The effect of traffic tickets on road traffic crashes

High-risk event prone driver identification considering driving behavior temporal covariate shift

Drivers who perform frequent high-risk events (e.g., hard braking maneuvers) pose a significant threat to traffic safety. Existing studies commonly estimated high-risk event occurrence probabilities based upon the assumption that data collected from different time periods are independent and identically distributed (referred to as i.i.d. assumption). Such approach ignored the issue of driving behavior temporal covariate shift, where the distributions of driving behavior factors vary over time. To fill the gap, this study targets at obtaining time-invariant driving behavior features and establishing their relationships with high-risk event occurrence probability. Specifically, a generalized modeling framework consisting of distribution characterization (DC) and distribution matching (DM) modules was proposed. The DC module split the whole dataset into several segments with the largest distribution gaps, while the DM module identified time-invariant driving behavior features through learning common knowledge among different segments. Then, gated recurrent unit (GRU) was employed to conduct time-invariant driving behavior feature mining for high-risk event occurrence probability estimation. Moreover, modified loss functions were introduced for imbalanced data learning caused by the rarity of high-risk events. The empirical analyses were conducted utilizing online ride-hailing services data. Experiment results showed that the proposed generalized modeling framework provided a 7.2% higher average precision compared to the traditional i.i.d. assumption based approach. The modified loss functions further improved the model performance by 3.8%. Finally, benefits for the driver management program improvement have been explored by a case study, demonstrating a 33.34% enhancement in the identification precision of high-risk event prone drivers.

ProjectDRIVE: study protocol for a randomized controlled trial to improve driving practices of high-risk teen drivers with a traffic violation

BACKGROUND

Teen drivers with a traffic violation are at increased risk for crashes and crash-related injuries; however, most parent-focused interventions target teen drivers with supervised learner's permits. Very few interventions are implemented at the probationary driver's license stage or target high-risk teen drivers, such as those with traffic violations. This paper describes the protocol of ProjectDRIVE, A Randomized Controlled Trial to Improve Driving Practices of High-Risk Teen Drivers with a Traffic Violation, which targets improving parent-teen communication about safe driving practices to reduce unsafe driving behaviors and traffic violation recidivism of teen drivers cited for traffic violation.

METHODS

Teen drivers (ages 16 or 17) cited for a moving violation and the parent/legal guardian most involved with the teen's driving are recruited from juvenile traffic courts following their required court hearing. After completing informed consent/assent, enrolled dyads are randomized into one of three groups using stratified block randomization: control, device feedback only, or device feedback plus parent communication training. Participating dyads are followed for 6 months with 3 months of active intervention. Using in-vehicle device and smartphone application technology, the study provides real-time and cumulative driving feedback to intervention teens and collects continually recorded, objectively measured driving outcome data throughout the teen's study participation. Primary outcomes include rates of risky driving events and unsafe driving behaviors per 1000 miles driven. Secondary outcomes include traffic violation recidivism up to 12 months following study completion and frequency and quality of parent-teen communication about safe driving practices.

DISCUSSION

Through partnership with the local juvenile traffic courts, this study integrates recruitment and randomization into existing court practices. Successfully completing this study will significantly impact juvenile traffic court's practices and policies by informing judges' decisions regarding the driving safety programs they refer to teens to prevent motor vehicle crashes and crash-related injuries and deaths. Trial registration The study was registered on ClinicalTrials.gov Registry (NCT04317664) on March 19, 2020, https://clinicaltrials.gov/study/NCT04317664 and updated on April 27, 2021. This protocol was developed per the SPIRIT (Standard Protocol Items: Recommendations for Interventional Trials) Checklist.

Effectiveness of road safety interventions: An evidence and gap map

Background

Road Traffic injuries (RTI) are among the top ten leading causes of death in the world resulting in 1.35 million deaths every year, about 93% of which occur in low- and middle-income countries (LMICs). Despite several global resolutions to reduce traffic injuries, they have continued to grow in many countries. Many high-income countries have successfully reduced RTI by using a public health approach and implementing evidence-based interventions. As many LMICs develop their highway infrastructure, adopting a similar scientific approach towards road safety is crucial. The evidence also needs to be evaluated to assess external validity because measures that have worked in high-income countries may not translate equally well to other contexts. An evidence gap map for RTI is the first step towards understanding what evidence is available, from where, and the key gaps in knowledge.

Objectives

The objective of this evidence gap map (EGM) is to identify existing evidence from all effectiveness studies and systematic reviews related to road safety interventions. In addition, the EGM identifies gaps in evidence where new primary studies and systematic reviews could add value. This will help direct future research and discussions based on systematic evidence towards the approaches and interventions which are most effective in the road safety sector. This could enable the generation of evidence for informing policy at global, regional or national levels.

Search Methods

The EGM includes systematic reviews and impact evaluations assessing the effect of interventions for RTI reported in academic databases, organization websites, and grey literature sources. The studies were searched up to December 2019.

Selection Criteria

The interventions were divided into five broad categories: (a) human factors (e.g., enforcement or road user education), (b) road design, infrastructure and traffic control, (c) legal and institutional framework, (d) post-crash pre-hospital care, and (e) vehicle factors (except car design for occupant protection) and protective devices. Included studies reported two primary outcomes: fatal crashes and non-fatal injury crashes; and four intermediate outcomes: change in use of seat belts, change in use of helmets, change in speed, and change in alcohol/drug use. Studies were excluded if they did not report injury or fatality as one of the outcomes.

Data Collection and Analysis

The EGM is presented in the form of a matrix with two primary dimensions: interventions (rows) and outcomes (columns). Additional dimensions are country income groups, region, quality level for systematic reviews, type of study design used (e.g., case-control), type of road user studied (e.g., pedestrian, cyclists), age groups, and road type. The EGM is available online where the matrix of interventions and outcomes can be filtered by one or more dimensions. The webpage includes a bibliography of the selected studies and titles and abstracts available for preview. Quality appraisal for systematic reviews was conducted using a critical appraisal tool for systematic reviews, AMSTAR 2.

Main Results

The EGM identified 1859 studies of which 322 were systematic reviews, 7 were protocol studies and 1530 were impact evaluations. Some studies included more than one intervention, outcome, study method, or study region. The studies were distributed among intervention categories as: human factors (n = 771), road design, infrastructure and traffic control (n = 661), legal and institutional framework (n = 424), post-crash pre-hospital care (n = 118) and vehicle factors and protective devices (n = 111). Fatal crashes as outcomes were reported in 1414 records and non-fatal injury crashes in 1252 records. Among the four intermediate outcomes, speed was most commonly reported (n = 298) followed by alcohol (n = 206), use of seatbelts (n = 167), and use of helmets (n = 66). Ninety-six percent of the studies were reported from high-income countries (HIC), 4.5% from upper-middle-income countries, and only 1.4% from lower-middle and low-income countries. There were 25 systematic reviews of high quality, 4 of moderate quality, and 293 of low quality.

Authors' Conclusions

The EGM shows that the distribution of available road safety evidence is skewed across the world. A vast majority of the literature is from HICs. In contrast, only a small fraction of the literature reports on the many LMICs that are fast expanding their road infrastructure, experiencing rapid changes in traffic patterns, and witnessing growth in road injuries. This bias in literature explains why many interventions that are of high importance in the context of LMICs remain poorly studied. Besides, many interventions that have been tested only in HICs may not work equally effectively in LMICs. Another important finding was that a large majority of systematic reviews are of low quality. The scarcity of evidence on many important interventions and lack of good quality evidence-synthesis have significant implications for future road safety research and practice in LMICs. The EGM presented here will help identify priority areas for researchers, while directing practitioners and policy makers towards proven interventions.

Identification and screening of key traffic violations: based on the perspective of expressing driver's accident risk

Drawing on the core idea of Propensity Score Matching, this study proposes a new concept named Historical Traffic Violation Propensity to describe the driver's historical traffic violations, and combines the new concept with an improved mutual information-based feature selection algorithm to construct a method for screening key traffic violations from the perspective of expressing driver's accident risk. The validation analysis based on the real data collected in Shenzhen demonstrated that drivers' state of Historical Traffic Violation Propensity on 19 key traffic violations screened have a stronger predictive ability of their subsequent accidents compared to the level in existing research. The positive state of Historical Traffic Violation Propensity on 'Drinking', 'Parking in dangerous areas', 'Wrong use of turn lights', 'Violating prohibited and restricted traffic regulations', and 'Disobeying prohibition sign' will increase the probability of a driver's subsequent accident by more than 1.7 times. The research provides directions to more efficiently and accurately capture the driver's accident risk through historical traffic violations, which is valuable for identifying high-risk drivers as well as the key psychological or physical risk factors that manifest in daily driving activities and lead to subsequent accidents.

Critical safety management driver identification based upon temporal variation characteristics of driving behavior

Identifying critical safety management drivers with high driver-level risks is essential for traffic safety improvement. Previous studies commonly evaluated driver-level risks based upon aggregated statistical characteristics (e.g., driving exposure and driving behavior), which were obtained from long-period driving monitoring data. However, given the great advancements of the connected vehicle and in-vehicle data instrumentation technologies, there has been a notable increase in the collection of short-period driving data, which has emerged as a prominent data source for analysis. In this data environment, traditionally employed aggregated behavior characteristics are unstable due to the time-varying feature of driving behavior coupled with insufficient data sampling periods. Thus, traditional modeling methods based upon aggregated statistical characteristics are no longer feasible. Instead of utilizing such unreliable statistical information to represent driver-level risks, this study employed temporal variation characteristics of driving behavior to identify critical safety management drivers in the short-period driving data environment. Specifically, the relationships between driving behavior temporal variation characteristics and individual crash occurrence probability were developed. To eliminate the impacts of drivers' driving behavior heterogeneity on model performance, "traffic entropy" index that could quantify the abnormal degrees of driving behavior was proposed. Deep learning models including convolutional neural network (CNN) and long short-term memory (LSTM) were employed to conduct the temporal variation feature mining. Empirical analyses were conducted using data obtained from online ride-hailing services. Experiment results showed that temporal variation characteristics based models outperformed traditional aggregated statistical characteristics based models. The area under the curve (AUC) index was improved by 4.1%. And the proposed traffic entropy index further enhanced the model performance by 5.3%. The best model achieved an AUC of 0.754, comparable to existing approaches utilizing long-period driving data. Finally, applications of the proposed method in driver management program development and its further investigations have been discussed.

Examining enforcement coverage for speeding and red-light offenses across various populations and driver characteristics

Over the years empirical evidence has shown that traffic enforcement reduces traffic violations, crashes, and casualties. However, less attention has been paid to enforcement coverage across different populations and driver characteristics. The current study develops and explores a method for estimating police enforcement coverage, by comparing the share of drivers across several characteristics who received tickets from automatic speed and red-light cameras - as an objective estimate of offenses committed - to the share of drivers who received tickets through manual police enforcement. Using data from all speeding and red-light tickets issued to Israelis over a period of one and a half years, we found under-enforcement by police officers for female drivers, two-wheeled vehicle drivers (for speeding), and drivers with previous tickets. We found over-enforcement for younger drivers, truck drivers, and two-wheeled vehicle drivers (for red-light offenses). The findings suggest that the method developed in the research is able to identify groups of drivers who are over- or under-enforced. Police authorities can use this information to create evidence-based enforcement policies.

Subsequent risky driving behaviors, recidivism and crashes among drivers with a traffic violation: A scoping review

PURPOSE

Drivers who have committed a traffic violation are a particularly high-risk group, yet studies conducted among this group are scarce. We analyzed and synthesized the current literature concerning subsequent risky driving behaviors, recidivism, and crashes among drivers with a traffic violation.

METHODS

We searched PubMed, Education Resources Information Center (ERIC), Academic Search Complete, Web of Science, and Scopus for articles published in English between January 1, 1999, and May 31, 2023. A total of 25 articles met the selection criteria and were included in the final analysis. Two coders independently extracted and analyzed the selected articles to identify common categories across the articles, including study design, study population, type of traffic violation, and study outcomes including subsequent driving behaviors, recidivism, and crash risks.

RESULTS

Of the 25 selected articles, 19 (76%) involved both male and female participants. Fourteen (56%) studies were interventions/evaluation studies, with the other 11 (44%) being observational. Nineteen (76%) studies included alcohol-impaired driving violations, and 23 (92%) studies examined recidivism as an outcome measure. Over half of the observational studies demonstrated that traffic offenders were more likely to commit a subsequent traffic violation or had elevated risk of crashes. Most of the intervention/evaluation studies demonstrated a significant reduction in driving under the influence (DUI) of alcohol among the study participants. However, such positive effects observed during the active intervention period were not always sustained.

CONCLUSIONS

Traffic offenders are a high-risk group for subsequent violations and crashes. Evidence from this review calls for more effective interventions implemented following a traffic violation to prevent recidivism, crashes, and crash-related injuries and deaths.

Personality, perceptions and behavior: A study of speeding amongst drivers in Victoria, Australia

INTRODUCTION

Road crashes present a serious public health issue. Many people are seriously or fatally injured every year in avoidable crashes. While these crashes can have multiple contributing factors, including road design and condition, vehicle design and condition, the environment and human error, the performance of illegal driving behavior, including speeding, may also play a role. The current study aimed to examine the mediating influence that four potential deterrents (perceptions towards enforcement, crash risk, social norms and disapproval, and negative personal/emotional affect) have between the Big Five personality traits (conscientiousness; extraversion; agreeableness; neuroticism; openness) and expectations to speed.

METHODS

A total of 5,108 drivers in Victoria, Australia completed an online survey in 2019. A mediated regression analysis was used to examine pathways in a conceptual model developed for the study.

RESULTS

The results showed that perceptions towards the four potential deterrents examined did mediate the relationship (either completely or partially) between personality and expectations to speed.

CONCLUSIONS

The results of this study suggest that if interventions to deter illegal driving behavior are to be successful, one factor that could be taken into account is the personality traits of drivers who may be at greatest risk of the performance of illegal driving behaviors.

How do driving behavior and attitudes toward road safety vary between developed and developing countries? Evidence from Iran and the Netherlands

INTRODUCTION

The rates of road traffic injuries and fatalities in developing countries are significantly higher than in developed countries. This study examines the differences in driving behavior, road safety attitudes, and driving habits between a developed country (the Netherlands) and a developing country (Iran), which bear major differences in terms of crash involvement per population.

METHOD

In this context, this study assesses the statistical association of crash involvement with errors, lapses, aggressive driving incidents, and non-compliance with traffic rules, attitudes, and habits. Structural equation modeling was used to evaluate data obtained from 1,440 questionnaires (720 samples for each group).

RESULTS

The results revealed that more insecure attitudes toward traffic-regulation observance, negative driving habits, and risky behaviors, such as traffic rule violations act as influential factors of crash involvement. Iranian participants showed a greater likelihood to get involved in violations and driving habits with a higher level of risk. In addition, lower levels of safety attitudes toward traffic-regulation observance were observed. On the other hand, Dutch drivers were more likely to report lapses and errors. Dutch drivers also reported safer behavior in terms of unwillingness to engage in risky behaviors such as violations (speeding and no-overtaking). The structural equation models for crash involvement based on behaviors, attitudes, and driving habits were also evaluated for their accuracy and statistical fit using relevant indicators.

PRACTICAL APPLICATIONS

Finally, the findings of the present study point out the need for extensive research in some areas to foster policies that can effectively enhance safer driving.

Determinants of self-efficacy of driving behavior among young adults in the UAE: Impact of gender, culture, and varying environmental conditions in a simulated environment

Research on traffic accidents have acknowledged that human error is the leading cause of road accidents around the world. In the UAE, those aged between 18 and 30 years are involved in the most accidents. As a result, this study examines the perception, attitude and driving behavior of young adults in the UAE. Virtual Reality (VR) was used to examine driving behavior because it offers alternatives to assess driving behavior with a high degree of immersive experience in a safe and replicable environment. Participants drove through a virtual environment that resembled the urban environment of Abu Dhabi in the UAE, which included six traffic events. A sample of 12 females and 27 males also completed a pre and post-simulation questionnaire to report and evaluate their personal driving experience in Abu Dhabi. The volunteer group represented young drivers with limited driving experience and diverse cultural backgrounds. Results indicated that male drivers were less adhering to safe driving behavior compared to females. Even though both males and females exceeded the designated speed limit, males traveled longer distances over the limit. Additionally, it was found that young drivers tend to overestimate their skills with factors like gender, cultural background, and driving experience being key contributors. The results indicate that traffic authorities should take into consideration different approaches in the formulation of policies related to young drivers with periodic reassessment of skills and training to enhance the safety of driving in the UAE and the region.

Generalized trust and traffic violations: The moderating role of the individualism dimension

Traffic crashes take well over a million lives every year and are mainly caused by driver behavior and traffic violations. Drivers' attitudes and beliefs are at the root of whether traffic violations will be committed, making it important to explore what contributes to disobedience of traffic law. Generalized trust is one of the most influential factors in interpersonal behavior but has not yet been studied empirically in the context of driving behavior in general, and traffic violations in specific. Using data from about 30,000 participants from 20 European countries, this study examines the relationship between generalized trust and committing traffic violations while paying attention to differences between countries scoring high and low in individualism. A multilevel mixed-effects logistic regression analysis shows that in countries with high individualism scores, the probability to commit traffic violations increases significantly as generalized trust increases, while the association between generalized trust and traffic violations decreases as the country's individualism level decreases. The findings and their implications are discussed with suggestions for future research.

A data-driven Bayesian network for probabilistic crash risk assessment of individual driver with traffic violation and crash records

In recent years, individual drivers' crash risk assessments have received much attention for identifying high-risk drivers. To this end, we propose a probabilistic assessment method of crash risks with a reproducible long-term dataset (i.e., traffic violations, license, and crash records). In developing this method, we used 7.75 million violations and crashes of 5.5 million individual drivers in Seoul, South Korea, from June 2013 to June 2017 (four years). The stochastic process of the Bayesian network (BN), whose structure is optimized by tabu-search, successfully evaluates individual drivers' crash and violation probability. In addition, the cluster analysis classifies drivers into five distinctive groups according to their estimated violation and crash probabilities. As a result, this study found that the estimated average crash rate within a cluster converges with the actual crash rate by the proposed framework without privacy issues. We also confirm that violation records and expected crash probability are strongly correlated, and there is a direct relationship between a driver's previous violations and crash record and the future at-fault crash. The proposed assessment method is valuable in developing proactive driver education programs and safety countermeasures, including adjusting the penalty system and developing user-based insurance by recognizing dangerous drivers and identifying their properties.

Does past offending behaviors catch up with you? A study examining the relationship between traffic offending history and fatal crash involvement

OBJECTIVE

The aim of the current study was to compare the traffic histories of drivers fatally injured in a road traffic crash, to alive drivers of the same age and gender in order to determine if key markers of increased fatality-risk could be identified.

METHODS

The case sample comprised 1,139 (82% male) deceased drivers, while the control sample consisted of 1,139 registered Queensland drivers (who were individually matched to the case sample on age and gender).

RESULTS

Using a logistic regression model, and adjusting for age and gender, it was found that a greater number of offenses predicted greater odds of fatal crash involvement, with each increase in offense frequency category increasing ones' odds by 1.98 (95% CI: 1.8, 2.18). When each offense type was considered individually, dangerous driving offenses were most influential, predicting a 3.44 (95% CI: 2, 5.93) increased odds of being in the case group, followed by the following offense types: learner/provisional (2.88, 95% CI: 1.75, 4.74), drink and drug driving (2.82, 95% CI: 1.97, 4.04), not wearing a seatbelt/helmet (2.63, 95% CI: 1.53, 4.51), licensing offenses (1.87, 95% CI: 1.41, 2.49), and speeding (1.48, 95% CI: 1.33, 1.66). In contrast, mobile phone and road rules offenses were not identified as significant predictors.

CONCLUSION

The findings indicate that engagement in a range of aberrant driving behaviors may result in an increased odds of future fatal crash involvement, which has multiple implications for the sanctioning and management of apprehended offenders.

Involvement of Road Users from the Productive Age Group in Traffic Crashes in Saudi Arabia: An Investigative Study Using Statistical and Machine Learning Techniques

Road traffic crashes (RTCs) are a major problem for authorities and governments worldwide. They incur losses of property, human lives, and productivity. The involvement of teenage drivers and road users is alarmingly prevalent in RTCs since traffic injuries unduly impact the working-age group (15–44 years). Therefore, research on young people’s engagement in RTCs is vital due to its relevance and widespread frequency. Thus, this study focused on evaluating the factors that influence the frequency and severity of RTCs involving adolescent road users aged 15 to 44 in fatal and significant injury RTCs in Al-Ahsa, Saudi Arabia. In this study, firstly, descriptive analyses were performed to justify the target age group analysis. Then, prediction models employing logistic regression and CART were created to study the RTC characteristics impacting the target age group participation in RTCs. The most commonly observed types of crashes are vehicle collisions, followed by multiple-vehicle and pedestrian crashes. Despite its low frequency, the study area has a high severity index for RTCs, where 73% of severe RTCs include individuals aged 15 to 44. Crash events with a large number of injured victims and fatalities are more likely to involve people in the target age range, according to logistic regression and CART models. The CART model also suggests that vehicle overturn RTCs involving victims in the target age range are more likely to occur as a result of driver distraction, speeding, not giving way, or rapid turning. As compared with the logistic regression model, the CART model was more convenient and accurate for understanding the trends and predicting the involvement probability of the target age group in RTCs; however, this model requires a higher processing time for its development.

Versatile, but not focused, traffic offenders are more likely to be at fault for a fatal crash

INTRODUCTION

The aim of this study was to determine whether drivers who had received more traffic infringements were more likely to be at fault for the crash in which they were killed.

METHOD

The current dataset was derived from the crash and traffic history records provided by the Queensland Department of Transport and Main Roads and Coroner's Court for every driver, with available records, who was killed in a crash in Queensland, Australia, between 2011 and 2019 (N = 1,136). The most common traffic offenses in the current sample were speeding, disobeying road rules, driving under the influence of drugs and alcohol, and unlicensed driving. Logistic regression models were used to compute odds ratios for the number of overall offenses, the number of specific offense types, and for specific offending profiles that were derived from the literature. Age, gender, and crash type were each controlled for by entering them into the initial blocks of the regression models.

RESULTS

After accounting for the variance associated with age, gender, and crash type, only the overall number of offenses and the number of unlicensed driving offenses predicted a significant change in a drivers' likelihood of being at fault for the crash that killed them. Furthermore, drivers who were identified as having versatile (i.e., multiple offenses from different categories) or criminal-type offense profiles (i.e., offenses that were considered to approximate criminal offenses) were each significantly more likely to be at fault for a fatal crash.

PRACTICAL APPLICATIONS

This study provided an important contribution by demonstrating how a more nuanced approach to understanding how a driver's traffic history might be used to identify drivers who are more at risk of being involved in a crash (i.e., for which they were at fault). The implications of these findings are discussed with recommendations and consideration for future research.

A proportional odds model of risk behaviors associated with recurrent road traffic crashes among young adults in Kuwait

Background

The aims of this cross-sectional study were to i) assess one-year period prevalence of one, two, three or more road traffic crashes (RTCs) as an ordinal outcome and ii) identify the drivers’ characteristics associated with this ordinal outcome among young adult drivers with propensity to recurrent RTCs in Kuwait.

Methods

During December 2016, 1465 students, 17 years old or older from 15 colleges of Kuwait University participated in this cross-sectional study. A self-administered questionnaire was used for data collection. One-year period prevalence (95% confidence interval (CI)) of one, two, three or more RTCs was computed. Multivariable proportional odds model was used to identify the drivers’ attributes associated with the ordinal outcome.

Results

One-year period prevalence (%) of one, two and three or more RTCs respectively was 23.1 (95% CI: 21.2, 25.6), 10.9 (95% CI: 9.4, 12.6), and 4.6 (95% CI: 3.6, 5.9). Participants were significantly (p < 0.05) more likely to be in higher RTCs count category than their current or lower RCTs count, if they habitually violated speed limit (adjusted proportional odds ratio (pOR_adjusted) = 1.40; 95% Cl: 1.13, 1.75), ran through red lights (pOR_adjusted = 1.64; 95%CI: 1.30, 2.06), frequently (≥ 3) received multiple (> 3) speeding tickets (pOR_adjusted = 1.63; 95% CI: 1.12, 2.38), frequently (> 10 times) violated no-parking zone during the past year (pOR_adjusted = 1.64; 95% CI: 1.06, 2.54) or being a patient with epilepsy (pOR_adjusted = 4.37; 95% CI: 1.63, 11.70).

Conclusion

High one-year period prevalence of one, two and three or more RTCs was recorded. Targeted education based on identified drivers’ attributes and stern enforcement of traffic laws may reduce the recurrent RTCs incidence in this and other similar populations in the region.

Modelling the relationship of driver license and offense history with fatal and serious injury (FSI) crash involvement

INTRODUCTION

Previous research has indicated that increases in traffic offenses are linked to increased crash involvement rates, making reductions in offending an appropriate measure for evaluating road safety interventions in the short-term. However, the extent to which traffic offending predicts fatal and serious injury (FSI) crash involvement risk is not well established, prompting this new Victorian (Australia) study.

METHOD

A preliminary cluster analysis was performed to describe the offense data and assess FSI crash involvement risk for each cluster. While controlling demographic and licensing variables, the key traffic offenses that predict future FSI crash involvement were then identified. The large sample size allowed the use of machine learning methods such as random forests, gradient boosting, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. This was done for the 'all driver' sample and five sometimes overlapping groups of drivers; the young, the elderly, and those with a motorcycle license, a heavy vehicle license endorsement and/or a history of license bans.

RESULTS

With the exception of the group of drivers who had a history of bans, offense history significantly improved the accuracy of models predicting future FSI crash involvement using demographic and licensing data, suggesting that traffic offenses may be an important factor to consider when analyzing FSI crash involvement risk and the effects of road safety countermeasures.

CONCLUSIONS

The results are helpful for identifying driver groups to target with further road safety countermeasures, and for showing that machine learning methods have an important role to play in research of this nature. Practical Application: This research indicates with whom road safety interventions should particularly be applied. Changes to driver demerit policies to better target offenses related to FSI crash involvement and repeat traffic offenders, who are at greater risk of FSI crash involvement, are recommended.

Can the effectiveness of driver education be sustained? Effects of driving breaks on novice drivers' traffic violations

Prior studies have shown that driver education can reduce traffic violations. However, few studies have examined how driving break between driver education and owning a car influences novice drivers' traffic violations. The main objective of this study is to examine the association between driving break and traffic violations. Data from 356,786 drivers with a total of 978,855 violations during their first year of driving were extracted from the Wuhan Traffic Management Bureau. Specifically, we focused on three outcome measures: time length of first traffic violation, severity of first traffic violation, and number of traffic violations in the first year of driving. The results indicated that driving break accelerated the occurrence of the first traffic violation but reduced its severity. The results also showed that driving break was significantly related to an increase in traffic violations during the first year of driving. The detrimental effects of driving break on the time length of first traffic violation and the number of traffic violations in the first year of driving were attenuated in older age groups. The inhibitory effect of driving break on serious violations was stronger in older age groups. The findings support that the effectiveness of driver education will fade over time if one does not consolidate the learned knowledge and skills through practice.

Mid-term prediction of at-fault crash driver frequency using fusion deep learning with city-level traffic violation data

Traffic violations and improper driving are behaviors that primarily contribute to traffic crashes. This study aimed to develop effective approaches for predicting at-fault crash driver frequency using only city-level traffic enforcement predictors. A fusion deep learning approach combining a convolution neural network (CNN) and gated recurrent units (GRU) was developed to compare predictive performance with one econometric approach, two machine learning approaches, and another deep learning approach. The performance comparison was conducted for (1) at-fault crash driver frequency prediction tasks and (2) city-level crash risk prediction tasks. The proposed CNN-GRU achieved remarkable prediction accuracy and outperformed other approaches, while the other approaches also exhibited excellent performances. The results suggest that effective prediction approaches and appropriate traffic safety measures can be developed by considering both crash frequency and crash risk prediction tasks. In addition, the accumulated local effects (ALE) plot was utilized to investigate the contribution of each traffic enforcement activity on traffic safety in a scenario of multicollinearity among predictors. The ALE plot illustrated a complex nonlinear relationship between traffic enforcement predictors and the response variable. These findings can facilitate the development of traffic safety measures and serve as a good foundation for further investigations and utilization of traffic violation data.

A systematic review of statistical models and outcomes of predicting fatal and serious injury crashes from driver crash and offense history data

BACKGROUND

Expenditure on driver-related behavioral interventions and road use policy is often justified by their impact on the frequency of fatal and serious injury crashes. Given the rarity of fatal and serious injury crashes, offense history, and crash history of drivers are sometimes used as an alternative measure of the impact of interventions and changes to policy. The primary purpose of this systematic review was to assess the rigor of statistical modeling used to predict fatal and serious crashes from offense history and crash history using a purpose-made quality assessment tool. A secondary purpose was to explore study outcomes.

METHODS

Only studies that used observational data and presented a statistical model of crash prediction from offense history or crash history were included. A quality assessment tool was developed for the systematic evaluation of statistical quality indicators across studies. The search was conducted in June 2019.

RESULTS

One thousand one hundred and five unique records were identified, 252 full texts were screened for inclusion, resulting in 20 studies being included in the review. The results indicate substantial and important limitations in the modeling methods used. Most studies demonstrated poor statistical rigor ranging from low to middle quality. There was a lack of confidence in published findings due to poor variable selection, poor adherence to statistical assumptions relating to multicollinearity, and lack of validation using new data.

CONCLUSIONS

It was concluded that future research should consider machine learning to overcome correlations in the data, use rigorous vetting procedures to identify predictor variables, and validate statistical models using new data to improve utility and generalizability of models.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42019137081.

Adopting Machine Learning and Spatial Analysis Techniques for Driver Risk Assessment: Insights from a Case Study

Traffic violations usually caused by aggressive driving behavior are often seen as a primary contributor to traffic crashes. Violations are either caused by an unintentional or deliberate act of drivers that jeopardize the lives of fellow drivers, pedestrians, and property. This study is aimed to investigate different traffic violations (overspeeding, wrong-way driving, illegal parking, non-compliance traffic control devices, etc.) using spatial analysis and different machine learning methods. Georeferenced violation data along two expressways (S308 and S219) for the year 2016 was obtained from the traffic police department, in the city of Luzhou, China. Detailed descriptive analysis of the data showed that wrong-way driving was the most common violation type observed. Inverse Distance Weighted (IDW) interpolation in the ArcMap Geographic Information System (GIS) was used to develop violation hotspots zones to guide on efficient use of limited resources during the treatment of high-risk sites. Lastly, a systematic Machine Learning (ML) framework, such as K Nearest Neighbors (KNN) models (using k = 3, 5, 7, 10, and 12), support vector machine (SVM), and CN2 Rule Inducer, was utilized for classification and prediction of each violation type as a function of several explanatory variables. The predictive performance of proposed ML models was examined using different evaluation metrics, such as Area Under the Curve (AUC), F-score, precision, recall, specificity, and run time. The results also showed that the KNN model with k = 7 using manhattan evaluation had an accuracy of 99% and outperformed the SVM and CN2 Rule Inducer. The outcome of this study could provide the practitioners and decision-makers with essential insights for appropriate engineering and traffic control measures to improve the safety of road-users.

Mobile phone use among Indonesian motorcyclists: prevalence and influencing factors

OBJECTIVE

Indonesia is one of many developing countries that relies on motorcycles as a major mode of transportation. Unfortunately, the widespread use of motorcycles in Indonesia coincides with a high number of motorcycle accidents which can often be attributed to unsafe behaviors of the motorcyclist. One unsafe behavior that is common and hypothetically associated with accidents is the use of a mobile phone while motorcycling. The aim of the present study was to observe the prevalence and behavior of mobile phone use among Indonesian motorcyclists and the factors that might have influenced their behavior.

METHODS

Five hundred Indonesian motorcyclists voluntarily participated in this study by filling out a questionnaire that gathered demographic data, motorcycling behaviors, and a statement related to what factors might influence their likelihood to use a mobile phone while motorcycling. A descriptive statistic and Structural Equation Modeling were applied in analyzing the data.

RESULTS

Results showed that the prevalence of mobile phone use among Indonesian motorcyclists was 75%. The demographic data that significantly influenced mobile phone use during motorcycling were age, education level, marital status, and number of children. Occupation, gender, and prior experiences that included accidents and tickets with fines did not influence the use of mobile phones during motorcycling. The behavioral model showed that the factors that influenced motorcyclist's intentions to avoid mobile phone use during motorcycling were attitude, perceived behavioral control, and cues to action.

CONCLUSIONS

This study supports previous findings regarding the high prevalence of mobile phone use among motorcyclists in developing countries. The models implied that further investigation on intervention strategy to minimize mobile phone use during motorcycling is a necessity.

Effects of the penalty mechanism against traffic violations in China: A joint frailty model of recurrent violations and a terminal accident

A penalty mechanism is usually considered as a powerful means to reduce the probability of traffic violations and accidents by encouraging drivers to comply with traffic regulations. Penalty point and fine strategies are often used in parallel. Different degrees of penalty points and/or fines are imposed according to the specific violation behavior of drivers. However, the question of whether each penalty produces positive effects in maintaining a driver's compliance with traffic regulations and promoting the driver's traffic safety is still unanswered. This study focuses on quantifying the effects of penalty point and fine strategies on violation recurrences and accident occurrences of drivers. A frailty survival analysis method is conducted to jointly model the occurrence of violation and accident events of each individual. The frailty term in the model is leveraged to address the unobserved heterogeneity among drivers. Personal characteristics and penalty status are also incorporated as covariates in the model. Actual violation and accident data from a province in China are utilized to calibrate the model. The results show that penalty point strategy exhibits deterrent and binding effects; however, penalty fine strategy does not show the expected effects. The number of years of driving is also a significant factor that influences violation recurrence and accident occurrence. The present study provides insightful information for improving violation penalty mechanisms.

The effectiveness and influencing factors of a penalty point system in China from the perspective of risky driving behaviors

Many countries have adopted penalty point systems (PPS) to deter drivers from breaking traffic laws. To investigate the effectiveness of PPS on reducing illegal driving behavior, this study analyzed traffic violation data of a Chinese city in 2017. This analysis revealed that 1) risky driving behaviors (RDBs) are among the main causes of traffic violations and 2) almost half of the offenders with multiple violations committed the same traffic rule violations more than once. To further explain these phenomena, a survey in another Chinese city-Tianjin-was conducted. Considering the fact that most types of RDBs will, if detected by the authorities, result in traffic violations, the present study investigated the influence of a PPS, represented by penalty experience (PE), on traffic violation behaviors from the perspective of RDBs. Moreover, the impact of cognitive processes on driving behaviors via self-efficacy was considered. We found that drivers' PE is positively associated with their RDBs and that offenders with more PE are more inclined to commit RDBs; we further observed that self-efficacy partially mediates the relationship between PE and RDBs. However, no gender difference in the effect of PE on RDBs was discovered, thus indicating that PE has the same effect on male and female drivers. Based on these findings, some strategies are suggested (such as the Increasing Block Penalty Points Policy) to improve the effectiveness of the PPS.

Regulatory focus, time perspective, locus of control and sensation seeking as predictors of risky driving behaviors

Empirical evidence shows that most of the road safety efforts fail to reach the most risk-prone drivers. In light of this issue, we have developed this study in order to distinguish between high-risk drivers and low-risk drivers based on variables that have already been shown to affect the effectiveness of preventive messages: regulatory focus orientation, time perspective, locus of control and sensation seeking. We sent paper and pencil questionnaires to five thousand low-risk drivers and five thousand high-risk drivers randomly selected based on their driving records. A driver who has been convicted of two or more traffic infractions with demerit points (e.g., exceeding speed limits, red light violation, no seatbelt, etc.) in the last two years was considered a high-risk driver whereas a low-risk driver had no traffic offense registered in his driving record in the last four years. We received two thousand and sixty-four completed questionnaires for a response rate of 20.6%. Seven hundred and ninety-eight belonged to the group of high-risk drivers and one thousand two hundred and sixty-six to the group of low-risk drivers. The results show that a promotion focused orientation, a present hedonistic perspective, an internal locus of control, and sensation seeking are associated with more risky driving behaviors and could therefore distinguish between high-risk and low-risk drivers. These results increase the understanding of risky drivers' personalities and motivations. The literature review provides insight into how these findings might be considered in developing more effective road safety programs and campaigns, and the conclusion encourages researchers to explore these new avenues in future research.

Reducing traffic violations in minority localities: Designing a traffic enforcement program through a public participation process

The current study tests an innovative public participation process for designing and implementing a tailored traffic enforcement program in minority localities. The quasi-experiment used two matched pairs of randomly selected Israeli Arab localities, where one locality in each pair was randomly assigned to the experimental group and the other to the control group. The intervention's main features were the public participation process and implementation by police of the traffic enforcement program designed during the process. Systematic field observations on 12,236 vehicles in the four localities found a meaningful and significant reduction in traffic violations in the experimental localities following the intervention, while a small increase in violations was observed in the control localities. The most meaningful decline, indicating improvement in drivers' behavior, was in non-use of seatbelts and small children in the front seat. The study suggests that a public participation process which identifies local road traffic problems and "dark" hot spots (places where offenses and risky behavior recur but might not be known to the police), followed by implementing tailored solutions for these problems, can reduce traffic violations. Future research should aim to separate out the independent effects of the two phases (the public participation process and tailored enforcement).

The relationship between the Driver Behavior Questionnaire, Sensation Seeking Scale, and recorded crashes: A brief comment on Martinussen et al. (2017) and new data from SHRP2

We provide a brief comment on the work of Martinussen et al. (2017), who studied the relationships between self-reported driving behavior, registered traffic offences, and registered crash involvement. It is argued that if the number of crashes is small, then the correlation with crashes is also small. Our analysis of the SHRP2 naturalistic driving study shows that the violations score of the Driver Behavior Questionnaire and the Sensation Seeking Scale exhibit small correlations with recorded crashes, and small-to-moderate correlations with recorded near-crashes and measures of driving style.

Risk of motor vehicle crash for older adults after receiving a traffic charge: A case-crossover study

OBJECTIVE

After the age of 65, the number of motor vehicle crashes per mile driven increases. Traffic-related charges issued by law enforcement can help identify drivers who are at a higher risk of having a crash. This study examines the relationship between motor vehicle crashes and traffic-related charges among older adult drivers.

METHODS

Iowa Department of Transportation crash data from 2011-2012 were linked with Iowa Court Information System data for moving violations that occurred during 2009-2012 for drivers over the age of 50. A time-stratified case-crossover design was used matching on time periods 1 year apart. Case exposure was defined as having a traffic-related charge 30 days before the crash. Control exposure was the same 30-day time period 1 year before the crash for each individual. Conditional logistic regression was used to analyze the self-matched pairs. Additional time periods of 31-60, 61-90, 91-120, 121-150, 151-180, and 181-210 days before the crash were also assessed.

RESULTS

There were 38,171 adults at least 50 years of age with an Iowa driver's license who were involved in a crash in Iowa between 2011 and 2012. In addition, 13,129 adults over the age of 50 received a charge during 2009-2012. Relative to the control time period, experiencing a traffic-related charge in the 30-day time period before the crash increased the risk of a crash by 21% (odds ration [OR] = 1.21, 95% confidence interval [CI], 1.03-1.42) for all drivers included in the study. This crash risk was similar for adults aged 50-64 (OR = 1.20, 95% CI, 1.00-1.45) and adults 65 and older (OR = 1.24, 95% CI, 0.90-1.72). In the 30 days after receiving a traffic-related charge, the risk of a crash was also increased for crashes occurring in adverse weather (OR = 1.79, 95% CI, 1.12-2.84) or during night, dawn, or twilight (OR = 1.89, 95% CI, 1.31-2.72).

CONCLUSIONS

A traffic-related charge for an adult over the age of 50 indicates an increased risk of experiencing a crash in the 30 days following the charge. The risk for crashes occurring in adverse conditions or outside of daylight hours was also increased in the 30 days after receiving a traffic-related charge. The risk of experiencing a crash decreases as time passes after receiving a charge. Measures to restrict or increase driving safety during these conditions could help reduce the crash risk for older adults who receive a traffic-related charge.

Methods to rank traffic rule violations resulting in crashes for allocation of funds

Education, enforcement and engineering countermeasures are implemented to make road users comply with the traffic rules. Not all the traffic rule violations can be addressed nor countermeasures be implemented at all unsafe locations, at once, due to limited funds. Therefore, this study aims at ranking the traffic rule violations resulting in crashes based on individual ranks, such as 1) frequency (expressed as a function of the number of drivers violating a traffic rule and involved in crashes), 2) crash severity, 3) total crash cost, and, 4) cost severity index, to assist transportation system managers in prioritizing the allocation of funds and improving safety on roads. Crash data gathered for the state of North Carolina was processed and used in this study. Variations in the ranks of traffic rule violations were observed when individual ranking methods are used. As an example, exceeding authorized speed limit and driving under the influence of alcohol are ranked 1st and 2nd based on crash severity while failure to reduce speed and failure to yield the right-of-way are ranked 1st and 2nd based on frequency. To minimize the variations and capture the merits of individual ranking methods, four different composite ranks were computed by combining selected individual ranks. The computed averages and standard deviations of absolute rank differences between composite ranks is lower than those obtained from individual ranks. The weights to combine the selected individual ranks have a marginal effect on the computed averages and standard deviations of absolute rank differences. Combining frequency and crash severity or cost severity index, using equal weights, is recommended for prioritization and allocation of funds.

Predicting Crashes Using Traffic Offences. A Meta-Analysis that Examines Potential Bias between Self-Report and Archival Data

Background

Traffic offences have been considered an important predictor of crash involvement, and have often been used as a proxy safety variable for crashes. However the association between crashes and offences has never been meta-analysed and the population effect size never established. Research is yet to determine the extent to which this relationship may be spuriously inflated through systematic measurement error, with obvious implications for researchers endeavouring to accurately identify salient factors predictive of crashes.

Methodology and Principal Findings

Studies yielding a correlation between crashes and traffic offences were collated and a meta-analysis of 144 effects drawn from 99 road safety studies conducted. Potential impact of factors such as age, time period, crash and offence rates, crash severity and data type, sourced from either self-report surveys or archival records, were considered and discussed. After weighting for sample size, an average correlation of r = .18 was observed over the mean time period of 3.2 years. Evidence emerged suggesting the strength of this correlation is decreasing over time. Stronger correlations between crashes and offences were generally found in studies involving younger drivers. Consistent with common method variance effects, a within country analysis found stronger effect sizes in self-reported data even controlling for crash mean.

Significance

The effectiveness of traffic offences as a proxy for crashes may be limited. Inclusion of elements such as independently validated crash and offence histories or accurate measures of exposure to the road would facilitate a better understanding of the factors that influence crash involvement.

A quarter of a century of the DBQ: some supplementary notes on its validity with regard to accidents

This article synthesises the latest information on the relationship between the Driver Behaviour Questionnaire (DBQ) and accidents. We show by means of computer simulation that correlations with accidents are necessarily small because accidents are rare events. An updated meta-analysis on the zero-order correlations between the DBQ and self-reported accidents yielded an overall r of .13 (fixed-effect and random-effects models) for violations (57,480 participants; 67 samples) and .09 (fixed-effect and random-effects models) for errors (66,028 participants; 56 samples). An analysis of a previously published DBQ dataset (975 participants) showed that by aggregating across four measurement occasions, the correlation coefficient with self-reported accidents increased from .14 to .24 for violations and from .11 to .19 for errors. Our meta-analysis also showed that DBQ violations (r = .24; 6353 participants; 20 samples) but not DBQ errors (r = - .08; 1086 participants; 16 samples) correlated with recorded vehicle speed. Practitioner Summary: The DBQ is probably the most widely used self-report questionnaire in driver behaviour research. This study shows that DBQ violations and errors correlate moderately with self-reported traffic accidents.