Risk Of Traffic Accidents Research Articles

Paediatric e-scooter riders at high risk of life-threatening traffic accidents.

This study presents the epidemiology and the development of e-scooter and non-electric scooter injuries in children and adolescents to highlight the nature and the severity of such injuries. All children and adolescents with electric or non-electric scooter related injuries between January 2019 until December 2022 were included in this single-centre study and retrospectively evaluated. An epidemiological overview including age, sex, type of scooter, injury mechanism, diagnosed injuries and surgical interventions were presented. Further, statistical comparisons of the means and proportions of injuries and the number of surgical interventions between electric and non-electric scooter riders were made. The study consists of 633 children and adolescents (9.1 ± 5.0 years; 231 female, 36.5%, 402 male, 63.5%). 80.1% (8.0 ± 4.1 years) used non-electric scooters, while 19.9% (14.2 ± 4.1 years) used e-scooters. In comparison, adolescent e-scooter riders were significantly more likely to be involved in traffic accidents (non-electric scooter: 16/507; e-scooter: 21/126; p = 0.0001) and suffered severe head injuries more often (non-electric scooter: 8/134; e-scooter: 7/37; p = 0.0217) than patients riding non-electric scooters. Adolescent e-scooter riders were more likely to be involved in potentially life-threatening traffic accidents having a higher risk of severe head injuries requiring surgery compared to non-electric scooter riders. Adolescent e-scooter riders have a higher risk to be involved in potentially life-threatening traffic accidents than riders of non-electric scooters. E-scooter riders have a higher risk of sustaining serious head injuries requiring surgical intervention than non-electric scooter riders. The data highly recommends the implementation of prevention strategies especially educating youth and parents and wearing protective clothing. Legislation and law enforcement could help prevent such injuries and potentially life-threatening traffic accidents involving children and adolescents who ride e-scooters.

Road Defect Identification and Location Method Based on an Improved ML-YOLO Algorithm

The conventional method for detecting road defects relies heavily on manual inspections, which are often inefficient and struggle with precise defect localization. This paper introduces a novel approach for identifying and locating road defects based on an enhanced ML-YOLO algorithm. By refining the YOLOv8 object detection framework, we optimize both the traditional convolutional layers and the spatial pyramid pooling network. Additionally, we incorporate the Convolutional Block Attention to effectively capture channel and spatial features, along with the Selective Kernel Networks that dynamically adapt to feature extraction across varying scales. An optimized target localization algorithm is proposed to achieve high-precision identification and accurate positioning of road defects. Experimental results indicate that the detection accuracy of the improved ML-YOLO algorithm reaches 0.841, with a recall rate of 0.745 and an average precision of 0.817. Compared to the baseline YOLOv8 model, there is an increase in accuracy by 0.13, a rise in recall rate by 0.117, and an enhancement in average precision by 0.116. After the high detection accuracy of road defects was confirmed, generalization experiments were carried out on the improved ML-YOLO model in the public data set. The experimental results showed that compared with the original YOLOv8n, the average precision and recall rate of all types of ML-YOLO increased by 0.075, 0.121, and 0.035 respectively, indicating robust generalization capabilities. When applied to real-time road monitoring scenarios, this algorithm facilitates precise detection and localization of defects while significantly mitigating traffic accident risks and extending roadway service life. A high detection accuracy of road defects was achieved.

Development of micromodels for improvements in driving safety using as a case study a university campus in Panama

This research focuses on addressing critical driving safety issues on university campuses, particularly vehicular congestion, inadequate parking, and hazards arising from the interaction between vehicles and pedestrians. These challenges are common across campuses and demand effective solutions to ensure safe and efficient mobility. To address these issues, the study developed detailed microsimulation models tailored to the Victor Levi Sasso campus of the Technological University of Panama. The primary function of these models is to evaluate the effectiveness of various safety interventions, such as speed reducers and parking reorganization, by simulating their impact on traffic flow and accident risk. The models provide calculations of traffic parameters, including speed and travel time, under different safety scenarios, allowing for a comprehensive assessment of potential improvements. The results demonstrate that the proposed measures significantly enhance safety and traffic efficiency, proving the model’s effectiveness in optimizing campus mobility. Although the model is designed to tackle specific safety concerns, it also offers broader applicability for addressing general driving safety issues on university campuses. This versatility makes it a valuable tool for campus planners and administrators seeking to create safer and more efficient traffic environments. Future research could expand the model’s application to include a wider range of safety concerns, further enhancing its utility in promoting safer campus mobility.

Design System of Solar-Powered Safety Lamp Integrated Proximity Sensor as a Solution for Accident Prevention at Blind Spot Areas

The curved contour of the road creates blind spots which increase the risk of traffic accidents. Throughout 2019, there were 107,500 accident cases recorded in Indonesia. Therefore, efforts are needed to provide road infrastructure that supports driving safety, such as traffic signs to reduce the risk of accidents in blind spot areas. This research aims to design a smart safety light warning system that is integrated with solar-based street lighting. The design uses a design-based research approach referring to several established standards including Indonesia National Standard (SNI) 7931: 2008, SNI IEC 60529:2014, Regulation of the Minister of Transportation of the Republic of Indonesia Number PM 13 of 2014, Manual on Uniform Traffic Control Devices (MUTCD) issued by the Federal Highway Administration (FHWA) of the United States Department of Transportation (USDOT), and Article 115 of Minister of Transportation Republic of Indonesia Regulation PM 27 of 2018. This study used Design-Based Research (DBR) as a research methodology. The result of this study is a prototype design and development of smart safety light warning system which can be optimized. Validation of the design and circuit is conducted using prototyping modeling 1:20 from the original dimensions to measure the function and performance of the circuit. The prototype is capable of turning on warning lights and siren notifications when detecting objects with a maximum distance of 350 cm as measured by the HC – SR04 sensor. Charging the stored solar panels via the accumulator allows the technology to continue working for 45 hours without charging. For power efficiency purposes, the technology is equipped with an LDR (Light Dependent Resistor) sensor with a minimum limit of 341-lux which regulates the lighting. The development of these safety lights will increase driver awareness when passing through blind spot areas and have positive implications for reducing the number of accidents in Indonesia.

A study of the relation between traffic accidents and election posters

Inattention in traffic is a risk factor for the occurrence of accidents. Elements surrounding traffic could potentially be a safety risk for road users. This study investigates the relation between election posters and traffic accidents using a seasonal autoregressive-moving-average model with exogeneous variables (seasonal ARMAX) correcting for variations in meteorological conditions and general traffic volume indicated through public holidays. Danish traffic accident micro data are used to construct a time series for daily number of accidents in city zones adjusted for probable known accident causes, namely drunk driving, narcotics, drivers deemed unfit to drive, and accidents related to low visibility. Model parameters are determined from Maximum Likelihood estimation on the period from 1 January 1997 to 15 December 2009 with an indicator for general election periods. The presence of general election posters is associated with an increased risk of traffic accidents (p = 0.003), when correcting for meteorological variables and public school holidays. While a causal relation between traffic accidents and the presence of election posters cannot be concluded from the analysis, we find distraction from election posters to be the most likely explanation for the associated increase in traffic accidents. On average, the model indicates that 1.18 additional daily accidents occur for general elections in Denmark. In total, that amounts to 127 additional accidents for the investigated period of time. This study shows that such sudden changes in traffic surroundings are significantly related to increased safety risks which could lead to a better discussion of relevant traffic legislation.

Multimodal Dataset Construction and Validation for Driving-Related Anger: A Wearable Physiological Conduction and Vehicle Driving Data Approach

Anger impairs a driver’s control and risk assessment abilities, heightening traffic accident risks. Constructing a multimodal dataset during driving tasks is crucial for accurate anger recognition. This study developed a multimodal physiological -vehicle driving dataset (DPV-MFD) based on drivers’ self-reported anger during simulated driving tasks. In Experiment 1, responses from 624 participants to anger-inducing videos and driving scenarios were collected via questionnaires to select appropriate materials. In Experiments 2 and 3, multimodal dynamic data and self-reported SAM emotion ratings were collected during simulated and real-vehicle tasks, capturing physiological and vehicle responses in neutral and anger states. Spearman’s correlation coefficient analysis validated the DPV-MFD’s effectiveness and explored the relationships between multimodal data and emotional dimensions. The CNN-LSTM deep learning network was used to assess the emotion recognition performance of the DPV-MFD across different time windows, and its applicability in real-world driving scenarios was validated. Compared to using EEG data alone, integrating multimodal data significantly improved anger recognition accuracy, with accuracy and F1 scores rising by 4.49% and 9.14%, respectively. Additionally, real-vehicle data closely matched simulated data, confirming the dataset’s effectiveness for real-world applications. This research is pivotal for advancing emotion-aware human–machine- interaction and intelligent transportation systems.

Major injuries and associated factors in traffic accidents among motorcycle food delivery riders during the COVID-19 pandemic in Thailand

Motorcycle food delivery riders (MFDRs) are at a higher risk of traffic accidents compared to regular motorcyclists. Their safety is a significant issue in many developing countries, particularly in Thailand, which has the highest rate of motorcyclist fatalities globally. This study aimed to determine the prevalence of traffic accidents and explore the association between risky riding behaviors, concerns for working conditions, and accidents among MFDRs. This cross-sectional study was conducted in Chiang Mai, Thailand. Data were collected from a total of 709 MFDRs through an online platform. Collected data included working conditions, risky riding behaviors, concerns about their work conditions, and experience with traffic accidents. In the past six months, the incidence of traffic accidents among MFDRs was 18.9 %., with 2.4 % experiencing hospitalized major injuries, 11.4 % having non-hospitalized major injuries, and 5.1 % having minor injuries. A total of 84.3 % of MFDRs exhibited at least one risky riding behavior, while 5.8 % engaged in ten or more such behaviors. Multivariable logistic regression analysis with adjustments for sex, age, and body mass index indicates that red-light running (adjusted odds ratio, aOR 2.78, 95 % CI 1.07 to 7.21) and being concerned for customer behaviors (aOR 2.66, 95 % CI 1.26 to 5.62) were significantly associated with major injuries. Additionally, factors such as sleeping less than 6 h per day (aOR 1.68, 95 % CI 1.10 to 2.56), riding the wrong way (aOR 2.49, 95 % CI 1.12 to 5.52), and having concern for customer behaviors (aOR 1.91, 95 % CI 1.03 to 3.55) were associated with total number of accidents. Red-light running and concerns for customer behavior in MFDRs are associated with a higher risk of traffic accidents with major injuries. Effective strategies and interventions should focus on strengthening the enforcement of traffic risk behaviors and encouraging food delivery companies to establish regulations relating to the workers’ concerns.

Mapping the relationship between traffic accidents, road network configuration, and urban land use

Understanding the nature of traffic accidents in relation to urban access networks is crucial for building safer and more resilient cities. This paper examines the issue of traffic accidents through the lenses of urban configurational theory and urban land use. Three data layers were used in the study, including space syntax analysis conducted in Depthmap X, geotagged traffic accidents collected by the police department, and geotagged land-use data. The method involved superimposing these data layers and exploring potential correlations using a geographic information system (GIS). The findings indicate significant correlations between the spatial frequency of traffic accidents and the choice measure (at 2500 m), local integration, and active land use. The findings of this study can help inform planners and policymakers about the best location to implement safety measures to reduce the risk of traffic accidents in urban access networks.

Real-time accident risk identification for freeway weaving segments based on video analytics

Accurately identifying the risk of traffic accidents in real time for specific road sections is crucial for implementing proactive traffic control strategies. The existing studies have focused on real-time prediction of collisions between two vehicles, identification of accident risks on road segments relies heavily on historical accident data. This study proposes a framework for identifying road section accident risks at the granular level by utilizing traffic conflicts as an intermediary. In this framework, vehicles are detected and tracked in real time and the pixel coordinates are then efficiently converted into world coordinates based on the camera projection principle. A binary logit model is constructed to identify road section accident risks using carefully selected macroscopic traffic flow parameters. The proposed framework was validated on two one-sided ramp weaves in Jinan, China, achieving an accuracy of 76.2 %. The findings will serve as a foundation for traffic safety monitoring and proactive traffic control.

Traffic Accidents: The Contrasting Roles of Life Satisfaction and Anxiety

AbstractIt is well established that people with low subjective wellbeing have heightened traffic accident risk. However, the roles of particular mental states, including overall evaluative subjective wellbeing and specific forms of mental distress such as depression or anxiety, have not hitherto been disentangled. Using an official representative population survey, we show that different forms of mental distress are associated with single versus multiple accident prevalence within a year. Anxiety (a lack of calmness) is strongly associated with having an accident. By contrast, conditional on having had at least one accident, overall life satisfaction is more strongly associated with having multiple accidents than are anxiety, depression or overall mental health. The relationship is n-shaped so that people with moderately low wellbeing have the highest multiple accident probability. These results are robust to the exclusion of respondents for whom reverse causality may be present and to the inclusion of variables representing other risky behaviours and representing social isolation. The findings imply that specific forms of intervention are likely to be needed to reduce accidents for people with moderately low subjective wellbeing who may engage in habitual risky behaviours that result in multiple accidents.

Work stressors and aggressive driving: The mediating roles of stress appraisals

While the association between work stressors and the risk of traffic accidents and driving lapses has been established, there is a lack of research exploring the relationship between work stressors and aggressive driving—a notable contributor to traffic incidents and injuries. To fill this gap, the present study utilized the challenge-hindrance stressor framework and the transactional theory of stress to investigate the effects of these stressors on aggressive driving behaviors, with a particular focus on the mediating roles of challenge and hindrance appraisals. We used time-lagged design and gathered self-reported data from 247 employees at a Chinese company over three distinct time points. The results of structural equation modeling indicated that both challenge and hindrance stressors are positively associated with aggressive driving, with their effects mediated by corresponding appraisals of challenge and hindrance. Notably, challenge appraisals were inversely related to aggressive driving. Our study is one of the first attempts to explore the relationship between work stressors and aggressive driving, underscoring the critical role of stress appraisals in understanding responses to stressors.

Comparison of Energy Absorptive Capacities of Different Aluminum Alloy Foams Placed Inside the Crash Box

Increasing population worldwide and the resulting increasing number of automobiles increase the risk of traffic accidents. Due to this increasing risk, automobile manufacturers take various safety measures to protect drivers and passengers in case of possible accidents. Crash boxes are one of the passive safety system elements that are the first to absorb the impact in the event of a front or rear impact accident, absorbing the resulting deformation energy and ensuring that it is transmitted into the car at the least possible level. Therefore, increasing the energy absorption ability of crash boxes is an extremely important issue. In this study, it was aimed to increase the energy absorption capabilities by placing aluminum foam based materials produced by using the powder metallurgy method using three different aluminum alloys (Al2024, Al5083, and Al6061) inside the crash boxes, which are normally manufactured as hollow. In addition, the produced aluminum foams were compared in terms of pore sizes with SEM images. It can be said that Al6061 is the most ideal material among the alloys used in terms of pore structure and homogeneity. On the other hand, Al6061 alloys produced the greatest damped energy value within the parameters of the investigation, 221.711 J. This value was 169.556 J for Al2024 alloy and 214.101 J for Al5083 alloy. As a result, it was concluded that the amount of energy absorption can be increased by about 4-5 times by using metallic foams produced using aluminum materials compared to the empty crash box.

Perceived Traffic Risk on Road Infrastructure Conditions among Car Drivers in Lhokseumawe City, Aceh, Indonesia

According to the Indonesian Department of Transportation, 86% of traffic accidents are attributed to human factors. Additionally, road conditions are identified as a contributing factor to road accidents. Therefore, this study aimed to explore road conditions and their impact on the driving behaviour of car drivers. Data for this exploration were collected by distributing questionnaires to 200 respondents, utilizing a Likert scale for answer options. The technique used was random sampling, utilizing descriptive statistical analysis and a Confirmatory Factor Analysis model. Consequently, the result showed that each latent variable construct examined by car drivers had a value exceeding 80%. The most prominent latent variable was the "Condition of Road Surface Facilities," accounting for 88.1% and featuring eight indicators. The indicator "Disturbed when passing through a narrow road," part of the latent variable "Condition of Road Equipment Facilities," had the highest standardized value at 1.223. Finally, this study suggested that the government should prioritize attention to road infrastructure conditions to enhance driver comfort and mitigate the risk of traffic accidents.

Reviewing the prevalence of refractive errors and color blindness among commercial drivers

Road traffic crashes pose a significant global public health concern, claiming the lives of approximately 1.19 million people each year. A worrisome trend surfaces as a considerable majority of these fatalities involve vulnerable road users, encompassing not only drivers of heavy and light vehicles but also pedestrians, cyclists, and motorcyclists. Visual impairments play a significant role in these tragic events, further exacerbating the risks faced by road users. Whether due to poor eyesight or other vision-related challenges, impaired visual perception contributes to the vulnerability of individuals on the road. This review aimed to systematically analyze the currently available research and articles to determine the prevalence of color vision defects and refractive errors among commercial drivers. The primary objective was to investigate whether refractive errors and color vision defects pose a risk factor for road safety among commercial drivers. A primary search of databases including PubMed, Google Scholar, and others was conducted using relevant keywords. Articles published between 2010 and 2023 were considered, resulting in 16 cross-sectional studies being included for analysis. Prevalence rates were calculated using weighted averages based on sample sizes. Among commercial drivers, the prevalence of color vision impairment was lower (4.35%) compared to refractive errors (23.42%). Individuals with protanopia were at higher risk of road traffic accidents (RTAs). Complex issues such as alcoholism and visual impairments contributed to higher RTA frequencies in certain populations, emphasizing the multifaceted nature of road safety challenges.

Improving train services to increase student mobility and safety on the Purwakarta-Karawang route

Transportation is essential for the mobility of workers and students, yet many prefer motorcycles over public transportation like trains due to inadequate schedules and limited train availability. This choice contributes to Indonesia's high motorcycle usage and associated traffic accident risks. This study focuses on the Purwakarta-Karawang train route and its impact on student mobility at Universitas Singaperbangsa Karawang. Employing a qualitative method with descriptive data collection and SWOT analysis, this research gathers student feedback on current train schedules and their impact on daily commutes. Findings indicate that increasing the number of train schedules could significantly improve student mobility and reduce the reliance on motorcycles, thereby decreasing traffic accidents. Moreover, better train schedules could enhance access to educational and employment opportunities. The study suggests that the local government should consider expanding and optimizing train services to address these issues. This research contributes to the broader field of transportation studies by highlighting the importance of efficient public transport schedules in reducing traffic accidents and supporting student mobility. It emphasizes the need for policy adjustments to improve Indonesia's public transportation infrastructure and services by proposing practical solutions.

Exploring the effects of traffic light countdown displays on the driving behaviours of drivers with different personality dispositions: A VR-simulated study

The dilemma zone, where drivers must decide whether to stop or proceed through an intersection as a traffic signal turns yellow, poses a substantial risk for traffic accidents. One factor affecting the dilemma zone is the inconsistency of green light countdown displays across intersections. This VR simulation study aims to investigate how different countdown display settings impact driver behaviour in the dilemma zone. Using a simulated traffic intersection developed using Unity3D, 31 participants completed driving tasks under 5 different green light countdown displays. Vehicle speeds were collected objectively in the experiments. Questionnaires were employed to assess drivers' hesitation levels and personality dispositions. The results from the statistical analysis reveal that drivers with diverse personality dispositions exhibited consistent hesitation levels across countdown displays. While longer countdown displays tended to reduce drivers' hesitation, the countdowns set between 5-10 seconds resulted in lower vehicle speeds through the intersection compared to other shorter or longer settings. This indicates that the optimal green light countdown display for mitigating the dilemma zone is 5-10 seconds. Findings of the study provide useful insights into the relevant research field. Transportation departments may apply these findings to improve driver safety, refine policies, and standardise countdown timers across intersections.

Research on deep learning models and data preprocessing techniques for driver fatigue detection

Detecting signs of fatigue while driving is one of the most important and urgent issues in today's modern transportation system. Early detection and warning will significantly reduce the risk of traffic accidents. To accomplish this, several methods have been proposed. In recent years, methods based on deep learning techniques have attracted great attention due to their high efficiency and cost savings in detecting and warning about signs of fatigue while driving. In this paper, we study a method to improve the accuracy of deep learning models based on the data preprocessing technique, applied to detect signs of fatigue while driving. Data preprocessing helps the training images become more accurate, noise-reduced, diverse and rich instead of just using the main image. To ensure high reliability and accuracy, the methods are trained and tested on large datasets including thousands of images of all types. Experimental results show that the combination of the VGG-16 model and the data augmentation technique gives better results than the traditional deep learning model, with an accuracy of over 96%.

Identifying the vehicle accident models based on driving behavior factors using structural equation modeling

The increase in population is accompanied by an increase in the number of vehicles. It is inevitable that the number of vehicle accidents will also increase, which can be caused by various factors. Driver factors reviewed in this study include socioeconomic characteristics, movement characteristics, accident characteristics, and driver behavior characteristics. the purpose of this study is to study the vehicle accident model using interviews and Driving Behavior questionnaires with a total of 307 motorist respondents who have experienced accidents. Driver factors reviewed in this study include socioeconomic characteristics, movement characteristics, accident characteristics, and driver behavior characteristics using interviews and Driving Behavior questionnaires with a total of 307 motorist respondents who have experienced accidents. This investigate used SEM (Structural Equation Modeling) with SmartPLS computer software. Two-wheeled vehicle accident modeling results Y=–0.234 X1+0.153 X3+ei2; R2=0.102. The greatest influence occurs in the characteristics of driver behavior (X3), namely Ordinary Violation, and for four-wheeled vehicle accident modeling results, Y=–0.343 X1+0.284 X3+ei2; R2=0.217. The greatest influence occurs in driver behavior characteristics (X3), namely Ordinary Violation. Ordinary Violation is defined as a deliberate deviation from the rule of law. Thus, from the research results, the most influential variable was the behavior of drivers who committed ordinary violations such as ignoring speed limits, breaking through intersections, and driving under the influence of alcohol. So, there needs to be collaboration between the police and related parties in tackling accidents and reducing the risk of traffic accidents, such as long as socialization or information through newspapers or electronic media to the public in Jayapura City regarding the importance of collective awareness of driving safety

Factors, Prediction, and Explainability of Vehicle Accident Risk Due to Driving Behavior through Machine Learning: A Systematic Literature Review, 2013–2023

Road accidents are on the rise worldwide, causing 1.35 million deaths per year, thus encouraging the search for solutions. The promising proposal of autonomous vehicles stands out in this regard, although fully automated driving is still far from being an achievable reality. Therefore, efforts have focused on predicting and explaining the risk of accidents using real-time telematics data. This study aims to analyze the factors, machine learning algorithms, and explainability methods most used to assess the risk of vehicle accidents based on driving behavior. A systematic review of the literature produced between 2013 and July 2023 on factors, prediction algorithms, and explainability methods to predict the risk of traffic accidents was carried out. Factors were categorized into five domains, and the most commonly used predictive algorithms and explainability methods were determined. We selected 80 articles from journals indexed in the Web of Science and Scopus databases, identifying 115 factors within the domains of environment, traffic, vehicle, driver, and management, with speed and acceleration being the most extensively examined. Regarding machine learning advancements in accident risk prediction, we identified 22 base algorithms, with convolutional neural network and gradient boosting being the most commonly used. For explainability, we discovered six methods, with random forest being the predominant choice, particularly for feature importance analysis. This study categorizes the factors affecting road accident risk, presents key prediction algorithms, and outlines methods to explain the risk assessment based on driving behavior, taking vehicle weight into consideration.

CycLight: Learning traffic signal cooperation with a cycle-level strategy

This study introduces CycLight, a novel cycle-level deep reinforcement learning (RL) approach for network-level adaptive traffic signal control (NATSC) systems. Traditional RL-based step-by-step traffic signal controllers, while precise and responsive, demand high computational resources for frequent data exchanges and can increase traffic accident risks due to disordered phase switching. Different from the step-by-step control strategy aforementioned, the proposed CycLight adopts a cycle-level strategy, optimizing cycle length and splits simultaneously using Parameterized Deep Q-Networks (PDQN) algorithm. This cycle-level approach effectively reduces the computational burden associated with frequent data communication, meanwhile enhancing the practicality and safety of real-world applications. Moreover, a decentralized framework is formulated for multi-agent cooperation, while attention mechanism is integrated to accurately assess the impact of the surroundings on the current intersection. CycLight is tested in a large synthetic traffic grid using the microscopic traffic simulation tool, Simulation of Urban MObility (SUMO). Experimental results not only demonstrate the superiority of CycLight over other state-of-the-art approaches but also showcase its robustness against information transmission delays.