scholarly journals Insights into Factors Affecting Traffic Accident Severity of Novice and Experienced Drivers: A Machine Learning Approach

Author(s):  
Shuaiming Chen ◽  
Haipeng Shao ◽  
Ximing Ji

Traffic accidents have significant financial and social impacts. Reducing the losses caused by traffic accidents has always been one of the most important issues. This paper presents an effort to investigate the factors affecting the accident severity of drivers with different driving experience. Special focus was placed on the combined effect of driving experience and age. Based on our dataset (traffic accidents that occurred between 2005 and 2021 in Shaanxi, China), CatBoost model was applied to deal with categorical feature, and SHAP (Shapley Additive exPlanations) model was used to interpret the output. Results show that accident cause, age, visibility, light condition, season, road alignment, and terrain are the key factors affecting accident severity for both novice and experienced drivers. Age has the opposite impact on fatal accident for novice and experienced drivers. Novice drivers younger than 30 or older than 55 are prone to suffer fatal accident, but for experienced drivers, the risk of fatal accident decreases when they are young and increases when they are old. These findings fill the research gap of the combined effect of driving experience and age on accident severity. Meanwhile, it can provide useful insights for practitioners to improve traffic safety for novice and experienced drivers.

2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Yunwei Meng

Mountainous freeways always suffer from accidents due to special terrain, weather conditions, driving environment, and so on. Based on the records of 898 accidents that occurred on mountainous freeways in Chongqing during the past 6 years, the partial proportional odds model is used to identify the factors affecting the accident severity. The time of the accident, season, involvement of trucks, accident characteristics, speeding, maximum driving experience of involved drivers, and weather and road conditions are found to be important for the levels of accident severity. Zero to 6 a.m. and 19 to 24 p.m. are the times prone to serious traffic accidents. The probability of serious traffic accidents in summer and autumn is greater than that in spring and winter. Once a truck is involved in an accident, the consequence is often more severe. Turnover and speeding will result in a grave accident. When there is an experienced driver, the probability of serious traffic accidents is low. The fog is extremely unfavorable weather conditions. The probability of serious accident happening in the downgrade, ramp, curve, bridge, and tunnel sections is greater than the others. The results aim to provide valuable reference for traffic safety on mountainous freeways.


2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Qiang Luo ◽  
Xinqiang Chen ◽  
Jie Yuan ◽  
Xiaodong Zang ◽  
Junheng Yang ◽  
...  

The reasonable distance between adjacent cars is very crucial for roadway traffic safety. For different types of drivers or different driving environments, the required safety distance is different. However, most of the existing rear-end collision models do not fully consider the subjective factor such as the driver. Firstly, the factors affecting driving drivers’ characteristics, such as driver age, gender, and driving experience are analyzed. Then, on the basis of this, drivers are classified according to reaction time. Secondly, three main factors affecting driving safety are analyzed by using fuzzy theory, and the new calculation method of the reaction time is obtained. Finally, the improved car-following safety model is established based on different reaction time. The experimental results have shown that our proposed model obtained more accurate vehicle safety distance with varied traffic kinematic conditions (i.e., different traffic states, varied driver types, etc.). The findings can help traffic regulation departments issue early warnings to avoid potential traffic accidents on roads.


2021 ◽  
Vol 13 (9) ◽  
pp. 5252
Author(s):  
Sreten Simović ◽  
Tijana Ivanišević ◽  
Aleksandar Trifunović ◽  
Svetlana Čičević ◽  
Dragan Taranović

The increase in the number of electric bicycles worldwide has resulted in a rise in the number of traffic accidents involving e-bicyclists. Previous studies have been based on analyzing the use, advantages and disadvantages of e-bicycles, whereas only a small number of studies have been focused on analyzing the e-bicycle traffic safety, particularly the factors leading to the occurrence of traffic accidents. One of the factors affecting the occurrence of traffic accidents is the incorrect perception of the e-bicycle speed by other traffic participants. To examine the mentioned problem, the authors of this paper conducted an experimental study to determine what affects the e-bicycle speed perception. The experiment included 175 participants, aged 18 to 50. The research was conducted under laboratory conditions using a driving simulator, at different e-bicycle speeds (10 km/h, 20 km/h and 30 km/h), in the situations in which the e-bicyclist was (not) using a reflective vest. The results show statistically significant differences in the e-bicycle speed perception when the e-bicyclist does not use/uses a reflective vest. Besides, the driving licence categories of traffic participants and their driving experience also have a significant impact on the perception of the e-bicycle speed.


2020 ◽  
Vol 14 (1) ◽  
pp. 237-250
Author(s):  
Dinh Hiep ◽  
Vu V. Huy ◽  
Teppei Kato ◽  
Aya Kojima ◽  
Hisashi Kubota

Introduction: One of the significant characteristics of schools in Vietnam is that almost all parents send their children to school and/or pick up their children from school using private vehicles (motorcycles). The parents usually stop and park their vehicle on streets outside the school gates, which can lead to serious congestion and increases the likelihood of traffic accidents. Methods: The objective of this study is to find out factors affecting the picking up of pupils at primary school by evaluating the typical primary schools in Hanoi city. A binary logistic regression model was used to determine factors that influence the decision of picking up pupils and the waiting duration of parents. The behavior of motorcyclists during the process of picking up pupils at the primary school gate has been identified and analyzed in detail by the Kinovea software. Results and Discussion: The study showed that, on the way back home, almost all parents use motorbikes (89.15%) to pick up their children. During their waiting time (8.48 minutes in average), they made a lot of illegal parking actions on the street there by, causing a lot of “cognitive” errors and “crash” points surrounding in front of the primary school entrance gate. Risky picking-up behaviors were significantly observed, i.e. picking-up on opposite side of the school, making a U-turn, backing-up dangerously, parking on the middle of street, and parking on the street next to sidewalk). Conclusion: Based on the analyzed results, several traffic management measures have been suggested to enhance traffic safety and reduce traffic congestion in front of school gates. In addition, the results of the study will provide a useful reference for policymakers and authorities.


2019 ◽  
Vol 11 (20) ◽  
pp. 5556
Author(s):  
Longhai Yang ◽  
Xiqiao Zhang ◽  
Xiaoyan Zhu ◽  
Yule Luo ◽  
Yi Luo

Novice drivers have become the main group responsible for traffic accidents because of their lack of experience and relatively weak driving skills. Therefore, it is of great value and significance to study the related problems of the risky driving behavior of novice drivers. In this paper, we analyzed and quantified key factors leading to risky driving behavior of novice drivers on the basis of the planned behavior theory and the protection motivation theory. We integrated the theory of planned behavior (TPB) and the theory of planned behavior (PMT) to extensively discuss the formation mechanism of the dangerous driving behavior of novice drivers. The theoretical analysis showed that novice drivers engage in three main risky behaviors: easily changing their attitudes, overestimating their driving skills, and underestimating illegal driving. On the basis of the aforementioned results, we then proposed some specific suggestions such as traffic safety education and training, social supervision, and law construction for novice drivers to reduce their risky behavior.


Transport ◽  
2015 ◽  
Vol 32 (1) ◽  
pp. 13-22 ◽  
Author(s):  
Angelo Stephen Cardamone ◽  
Laura Eboli ◽  
Carmen Forciniti ◽  
Gabriella Mazzulla

Road accidents have a relevant impact in terms of economic and social costs. As a consequence, many research studies have focused on identifying the key factors affecting accident severity. Traditionally, these factors can be included in the infrastructural, human and vehicle groups. Among these, human factors have a relevant impact on accident severity, which depends on driving experience, driver’s socio-economic characteristics, and driving behaviour, but also on the driver’s psychological state while driving. In this paper we investigate on the relationships between driving behaviour usually taken by the driver and his/her perceived psychological state while driving. In order to achieve this goal we adopt an Ordered Probit (OP) model formulation calibrated on the basis of experimental data collected by a sample survey. We demonstrate that the adopted methodology accounts for the differential impacts of certain human factors on driver’s psychological state.


Entropy ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. 360 ◽  
Author(s):  
Serafín Moral-García ◽  
Javier Castellano ◽  
Carlos Mantas ◽  
Alfonso Montella ◽  
Joaquín Abellán

Presently, there is a critical need to analyze traffic accidents in order to mitigate their terrible economic and human impact. Most accidents occur in urban areas. Furthermore, driving experience has an important effect on accident analysis, since inexperienced drivers are more likely to suffer fatal injuries. This work studies the injury severity produced by accidents that involve inexperienced drivers in urban areas. The analysis was based on data provided by the Spanish General Traffic Directorate. The information root node variation (IRNV) method (based on decision trees) was used to get a rule set that provides useful information about the most probable causes of fatalities in accidents involving inexperienced drivers in urban areas. This may prove useful knowledge in preventing this kind of accidents and/or mitigating their consequences.


2019 ◽  
Vol 11 (4) ◽  
pp. 1168 ◽  
Author(s):  
Shi Niu ◽  
Yan Liu ◽  
Lin Wang ◽  
Hai Li

The objective of this work is to examine the human response to different interventions to determine its direct intervention effect and education effect on the speeding of novice drivers. Several experiments, in which participants received different interventions when they were speeding, were conducted on the simulating driving system. The direct intervention effect of different intervention methods was measured by speed reduction and the education effect of voice intervention was measured by questionnaires. A total of 60 novice drivers and 20 experienced drivers were involved in this study, and the personality, gender and driving experience were considered in the analysis. We found that the steer wheel vibration has a significant influence on the intervention effect, but the lighting does not. The driving experience has more impact on the intervention effect of voice intervention with the Rational Style. While gender mainly influences the intervention effect of Emotional Style. The education effect of voice intervention designed with Emotional Style performs better than Rational Style. The personality from Eysenck Personality Questionnaire (EPQ) does not have a significant influence on the intervention effect. At last, a new driving style variable which can be calculated automatically from driving data was designed and the novel intervention strategy was proposed according to the research results. Our research provides a novel intervention strategy for drivers’ speeding behavior and gives an underlying insight into urban traffic safety, which is beneficial to ensure the safety, efficiency, and sustainability of the transportation system. It also serves as a reference for traffic safety research management agencies, the government, and the produced smart vehicles companies, providing guidance not limited to speeding intervention and aimed at improving other unsafe driving behavior.


Author(s):  
Khair Jadaan ◽  
Noor Albeetar ◽  
Dania Abuhalimeh ◽  
Yara Naji

A key component in combating traffic accidents is to study the contributory factors behind them, among these factors, the driver behavior stands out as the main causative factor. One of the most effective tools used worldwide in measuring self-reported driving components is the Manchester Driver Behavior Questionnaire (DBQ), it investigates the relationship between the driver and accidents involvement, throughout the analysis of both sociodemographic characteristics of drivers, and the risky driving components practiced such as; violations, errors and lapses. The present study investigates the factor structure of the DBQ and examines the relationships between the driver behavior factors and accident involvement. A survey questionnaire including the DBQ and background information was filled by a randomly selected sample of drivers in Amman, the capital of Jordan and the Statistical Package for Social Sciences (SPSS) software was used for data analysis. Driver behavior differed according to the gender, educational level and driving experience of the respondents. The results reflected the lifestyle, way of thinking and the general attitude of the driver and its relationship with traffic safety.


Author(s):  
Dmitrii Novgorodov ◽  
Aleksandr Tarasov

The research object is social relations connected with the admission of novice drivers to traffic on roads and the issue of driver’s licences. The research subject is the set of normative acts of the Russian Federation regulating the admission of drivers to traffic on roads, and the statistical data of the State Road Safety Unit on road accidents with novice drivers whose driving experience is up to 2 years. The authors analyse road accidents with novice drivers, identify the main reasons of accidents and offer the solutions to these problems. The scientific novelty of the research consists in the fact that the analysis of traffic accidents helped to outline the problems that should be solved within the shortest possible time in order to reduce the number of road accidents caused by novice drivers. In this context, the authors suggest introducing changes into the legislation of the Russian Federation which would allow for the declaration of driver’s licences issued in other states invalid, as well as the exchange of non-Russian driver’s licences for Russian ones only after adequate training and passing the exams. Besides, the authors suggest introducing the possibility for juveniles who passed the exams to drive a vehicle before they arrive the age of 18 with particular restrictions and accompanied by an experienced driver.   


Sign in / Sign up

Export Citation Format

Share Document