Analysis of Driving Behavior Based on Dynamic Changes of Personality States

Driving safety: Investigating the cognitive foundations of accident prevention

Driving is a crucial aspect of personal independence, and accurate assessment of driving skills is vital for ensuring road safety. This study aimed to identify reliable cognitive predictors of safe driving through a driving simulator experiment. We assessed the driving performance of 66 university students in two distinct simulated driving conditions and evaluated their cognitive skills in decision-making, attention, memory, reasoning, perception, and coordination. Multiple regression analyses were conducted to determine the most reliable cognitive predictor of driving outcome. Results revealed that under favorable driving conditions characterized by good weather and limited interactions with other road users, none of the variables tested in the study were able to predict driving performance. However, in a more challenging scenario with adverse weather conditions and heavier traffic, cognitive assessment scores demonstrated significant predictive power for the rate of traffic infractions committed. Specifically, cognitive skills related to memory and coordination were found to be most predictive. This study underscores the significance of cognitive ability, particularly memory, in ensuring safe driving performance. Incorporating cognitive evaluations in driver licensing and education/training programs can enhance the evaluation of drivers' competence and promote safer driving practices.

Born to Be a Risky Driver? The Relationship Between Cloninger's Temperament and Character Traits and Risky Driving

Temperament refers to basic, largely inherited, relatively stable personality traits which have been present since early childhood. Considering the very fundamental role of temperament in human development and behaviour, it is reasonable to assume that temperament is also related to risky driving and drivers' view of themselves as drivers. The aim of the present study was to investigate the relationships between Cloninger's temperament dimensions, risky driving and drivers' view of their perceptual motor and safety skills. The sample consisted of 335 Turkish drivers (aged 19-57; 53.7% men) who completed an Internet-based survey including Temperament and Character Inventory (TCI), Driver Behaviour Questionnaire (DBQ) and Driver Skill Inventory (DSI). Correlation analyses showed that TCI scale Cooperativeness correlated negatively with all DBQ scales indicating risky driving and positively with safety skills. In regression analyses after controlling age, gender and lifetime mileage, cooperativeness still was significantly related to all DBQ scales and safety skills. Persistence correlated negatively with ordinary violations, lapses and errors and positively with perceptual motor skills. In regression analyses, persistence was related to errors and lapses. Reward dependence was positively related to lapses and harm avoidance negatively to perceptual motor skills. The results of the present study indicate that largely innate temperament character traits may influence an individual's predisposition to risky driving. Future studies about temperament and risky driving with larger samples allowing sub-group analyses are needed.

An Analysis of Driving Behavior of Educated Youth in Bangladesh Considering Physiological, Cultural and Socioeconomic Variables

One of the alarming aspects of Bangladesh’s traffic safety is the massive growth in the number of drivers without previous driving instruction or licenses. Proper traffic safety is defined as systems and techniques used to safeguard road users against dying or being severely injured. A driving simulator policy and an environmental model are validated in this research. It aims to create a safe mass transit system with a minimal number of fatalities and injuries. The study focuses on current road and transportation strategies. Educated and internet-using Bangladeshi drivers took part in a questionnaire about their emotional stability on an online platform with more than 100 questions comprising two parts. While one of the part outlines the physiological, cultural, and socioeconomic factors and driver education, in another part, an 18-point Driver’s Behavior Questionnaire was introduced to the responders. About 40% of the surveyed drivers in the poll were inexperienced. However, 49% of people prefer to ride two-wheelers. Moreover, 70% of surveyed drivers hold valid driver’s licenses. At the same time, 35.2% of those were college graduates. Even 34.8% of accidents were caused by excessive speed and non-aggressive driving. In addition, age and degree of education were significant indicators of distracted driving violations. The study’s findings will raise awareness about the country’s undesirable driving patterns, resulting in a safer transit system with fewer accidents and deaths. In addition, the findings may be utilized to improve present road and transit policies and lead to the development of a driving simulator program for Bangladeshis.

Association between psychological symptoms and illegal driving behaviors in a sample of Chinese private car drivers

BACKGROUND

Findings on the associations between psychological symptoms and driving behaviors in private car drivers are inadequate.

METHOD

The study consisted of 3,115 private car drivers in Yulin, China. The measurements included socio-demographic data, traffic violations, accidents, and Symptom Checklist-90 (SCL-90). In addition, an ordered logistic regression model was employed to examine the association between each psychological symptom and risky driving behaviors.

RESULTS

The overall prevalence rate of any self-reported psychological symptom was 10.24%, with 9.22% for males and 11.49% for females. Among them, obsessive-compulsive, interpersonal sensitivity, additional items, hostility, and depression were the five most common psychological symptoms, with prevalence rates of 7.90, 6.29, 6.00, 5.91, and 5.62%, respectively. Any psychological symptom factor was associated with a higher risk of traffic violations and accidents. However, the intensity of the correlations varied, with obsessive-compulsive symptoms the strongest in general traffic violations and anxiety symptoms in traffic accidents. All psychological symptoms except phobic anxiety and paranoid ideation contributed to a higher risk of failing the driver's license test.

CONCLUSIONS

The prevalence rate of psychological symptoms was high in private car drivers. This study calls for an urgent need to establish a pilot tertiary prevention strategy to reduce risky driving behaviors through psychological symptom screening and interventions among private car drivers.

Risky Driver Recognition with Class Imbalance Data and Automated Machine Learning Framework

Identifying high-risk drivers before an accident happens is necessary for traffic accident control and prevention. Due to the class-imbalance nature of driving data, high-risk samples as the minority class are usually ill-treated by standard classification algorithms. Instead of applying preset sampling or cost-sensitive learning, this paper proposes a novel automated machine learning framework that simultaneously and automatically searches for the optimal sampling, cost-sensitive loss function, and probability calibration to handle class-imbalance problem in recognition of risky drivers. The hyperparameters that control sampling ratio and class weight, along with other hyperparameters, are optimized by Bayesian optimization. To demonstrate the performance of the proposed automated learning framework, we establish a risky driver recognition model as a case study, using video-extracted vehicle trajectory data of 2427 private cars on a German highway. Based on rear-end collision risk evaluation, only 4.29% of all drivers are labeled as risky drivers. The inputs of the recognition model are the discrete Fourier transform coefficients of target vehicle’s longitudinal speed, lateral speed, and the gap between the target vehicle and its preceding vehicle. Among 12 sampling methods, 2 cost-sensitive loss functions, and 2 probability calibration methods, the result of automated machine learning is consistent with manual searching but much more computation-efficient. We find that the combination of Support Vector Machine-based Synthetic Minority Oversampling TEchnique (SVMSMOTE) sampling, cost-sensitive cross-entropy loss function, and isotonic regression can significantly improve the recognition ability and reduce the error of predicted probability.