's accident risk based on the history of driving trajectories, driving events, and exposure records exist, these models do not take the geographical context of the driven trajectories and driving events into account. This study explores the influence of enriching the existing purely driving-behavior-based feature set by multiple geographical context features for the task of differentiating between accident and accident-free drivers. Prediction performances of five machine learning classifiers—logistic regression, random forest, XGBoost, feed-forward neural networks (FFNN), and long short-term memory (LSTM) networks—were evaluated on the usage records of over 8000 vehicles in one year from Italy. The results show that the inclusion of geographical information such as weather, points of interest (POIs), and land use can increase the relative predictive performance in terms of AUC by up to 8%, among which land use is the most informative. For the data of this study, XGBoost generally yielded the best performance and made most use out of the geographical information, while logistic regression is only slightly outperformed by more complex models if the proposed geographical information is not available. LSTM did not outperform the other methods, possibly due to the small volume of training data available. The results outline the potential of including the geographical context in usage-based car insurance risk modeling to improve the accuracy, leading to fairer usage-based insurance policies.

Analysis of visual risk perception model for braking control behaviour of human drivers: A literature review

In the interest of driving safety, it is essential to understand driver risk assessment to develop human-centred automated driving systems. Visual perception plays a core role in observing, analysing, and predicting driving crash risks. Furthermore, comprehensive progress of visual perception has been achieved in the development of risk perception metrics. However, it is still of interest to understand driver control behaviours, which depend on visual perception. Therefore, the objective of this literature review is to assess the potential of coupling time-remaining cues for risk perception and braking control behaviour. First, conventional risk perception metrics are classified based on trajectory, contact, and state principles, along with new analysis metrics that have been derived from conventional ones. Then, the analysis metrics are discussed based on visual perception information. Next, driver risk assessment is summarised according to the environment, driver, and object characteristics. Moreover, braking behaviour models are compared in relation to visual perception variables, action affordances, and behaviour dynamics. The current review further discusses the possibility of applying driver behaviour modelling to perception, navigation, and spatial awareness in autonomous vehicles. This human-centred approach has the potential to improve interaction between drivers and automation.

A Framework for Building Comprehensive Driver Profiles

Conventional approaches to modelling driver risk have incorporated measures such as driver gender, age, place of residence, vehicle model, and annual miles driven. However, in the last decade, research has shown that assessing a driver’s crash risk based on these variables does not go far enough—especially as advanced technology changes today’s vehicles, as well as the role and behavior of the driver. There is growing recognition that actual driver usage patterns and driving behavior, when it can be properly captured in modelling risk, offers higher accuracy and more individually tailored projections. However, several challenges make this difficult. These challenges include accessing the right types of data, dealing with high-dimensional data, and identifying the underlying structure of the variance in driving behavior. There is also the challenge of how to identify key variables for detecting and predicting risk, and how to combine them in predictive algorithms. This paper proposes a systematic feature extraction and selection framework for building Comprehensive Driver Profiles that serves as a foundation for driver behavior analysis and building whole driver profiles. Features are extracted from raw data using statistical feature extraction techniques, and a hybrid feature selection algorithm is used to select the best driver profile feature set based on outcomes of interest such as crash risk. It can give rise to individualized detection and prediction of risk, and can also be used to identify types of drivers who exhibit similar patterns of driving and vehicle/technology usage. The developed framework is applied to a naturalistic driving dataset—NEST, derived from the larger SHRP2 naturalistic driving study to illustrate the types of information about driver behavior that can be harnessed—as well as some of the important applications that can be derived from it.

The effect of dangerous driving behaviors on the risk of traffic accidents using structural equation modeling

Background and Objectives: Professional drivers are mostly exposed to heavy workload, like night shifts, long working hours and irregular schedules, leading to high prevalence of psychiatric disorder, including fatigue, memory loss, and insomnia leading to road traffic accidents and injury. The present paper evaluates the relationship between unsafe behaviors and accident risk in heavy vehicle drivers. Methods: This cross-sectional study was carried out among 303 professional drivers in Kashan. Unsafe behavior was measured using the Driving Behavior Questionnaire. In addition, a questionnaire was developed to assess the number of accidents and sociodemographic factors. Structural equation modeling (SEM) approaches were employed in the evaluated research hypothesis. Results: The results revealed that the average age of participants was 43.15, consisting of passenger vehicle drivers (20.1%) and commercial vehicle drivers (79.9%). The majority were married (94%). Participants drove for an average 11.3 years (standard deviation [SD] = 9.2) with the average speed 85.9 km/h (SD = 13.2). The DB questionnaire had validity and reliability (the factor loading, alpha Cronbach, composite reliability, and average variance extracted were more than 0.5, 0.7, 0.7, and 0.5, respectively). The SEM's results showed proper fit indices for the tested model (x2/df = 2.37; confirmatory fit index = 0.83; root mean square error of approximation = 0.06). Conclusions: The main factors of the driver to get involved in a traffic accident and dangerous driving behavior are followed: (a) driver's education level, (b) driver's experience, (c) hours of driving, (d) driver's drug use habit, and (f) risky and slip. It was noted that the level of road safety awareness is low. It can be decided that additional exertions should be made for arranging and imposing road safety and active traffic law legislation to encourage traffic safety responsiveness of the public.

Lower risk of car crashes among older drivers compared with younger drivers: analysis of 10 years of data

Objective: Traffic crashes are a significant cause of health expenditure, mainly considering disability and death. Driving skills are key when it comes to traffic crashes, and older drivers may be unfit to drive. The statistics of traffic crashes involving older drivers can contribute to planning actions that reduce accidents. This study aimed to present statistical data on traffic crashes among older adults in a Brazilian state. Methods: This is an epidemiological study performed with data from the Traffic Accident Information System of the Federal District Traffic Department, Brazil, ranging from 2008 to 2017 and comparing the incidence of injury crashes between older drivers and adult drivers. Results: Although the system recorded 60 705 drivers involved in injury crashes, a 24% reduction was seen in the overall crash incidence during the studied period (2008 – 2017); within the older drivers group, this reduction was two times smaller (12%). Despite the smaller drop in incidence, older car drivers presented around three times less risk of crashes when compared to adult drivers, along with a lower risk of accidents on urban, low-speed streets, and were mostly involved in collisions during the day. Conclusion: We found that the risk of older drivers being involved in injury crashes was three times smaller than that of adult drivers. The behavior of older drivers can influence the occurrence of accidents.