Cause Of Traffic Crashes Research Articles

State space model detection of driving fatigue considering individual differences and time cumulative effect

Fatigue is an important cause of traffic crashes, and effective fatigue detection models can reduce these crashes. Research has found large differences in fatigued driving performance from driver to driver, as well as a significant cumulative effect of fatigue on a given driver over time. Both sources of variation can decrease the accuracy of detection systems, but previous studies have not done enough to evaluate these differences. The purpose of this study is therefore to develop a fatigue detection model that considers individual differences and the time cumulative effect of fatigue. Data on the lateral position of the car in its lane, steering wheel movement, speed, and eye movement were collected from 22 drivers using a driving simulator with an eye-tracking system. Drivers’ subjective fatigue scores were collected using the Karolinska Sleepiness Scale. State space models (SSMs) were built to detect fatigue in each driver, considering his or her individual features. As a time series model, the SSM can also address the time cumulative effect of fatigue, and it does not require a large dataset to achieve high levels of accuracy. The differences in SSM results confirm that diversity does exist among drivers’ fatigued driving performance, so the ability of the SSM to take into account driver-specific information from each individual driver suggests that it is more suitable for fatigue detection than models that use aggregated driver data. Results show that the fatigue detection accuracy of the SSM (77.73%) is higher than that of artificial neural network models (61.37%). The advantages of accuracy, high interpretability, and flexibility make the SSM a comprehensive and valuable individualized fatigue detection model for commercial use.

Understanding key contributing factors on the severity of traffic violations by elderly drivers: a hybrid approach of latent class analysis and XGBoost based SHAP

Traffic violation is one of the leading causes of traffic crashes. In the context of global aging, it is important to study traffic violations by elderly drivers for improving traffic safety in preparation for a worldwide aging population. In this study, a hybrid approach of Latent Class Analysis (LCA) and XGBoost based SHAP is proposed to identify hidden clusters and to understand the key contributing factors on the severity of traffic violations by elderly drivers, based on the police-reported traffic violation dataset of Beijing (China). First, LCA is applied to segment the dataset into several latent homogeneous clusters, then XGBoost based SHAP is established on each cluster to identify feature contributions and the interaction effects of the key contributing factors on the severity of traffic violations by elderly drivers. Two comparison groups were set up to analyze factors, which are responsible for the different severities of traffic violations. The results show that elderly drivers can be classified into four groups by age, urban or not, license, and season; factors such as less annual number of traffic violations, national & provincial highway, night and winter are key contributing factors for higher severity of traffic violations, which are consistent with common cognition; key contributing factors for all clusters are similar but not identical, for example, more annual number of traffic violations contribute to more severe violation for all clusters except for Cluster 2; some factors which are not key contributing factors may affect the severity of traffic violations when they are combined with other factors, for example, the combination of lower annual number of traffic violations and county & township highway contributes to more severe violation for Cluster 1. These findings can help government to formulate targeted countermeasures to decrease the severity of traffic violations by specific elderly groups and improve road service for the driving population.

Prediction of high-risk bus drivers characterized by aggressive driving behavior

Identification of driving behavior is a fundamental to developing effective treatments to address various traffic-related problems. In particular, the driving behavior of city bus drivers is of great interest because the crash severity can become much higher than any other vehicle types due to the larger number of passengers on board. However, there is a lack of effective policy preparation to prevent crashes because of limitations associated with identifying intrinsic factors underlying the cause of traffic crashes based on driving behavior analysis. This study aims to develop a methodology to predict high-risk bus drivers, which can be a baseline in establishing effective bus safety policies. An in-depth questionnaire survey was conducted to collect wellness data to represent intrinsic characteristics used for inputs of the proposed prediction methodology in addition to the aggressive driving behavior data obtained from in-vehicle data recorders. Bus drivers were classified into two groups, normal drivers and risky drivers, based on aggressive driving behavior. The priority of intrinsic factors was determined by a gradient boosting method and further utilized to derive input features of the proposed method. Deep-learning-based neural network models were evaluated to predict risky bus drivers in this study. A model with variables up to 11th priority as inputs was selected as the best model. A classification accuracy of 85% was achievable with the proposed model. The outcome of this study would be valuable in supporting policymaking activities to prevent aggressive driving behavior.

Drunk driving policies and breath test refusal in Taiwan

Objective Driving under the influence (DUI) is one of the major causes of traffic crashes in Taiwan, leading to huge medical expenditures and human capital loss. Although the authorities have enacted several policies to reduce drunk driving, most penalties are based on drunk drivers’ alcohol levels. According to Taiwan regulations, drivers could pay a fine to refuse the breath test if they are not involved in a traffic collision, and there is no clear evidence showing that they are DUI. Therefore, increased sanctions for DUI may lead to increased breath test refusals. If breath tests for drunk driving could be refused with little or no punishments for drivers, then the detection of behavioral impairment would weaken, and the deterrent effect of DUI punishment would be limited. Method This research uses interrupted time-series analysis (ITSA) to examine how policy reforms from 2007 to 2020 affected driver’s breath refusal rate in Taiwan. Results We find that said reforms that exclusively increase the punishment of DUI offenders did raise the refusal rate immediately and persistently, suggesting that more drunk drivers would refuse a breath test to avoid more severe DUI punishment. Policy reforms that increase penalties for drivers refusing to take breath tests may instantly lower the refusal rate, but the long-term effects are contingent upon the DUI punishment. Conclusions It appears that drunk drivers could still decide on breath test refusal to avoid a DUI conviction if the punishment for refusing the test is less severe than that for DUI. Aggravating penalties for refusing breath tests would decrease the refusal rate and help reinforce DUI’s deterrent effect.

A Review of The Relationship Between Speed and Road Safety

Despite research showing a connection between vehicle speed and crash severity and risk, the leading cause of traffic crashes and fatalities worldwide continues to be driving at speeds that are illegal or unsuitable. An overview of the relationship between vehicle speed and road safety in relation to crash involvement and crash severity is given in this study. Additionally, it examines and emphasizes the Power Model's applicability and effectiveness in projecting safety gains from speed increases. According to the paper's summary, there is still a significant association between speed and road safety. Yet, because of the moderating effects of several factors, it is difficult to quantify the exact relationship between speed and crash rate and injury severity. But it is generally acknowledged that speed both directly and indirectly affects crash rates and raises the severity of damage or fatality.

A temporal analysis of crash injury severities in multivehicle crashes involving distracted and non-distracted driving on tollways

Distracted driving is a prominent cause of traffic crashes and may increase the severity of collisions. Due to the larger speeds on toll ways, distracted driving crashes are more severe than on other types of roads, making it worthwhile to investigate. This study examined the variation in the influence of factors affecting injury severity in crashes involving distracted and non-distracted driving, as well as the change over time, using crash data from Florida toll ways from the 2017 to 2019. A series of random parameters logit models with heterogeneity in the means and variances were developed to analyze different driver-injury severities (no injury, minor injury, and severe injury) in crashes involving distracted and non-distracted driving. In addition, likelihood ratio tests were conducted to determine whether model parameters differed between different driver behaviors (distracted/non-distracted driving) and among years. Several factors potentially impacting injury severities were studied, including driver, crash, vehicle, roadway, environment, temporal, and others. Significant disparities were observed between the contributing factors of the severity of crashes involving distracted and non-distracted driving. Results showed that considerable differences were also observed in the severity of injuries caused by two types of crashes and distracted driving resulted in more serious crashes than non-distracted driving. Despite model results indicated that factors influencing injury severity altered over time, several factors, such as motorcycle involvement and commercial car involvement, still exhibited relative temporal stability in non-distracted driving crashes over the three years. Temporal instability and non-transferability were also captured by out-of-sample predictions to verify the temporal shifts of contributing variables from year to year. This study is useful for distinguishing the influence mechanisms between the two types of crashes involving distracted and non-distracted driving, and the results can be applied for safety countermeasures development.

Analysis of pedestrian violations based on an integrative model: Evidence from college students in China

IntroductionWalking is a popular mode of transportation for college students. A disproportionate number of traffic-related fatalities and injuries involve pedestrians. The violation of traffic laws is a significant cause of traffic crashes. Few studies have analyzed the walking violation behavior of Chinese college students. Therefore, it is essential to examine the factors that influence college students’ intention to engage in walking violation behaviors. MethodsThree models were used to analyze college students’ walking violations. In Model 1, the theory of planned behavior (TPB) was analyzed; In Model 2, the health belief model (HBM) was analyzed; In Model 3, the integrative model that considered exogenous constructs in the TPB, exogenous constructs in the HBM, and descriptive norm was analyzed. ResultsThe HBM has a moderately larger power than the TPB in explaining behavioral intention's variance, and the integrative model has a slightly larger power than the HBM in explaining behavioral intention's variance. Attitude, subjective norm, perceived severity, perceived benefit, and descriptive norm have significant impacts on behavioral intention to violate traffic rules, while perceived behavioral control, perceived susceptibility, perceived barrier, and cues to action do not have significant impacts. ConclusionsThe findings of this study could be used to explain pedestrian violation behaviors among Chinese college students and encourage them to obey traffic rules.

Influence of Risky Driving Behavior and Road Section Type on Urban Expressway Driving Safety

The causes of traffic crashes are complex and uncertain, among which the risky driving behaviors of drivers and the types of road sections in high-crash areas are all critical influencing factors. We used ArcGIS software to draw traffic heat maps under different thresholds to prevent the occurrence of traffic crashes accurately and effectively according to the vehicle GPS data of urban expressways in Jinan City, Shandong Province. This paper studied the relationship between risky driving behaviors (rapid acceleration, rapid deceleration, and overspeed) and road types with traffic crashes. The traffic safety evaluation model of urban expressways based on ordered logistic was established to predict the safety level of the urban expressway. The model’s accuracy was 85.71%, and the applicability was good. The research results showed that rapid deceleration was the most significant influencing factor of crashes on urban expressways. When the vehicle deceleration was less than or equal to −4 m/s2, the probability of a crash was 22.737 times greater than when the vehicle deceleration was at −2 to −2.5 m/s2; when the vehicle acceleration was greater than or equal to 3 m/s2, the probability of a crash was 19.453 times greater than when the vehicle acceleration was at 1 to 1.5 m/s2. The likelihood of a crash at a road section with a ramp opening was 8.723 times greater than that of a crash at a non-ramp opening; the crash probability of a speeding vehicle was 7.925 times greater than that of a non-speeding vehicle; the likelihood of a crash on a curve was 6.147 times greater than that on a straight. The research results can provide adequate technical support for identifying high-risk sections of expressways and active early warning of traffic crashes.

Identifying Causes of Traffic Crashes Associated with Driver Behavior Using Supervised Machine Learning Methods: Case of Highway 15 in Saudi Arabia

Identifying the causes of road traffic crashes (RTCs) and contributing factors is of utmost importance for developing sustainable road network plans and urban transport management. Driver-related factors are the leading causes of RTCs, and speed is claimed to be a major contributor to crash occurrences. The results reported in the literature are mixed regarding speed-crash occurrence causality on rural and urban roads. Even though recent studies shed some light on factors and the direction of effects, knowledge is still insufficient to allow for specific quantifications. Thus, this paper aimed to contribute to the analysis of speed-crash occurrence causality by identifying the road features and traffic flow parameters leading to RTCs associated with driver errors along an access-controlled major highway (761.6 km of Highway 15 between Taif and Medina) in Saudi Arabia. Binomial logistic regression (BNLOGREG) was employed to predict the probability of RTCs associated with driver errors (p < 0.001), and its results were compared with other supervised machine learning (ML) models, such as random forest (RF) and k-nearest neighbor (kNN) to search for more accurate predictions. The highest classification accuracy (CA) yielded by RF and BNLOGREG was 0.787, compared to kNN’s 0.750. Moreover, RF resulted in the largest area under the ROC (a receiver operating characteristic) curve (AUC for RF = 0.712, BLOGREG = 0.608, and kNN = 0.643). As a result, increases in the number of lanes (NL) and daily average speed of traffic flow (ASF) decreased the probability of driver error-related crashes. Conversely, an increase in annual average daily traffic (AADT) and the availability of straight and horizontal curve sections increased the probability of driver-related RTCs. The findings support previous studies in similar study contexts that looked at speed dispersion in crash occurrence and severity but disagreed with others that looked at absolute speed at individual vehicle or road segment levels. Thus, the paper contributes to insufficient knowledge of the factors in crash occurrences associated with driver errors on major roads within the context of this case study. Finally, crash prevention and mitigation strategies were recommended regarding the factors involved in RTCs and should be implemented when and where they are needed.

Driver Drowsiness Detection Using Smartphone

Abstract: Transition state between being awake and asleep is called drowsiness. Driver drowsiness is the major cause of traffic crashes and financial losses. This abstract presents a mobile technology using smartphones to visual indicators of driver drowsiness, allowing the possibility of making drowsiness detection systems more affordable and portable. This technology uses the front camera of a smartphone to capture images of drivers, and then uses smartphone vision algorithms to detect and track the face and eye of the drivers. Eye blinks are then detected as indicators of driver drowsiness. A simulated driving study showed that drowsy drivers differed significantly in the frequency of and eye blinks, compared to when they were attentive. The smartphone-based Driver-Drowsiness detection technology may have important applications in reducing drowsiness-related improving driving safety. This abstract describes the steps involved in designing and implementing a driver drowsiness detection system based on smartphone. It combines off the-shelf smartphone components for eye state (open vs. closed) classification. Preliminary results show that the system is reliable and tolerant to many real-world constraints. Driver drowsiness is a highly problematic issue which impairs judgment and decision making among drivers resulting in fatal motor crashes. This describes a simple drowsiness detection approach for a smartphone with Android / IOS application using Android Studio 4.4.2. & Mobile Vision API for drowsiness detection before and while driving. Quick facial analysis were performed to check drowsiness before the driver starts driving. Facial analysis was undertaken by eye blinking duration. Blinking duration is used to indicator for drowsiness. A performance accuracy of drossiness detection proved to be around 90%.

The nudging effect of social norms on drivers’ yielding behaviour when turning corners

Drivers who do not give way to pedestrians are among the main causes of traffic crashes of motor vehicles and pedestrians in China. There is an urgent need to explore effective methods for improving drivers' yielding behaviour. This study used eight kinds of social norm slogans to nudge drivers’ yielding behaviour and explored the influence of pedestrian characteristics and situational factors on drivers’ decision-making regarding giving way when turning right. By analysing 254 valid questionnaires, it was found that compared with static norms, injunctive norms and dynamic + static norms, positively worded dynamic norms have a better nudging effect on drivers' yielding behaviour. The results of the conjoint analysis showed that social norms have the greatest impact on drivers' decisions to yield (32.28%), followed by whether pedestrians comply with traffic rules (23.33%) and the age of pedestrians (18.40%). This study expands the application of social norms and provides a new perspective to promote positive behaviour among drivers.

A Nonintrusive and Real-Time Classification Method for Driver’s Gaze Region Using an RGB Camera

Driver distraction has become a leading cause of traffic crashes. Visual distraction has the most direct impact on driving safety among various driver distractions. If the driver’s line of sight deviates from the road in front, there will be a high probability of visual distraction. A nonintrusive and real-time classification method for driver’s gaze region is proposed. A Multi-Task Convolutional Neural Network (MTCNN) face detector is used to collect the driver’s face image, and the driver’s gaze direction can be detected with a full-face appearance-based gaze estimation method. The driver’s gaze region is classified by the model trained through the machine learning algorithms such as Support Vector Machines (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN). The simulated experiment and the real vehicle experiment were conducted to test the method. The results show that it has good performance on gaze region classification and strong robustness to complex environments. The models in this paper are all lightweight networks, which can meet the accuracy and speed requirements for the tasks. The method can be a good help for further exploring the visual distraction state level and exert an influence on the research of driving behavior.

Effects of vehicle’s human machine interface devices on driving distractions

Driving distraction is an important cause of traffic crashes, as it diverts the driver’s attention away from the primary driving task. This paper studies the engagement frequency of drivers in distracting activities due to modern devices used in vehicle dashboards, to improve roadway safety. Data were collected from Jordanian drivers through two questionnaires. In the first, a wide range of distracting activities and their influence on crashes were considered. The focus of the second questionnaire was on factors affecting the driver’s distraction by the Human-Machine Interface (HMI) screens in vehicles. The collected data were analyzed statistically. Several significant factors were found that distract drivers, including but not limited to the use of HMI screens, the driver’s age, experience and occupation. This paper raises public awareness of the risks of distracted driving due to modern devices, in order to boost traffic safety.

Analysis of pedestrians’ behaviour: A segmentation approach based on latent variables

Crash statistics indicate that the number of pedestrian fatalities has been increasing at an alarming rate in Iran. Crossing over non-designed places is a main cause of traffic crashes among pedestrians. This study aimed to investigate how perceptions about walking facilities and risk-taking affect pedestrians’ crossing behaviour. A stated preference questionnaire was designed and a random sample of 390 pedestrians were interviewed face-to-face in two regions of Tehran with three options for pedestrians to cross (overpass, zebra crossing, and non-designed places (NDP)). Exploratory factor analysis (EFA) resulted in three latent dimensions: risk-taking/conformity, pedestrians’ perception of overpass, and NDP. Then, data were classified based on latent variables using K-means cluster analysis. Clustering resulted in four groups: group 1 (Cautious; negative perception of overpasses; positive perception of NDP), group 2 (Cautious; negative perception of overpasses; negative perception of NDP), group 3 (Cautious; positive perception of overpasses; negative perception of NDP), and group 4 (Risk-taker; negative perception of overpasses; negative perception of NDP). Finally, a Multinomial Logit Model (MNL) was developed for four groups of pedestrians. The results show that pedestrians’ behaviour differentiate based on latent variables. It was found that being accompanied by a child increases the probability of using an overpass even for pedestrians in group 4 with high risk-taking propensity, but it was more important for pedestrians in group 3 who held positive perceptions of overpasses and negative perceptions of NDP. Also, during congestion, group 4 was more inclined to cross at NDP. It was concluded that in the first group, unsafe choices among student respondents could be associated with their facility perceptions rather than their risk-taking/conformity. Results of this study can be helpful in selecting more appropriate locations for overpasses and crosswalks installation based on pedestrians’ behaviour.

An evaluation of highway crash-prone areas: A case study on Pan Borneo Highway in the state of Sarawak

Road traffic crashes is one of the major causes of death that needs to be addressed globally. Many studies have been conducted to identify the contributing factors to traffic crashes and to determine the required preventive measures. This study evaluates the causes of 164 traffic crashes along a 10 kilometres section of Pan Borneo Highway Sarawak. The study investigated the main causes of traffic crashes within this section of road through multiple sources: based on expert on site evaluation, analysis of site incident report and police accident record. The finding reveals that most of the accidents (93%) occurs during the daytime, weather contributes a combined 69% and private car owners (80%) cause most of the traffic crashes. The study also indicates that the road condition is a significant factor to the occurrence of traffic crashes in that area contributing 64% of the total crashes.

The influence of WeChat use on driving behavior in China: A study based on the theory of planned behavior

Driving has become common, and distracted driving, especially that caused by WeChat use, is a significant cause of traffic crashes. Based on the theory of planned behavior, this study analyzes self-reports from a sample of 286 drivers from China to explore the influence of different WeChat functions on driving behavior. The analyses reveal that the intention to use WeChat while driving can substantially predict the use of WeChat while driving. Moreover, drivers’ attitudes can effectively predict whether they will send texts, listen to voice messages, and send and browse pictures on WeChat while driving. However, drivers’ attitudes cannot effectively predict whether they will read texts or send voice messages on WeChat while driving. In recent years, WeChat has become a popular messaging software, and many drivers use it. Therefore, it is important and necessary to raise awareness among drivers about the dangers of using WeChat while driving.

Driver drowsiness detection using mixed-effect ordered logit model considering time cumulative effect

Drowsy driving is one of the main causes of traffic crashes, a serious threat to road traffic safety. The effective early detection of a drowsiness state can help provide a timely warning for drivers, but previous studies have seldom considered the cumulative effect of drowsiness over time. The purpose of this study is therefore to establish a model to detect a driver's drowsiness level by considering individual differences combined with the time cumulative effect (TCE) of drowsiness. Driving behavior and eye movement data from 27 drivers were collected by a driving simulator with an eye-tracking system, and the Karolinska Sleepiness Scale (KSS) was used to record drivers’ perceptions of their states of drowsiness. Since the degree of driver drowsiness was shown to increase with time, a mixed-effect ordered logit (MOL) model was established, and a non-decreasing function of time was applied to consider time accumulation. Results showed that with increasing drowsiness, the standard deviation of lateral position and percentage of driver eyelid closure (PERCLOS) increased significantly. Consideration of these variables can thus improve the accuracy of drowsy driving detection. The developed MOL-TCE model was compared with a non-TCE MOL and a TCE mixed generalized ordered response (MGOR) model. The drowsiness detection accuracy of the MOL-TCE model was 62.84%, higher than the 61.04% accuracy of the MGOR-TCE and appreciably higher than the 52.47% of the non-TCE MOL model.

Impact of Cognitive Distractions on Drivers’ Hazard Anticipation Behavior in Complex Scenarios

Distraction is one of the main causes of traffic crashes. The effect of cell phones, a major contributor to cognitive distraction, on response time has tested in many simulator studies. Response time is not the only driving skill affected by cell phone conversations, however. Specifically, it is known that cell phone usage contributes to a reduction in hazard anticipation skills at intersections, and there are many other scenarios where cell phone conversations could have a detrimental effect. The objective of this study is to determine whether cognitive distractions associated with cell phone use affect hazard anticipation, not only at intersections but also in other scenarios which contain latent hazards. Twenty-four drivers navigated 18 scenarios on a driving simulator twice, with their eye movements continuously monitored. During one drive, participants performed a hands-free mock cell phone task while driving; on the other drive, they navigated through the virtual world without any additional tasks apart from the primary task of driving. The scenarios were classified into two types: intersection and non-intersection. Using a logistic regression model within the framework of generalized estimation equations, it was determined that the proportion of anticipatory glances toward potential hazards was reduced significantly for all scenarios when drivers were engaged in a mock cell phone task. Perhaps the most disturbing finding is that this was true both at work zones and at marked midblock crosswalks, scenarios which often endanger vulnerable road users. In summary, the study found a negative effect of cognitive distraction on latent hazard anticipation.

Turn signal use among car drivers and motorcyclists at intersections: a case study of Da Nang, Vietnam

Turn signal neglect is a major cause of traffic crashes, particularly rear-end collisions. However, little research has investigated the use of turn signals among motorists, particularly in developing countries with high levels of motorcycle use. This research aimed to investigate the prevalence and factors associated with turn signal use at intersections among car drivers and motorcyclists in Da Nang, Vietnam. Cross-sectional roadside observations were undertaken at 24 sites across Da Nang City during weekday and weekend periods. A total of 17,142 vehicles were observed, including 2392 cars and 14,750 motorcycles. Turn signal use among car drivers (68.27%) was found to be significantly higher than motorcyclists (40.13%). Binary logistic regression modelling showed that turn signal neglect at intersections was associated with making a right turn, not carrying passengers, travelling outside of the city centre, travelling on weekdays, and the absence of separate car lanes, pedestrian crossings and traffic lights. Despite national legislation regulating turn signal use in Vietnam, the use of turn signals is relatively low compared with developed countries. The findings highlight the need for both greater and more targeted enforcement of existing legislation combined with extensive road safety education.

Design and Evaluation of K-Pass: A Bicycle-Friendly Modification of Speed Bumps

Traffic safety is a major concern across the world. Since speed is a major cause of traffic crashes, various traffic calming measures are used to enhance the safety of the road users in urban areas. Speed humps and bumps are the most widely used traffic calming devices. As a considerable number of bicyclists use the road along with motorized users, it is important to consider them while deploying any traffic calming devices. Studies have shown that bicyclists experience significantly larger discomfort as compared to motorized vehicles while passing over speed humps. In this study, a modification has been proposed to enhance riding comfort of bicyclists without compromising the traffic calming attribute of a speed bump. This modification is named “K-pass.” Analysis of data collected before and after the modification justifies the effectiveness in reducing the discomfort of bicyclists. Over a period of eight months, 70% of the bicyclists chose to use K-pass. Data also revealed that a high proportion of motorized two-wheeler users also used the K-pass at reduced speeds. It is expected that the K-pass will be a useful modification to the existing speed humps and speed bumps in areas where bicycle usage is expected.