Field Of Traffic Safety Research Articles

Causation analysis of crashes and near crashes using naturalistic driving data

Understanding crash causation to the extent needed for applying countermeasures has always been a focus as well as a difficulty in the field of traffic safety. Previous research has been limited by insufficient crash data and analysis methods more suitable to single crashes. The use of crashes and near crashes (CNCs) and naturalistic driving studies can help solve the data problem, and use of pre-crash scenarios can identify the high-prevalence causes across multiple crashes of a given scenario. This study therefore proposes a two-stage crash causation analysis method based on pre-crash scenarios and a crash causation derivation framework that systematically categorizes and analyzes contributing factors. From the Shanghai Naturalistic Driving Study (SH-NDS), 536 CNCs were extracted, and were grouped into 23 different pre-crash scenarios based on the National Highway Traffic Safety Administration (NHTSA) pre-crash scenario typology. In-depth investigations were conducted, and CNCs sharing the same scenario were analyzed using the proposed framework, which identifies causation patterns based on the interaction of the framework’s road user, vehicle, roadway infrastructure, and roadway environment subsystems. Through statistical analysis, the causation patterns and their contributing factors were compared for three common pre-crash scenarios of highest incidence: rear-end, lane change, and vehicle-pedalcyclist. Braking error in low-speed car following, following too closely, and non-driving-related distraction were important causes of rear-end scenarios. In lane change scenarios, the main causation patterns included illegal use of turn signals and dangerous lane changes as critical factors. Pedalcyclist scenarios were particularly impacted by visual obstructions, inadequate lanes for non-motorized vehicles, and pedalcyclists violating traffic regulations. Based on the identified causation patterns and their contributing factors, countermeasures for the three common scenarios are suggested, which provide support for safety improvement projects and the development of advanced driver assistance systems.

Validation of the Driver's Angry Thoughts Questionnaire (DATQ) in a sample of professional drivers in Iran

Aggressive driving has emerged as one of the most studied behaviors in the traffic safety field, due to its association with the odds of motor vehicle crashes and especially fatal crashes. Previous research has investigated the situations which provoke anger while driving, as well as the emotional (anger) and behavioral (aggression) aspects of aggressive driving. However, surprisingly the cognitive aspects of aggressive driving have largely been neglected. This study investigated the psychometric properties of the short-forms of the Driver's Angry Thoughts Questionnaire (DATQ) and the Driving Anger Expression Inventory (DAX) in a sample of professional drivers. Furthermore, the study aimed to investigate the mediation effects of aggressive thoughts, as the cognitive aspect of aggressive driving, on the relationship between traffic congestion and driving aggression. To this end, 613 public transport bus drivers completed the DATQ and DAX and were also asked to report the level of traffic congestion they normally faced in their daily driving, using six pictures. Confirmatory factor analysis (CFA) supported the four factor DAX and the five factor DATQ, which largely replicated the original factors. The four forms of maladaptive thoughts on the road were positively associated with aggressive driving, while the positive factor (coping self-instruction) was negatively associated with aggressive driving and traffic violations. Moreover, the results indicated that traffic congestion does not contribute directly to anger expression on the road, but rather through aggressive thoughts. This study suggests that cognitive interventions may help to eliminate aggressive driving and its adverse outcomes on traffic safety.

Organizational bases of the preparatory stage of the inspection of the scene of a traffic accident

This article analyses the activities of the internal affairs bodies in the field of solving and investigating crimes, related to the violation of traffic rules and the operation of vehicles, focuses on the specifics of preparation for the investigative action inspection of the scene of a traffic accident, as one of the main investigative actions, as well as the importance of the actions of the investigator, related to the detection and fixation of the material and road situation at the scene of a traffic accident. The article emphasizes: a methodology for documenting crimes committed in the field of traffic safety and operation of transport, characterized by the fact that qualified persons are important from the moment such facts are reported, timely and competent actions of the investigator related to the detection and recording of the physical and road situation at the scene of a traffic accident, and the seizure of physical objects and traces due to the fact that they are subject to change within a short period of time. The inspection of the scene of a traffic accident is presented in the form of an investigative action, the essence of which is the direct perception by the person producing it of the material situation displayed on the road and the elements adjacent to it (objects) as a result of a traffic accident, in order to detect, fix and remove material traces and circumstances that make it possible to subsequently recreate the mechanism of the event, as well as other circumstances of the incident that need to be established in order to solve the tasks of criminal procedure.

An alternate crash severity multicategory modeling approach with asymmetric property

The logit model and its variations have been used extensively in the field of traffic safety in general, and crash severity analysis in particular. Attempts were made to overcome the logit's shortcomings and limitations by generalizing its binary form to a more relaxed and unconstrained setting. Such attempts include the addition of shape parameters in order to add more flexibility to the probability distribution, while maintaining the straightforwardness provided in the logit-type models, with the least computational effort. A well-known form that provides an extra parameter to the base logit is the scobit model. In this study, we explore several generalizations of the binary scobit model by applying the same conventional methods associated with the generalized logit forms, principally to cover the multinomial nature of crash severity outcomes. Those are the multinomial and the ordinal forms. Furtherly, we utilize mixed distributions to provide crash-specific random parameters with heterogeneity in means and variances. Crash severity dataset taken from Guangdong province, China, was used to compare the different forms. The multinomial scobit models provided better results in terms of sample and out-of-sample fit, with the cost of some complexity in the heterogeneous forms. Other forms did not show a substantial or consistent advantage over their logit counterparts. All models exhibit temporal instability when applied to multiple time periods.

Inovativni pristup edukaciji o bezbednosti saobraćaja - projekat TRAFSAF

The problems of traffic safety and the profession of traffic safety are universal problems that require constant strengthening of the system of education and innovation both in syllabuses and in technologies and techniques applied in the field of traffic safety. The purpose of the innovative approach to the education program is to educate undergraduate and graduate students in the field of traffic safety, in accordance with the needs of society, which should provide an interdisciplinary and multidisciplinary approach to safety of all road users, technical solutions and social response to traffic accidents. Traffic safety problems are complex problems, which is why the competencies and skills acquired by engineers should provide knowledge and a deeper understanding of risk while strengthening the applied and practical skills. Innovative study programs must have a common basis for all directions, with a deep knowledge of mathematics, physics and mechanics with an emphasis on a holistic and interdisciplinary approach to the use of engineering in improving traffic safety.

Research on possibilities for monitoring stability of adjacent slopes to transport routes

Development of human society also implies modernization, respectively extension a road and railway transport structures. From this perspective, in order to achieve performance in the field of traffic safety, actions are also required to monitor the slopes, tailings dumps (active or greened) adjacent to transport routes where there are uncertainties regarding their stability. Ignoring stability and landslides can lead to loss of life, as well as significant material damage. Thus, the paper mainly addresses the issue of monitoring the slopes adjacent to road and rail transport routes where there are uncertainties regarding the control of landslides, as well as possibility of alerting before this occurs. From the multitude of possible solutions to be applied in the field, an equipment was developed and realized, which was experienced in real working conditions, and the results confirm validity of assumptions and certify the operation.

Legal regulation in the field of traffic safety in the Kyrgyz Republic

Legal regulation in the field of traffic safety in the Kyrgyz Republic

Economic and legal aspects of violations of traffic safety rules on railway transport in Russia

Railway transportation is a vital service to global society and the backbone of a sustainable economy. It has an unprecedented opportunity to achieve the sustainability which is required for the 21 century. By doing so, railway will be able to respond to the expected growth in transport demand, both passenger and freight. This article reflects the main issues facing the transport system in the field of traffic safety and operation of railway transport, analyzes the criminal law aspects of the current legislation. Railways are an important part of the Russian transport network. Most of the Railways belong to the East Siberian railway. A special place in ensuring railway safety is occupied by economic legal regulators, especially the the most effective means of influencing socially significant behavior. Russian legislation provides for different norms of liability, including those provided for in the criminal legislation of the Russian Federation: 1) violation of the rules of traffic safety and operation of rail, air or water transport (Art. 263); 2) poor quality repair of vehicles and their release into operation with technical faults (art. 266); 3) bringing into disrepair vehicles or means of communication (article 267); 4) violation of the rules ensuring the safe operation of transport (article 268). In quantitative terms, they are quite enough to counter internal and external threats to the safe functioning of rail transport, but there are a number of significant shortcomings that do not allow to realize their protective potential to the full.

Semi and Nonparametric Conditional Probability Density, a Case Study of Pedestrian Crashes

Background: Kernel-based methods have gained popularity as employed model residual’s distribution might not be defined by any classical parametric distribution. Kernel-based method has been extended to estimate conditional densities instead of conditional distributions when data incorporate both discrete and continuous attributes. The method often has been based on smoothing parameters to use optimal values for various attributes. Thus, in case of an explanatory variable being independent of the dependent variable, that attribute would be dropped in the nonparametric method by assigning a large smoothing parameter, giving them uniform distributions so their variances to the model’s variance would be minimal. Objectives: The objective of this study was to identify factors to the severity of pedestrian crashes based on an unbiased method. Especially, this study was conducted to evaluate the applicability of kernel-based techniques of semi- and nonparametric methods on the crash dataset by means of confusion techniques. Methods: In this study, two non- and semi-parametric kernel-based methods were implemented to model the severity of pedestrian crashes. The estimation of the semi-parametric densities is based on the adoptive local smoothing and maximization of the quasi-likelihood function, which is similar somehow to the likelihood of the binary logit model. On the other hand, the nonparametric method is based on the selection of optimal smoothing parameters in estimation of the conditional probability density function to minimize mean integrated squared error (MISE). The performances of those models are evaluated by their prediction power. To have a benchmark for comparison, the standard logistic regression was also employed. Although those methods have been employed in other fields, this is one of the earliest studies that employed those techniques in the context of traffic safety. Results: The results highlighted that the nonparametric kernel-based method outperforms the semi-parametric (single-index model) and the standard logit model based on the confusion matrices. To have a vision about the bandwidth selection method for removal of the irrelevant attributes in nonparametric approach, we added some noisy predictors to the models and a comparison was made. Extensive discussion has been made in the content of this study regarding the methodological approach of the models. Conclusion: To summarize, alcohol and drug involvement, driving on non-level grade, and bad lighting conditions are some of the factors that increase the likelihood of pedestrian crash severity. This is one of the earliest studies that implemented the methods in the context of transportation problems. The nonparametric method is especially recommended to be used in the field of traffic safety when there are uncertainties regarding the importance of predictors as the technique would automatically drop unimportant predictors.

The Impact on Mobile Phone use on Pedestrian Road Crossing Behaviour

Mobile phone use at pedestrian crossings has been recognized as a growing problem in the field of traffic safety. The objective of the paper is to analyze the impact of mobile phone use at pedestrian crossings considering specific territory. Signalized and unsignalized intersections are observed in the study. Several factors having the impact on unsafe pedestrian crossing behaviour are identified such as: age, location and the type of mobile phone using. The model of unsafe pedestrian behaviour based on displayed mobile phone use while crossing the intersection is constructed. It has been shown in this research that talking and texting on mobile phone distract pedestrians. Listening to music does not affect pedestrians to behave unsafely because it requires less cognitive activity than talking or texting. Also, location affects the pedestrian crossing behavior. The results of this research can serve the purpose of preventing the mobile phones use and reduce the negative impact on pedestrian crossing behavior.

ERP Waveforms and Time-Varying Networks Analysis of a Novel Audiovisual P300-Speller Paradigm

This article presents the case for, and against, using the term crash versus accident to describe unintended events that involve motor vehicles in transport on a trafficway and which result in damage to property or injury to involved persons. The history of the preference for crash versus accident among safety practitioners goes back to the 1960s. The change is not yet universal for a variety of reasons; however, it is gaining acceptance both within and outside the traffic safety field. The case for crash relies mainly on the observation that these events, while unintended, are not unavoidable and the causes and contributing factors are known. Moreover, we can apply effective countermeasures and measure the impact of those countermeasures in reducing the frequency and severity of these events. The counterargument, that the term accident is best, relies mostly on historic precedent and parallel terminology in industrial safety. The preference for crash is strongest among safety practitioners who focus on implementing countermeasures (behavior change, vehicle systems, and the roadway environment) and among those harmed in crashes and their families. We must also recognize the special case of intentionally harmful events that clearly are not accidental under any accepted definition. Those who argue in favor of using the word accident have some difficulty classifying which of the crash contributing factors point to intentional behaviors about which they must agree the term accident is a poor choice. Evidence suggests that media outlets are starting to adopt the changed word choice as well. In the United States, some states are resistant because their laws include the term accident, but classification guidance and standards from the National Highway Traffic Safety Administration (NHTSA) and the American National Standards Institute (ANSI) have made the change a permanent part of the safety lexicon, and some states are following this guidance as well. Note that the majority of this article presents discussions that are taking place in and about the situation in the United States. I have included some information about the situation in the rest of the world regarding terminology and mind-sets and for that input I thank my international colleagues.

Learning of Pseudoword-Movement Association is Accompanied by Enhanced Beta Synchronization

This article presents the case for, and against, using the term crash versus accident to describe unintended events that involve motor vehicles in transport on a trafficway and which result in damage to property or injury to involved persons. The history of the preference for crash versus accident among safety practitioners goes back to the 1960s. The change is not yet universal for a variety of reasons; however, it is gaining acceptance both within and outside the traffic safety field. The case for crash relies mainly on the observation that these events, while unintended, are not unavoidable and the causes and contributing factors are known. Moreover, we can apply effective countermeasures and measure the impact of those countermeasures in reducing the frequency and severity of these events. The counterargument, that the term accident is best, relies mostly on historic precedent and parallel terminology in industrial safety. The preference for crash is strongest among safety practitioners who focus on implementing countermeasures (behavior change, vehicle systems, and the roadway environment) and among those harmed in crashes and their families. We must also recognize the special case of intentionally harmful events that clearly are not accidental under any accepted definition. Those who argue in favor of using the word accident have some difficulty classifying which of the crash contributing factors point to intentional behaviors about which they must agree the term accident is a poor choice. Evidence suggests that media outlets are starting to adopt the changed word choice as well. In the United States, some states are resistant because their laws include the term accident, but classification guidance and standards from the National Highway Traffic Safety Administration (NHTSA) and the American National Standards Institute (ANSI) have made the change a permanent part of the safety lexicon, and some states are following this guidance as well. Note that the majority of this article presents discussions that are taking place in and about the situation in the United States. I have included some information about the situation in the rest of the world regarding terminology and mind-sets and for that input I thank my international colleagues.

A visual approach for defining the spatial relationships among crashes, crimes, and alcohol retailers: Applying the color mixing theorem to define the colocation pattern of multiple variables

In traffic safety studies, the few scholars who have focused on analyzing disaggregated data obtained results that have been either difficult to explain or demonstrate because they did not provide clear visual maps or utilize statistical tests to quantify the spatial relationships. In order to increase the use of such disaggregated spatial methods for use in traffic safety studies, the current study documents the application of a new RGB (red, green, blue) model which combines the color additive theorem and the kernel density map (KDE) to define crash colocation patterns and the coincidence spaces of related variables.This study contributes to the literature in three major ways: (1) a new RGB model was established and applied in the field of traffic safety; (2) the variable dimensions were expanded from two to three; and, (3) the dimension of uncertainty was also included. When the new RGB model was utilized with data collected in College Station, Texas, the results indicated that the new colocation map is able to clearly and accurately define colocation hotspots of crashes, crimes, and alcohol retailers. As expected, these hotspots are located in areas with many bars, the largest strip malls and busiest intersections. The intensity maps have provided results consistent with the above colocation maps. However, the uncertainty map does not show a relatively higher level of certainty regarding the location of hotspots as we expected because the input of each variable was not related to the highest kernel value. Therefore, future scholars should focus on the colocation and intensity maps while using the uncertainty map as a reference for individual event risk evaluation only.

Driving simulation sickness and the sense of presence: Correlation and contributing factors

Driving simulators are useful and effective tools for conducting studies in the field of traffic safety. Simulation sickness (SS) and the sense of presence (SP) are two well-known factors that could affect the results of the driving simulator experiments. This study investigated the relationship between SP and SS in a medium-fidelity driving simulator. Additionally, the impact of the road environment (urban arterials or rural expressways) on these subscales was investigated. Data was collected by means of self-reported questionnaires, which were conducted after the participants have driven the simulation scenarios in a fixed-base medium-fidelity driving simulator. A total of 125 drivers participated in this study. Results showed that females reported significantly higher SS scores than males. An increasing trend in the SS was observed with the increase of age. Importantly, designing buildings that replicate a real-world environment could increase SP and decrease SS. Moreover, designing high quality and resolution scenarios could also increase SP, thus decreasing the severity of SS symptoms. The results of this study can help researchers using medium-fidelity driving simulators to know the influencing factors for each subscale of SP on SS. Adjustments in the driving simulator and scenario settings as well as additional training exercises for higher speed scenarios can be beneficial in reducing the severity of SS.

Incorporating accident liability into crash risk analysis: A multidimensional risk source approach

In the field of traffic safety, the occurrence of accidents remains a cause of concern for road regulators as well as users. Exploring risk factors inducing the accidents and quantifying the accident risk will not only benefit the prevention and control of traffic accidents but also assist in developing effective risk propagation model for road accidents. This study uses detailed accident record data to mine the risk factors affecting the occurrence of accidents, and quantify the accident risk under the combination of risk factors. First, by reviewing relevant literature and analyzing historical accident, we construct a multi-dimension characterization framework of risk factors with bi-level structure. The Human Factors Analysis and Classification System (HFACS) is applied to supplement and improve the framework. Next, under this framework, we identify the risk factors in traffic accident record, and analyze the statistical characteristics from the level of risk sources and risk characteristics. Then, the concept of accident liability weight is proposed to measure the impact of risk factors on accident occurrence. Through the liability affirmation of risk factors, the accident probability are updated. Last, we establish an accident risk quantify model (ARQM) based on the mean mutual information to compare the likelihood of accidents in different scenarios. In addition, we compare the accident probability and risk under equivalent liability and liability affirmation, as well as give some fundamental ideas regarding how to effectively prevent accidents.

MEASURES OF CRIMINAL JUSTICE RESPONSE TO PROHIBITIONS IN THE FIELD OF TRAFFIC SAFETY AND VEHICLE OPERATION: SOME ASPECTS OF REGULATORY CERTAINTY AND PRACTICE OF USE

The article is devoted to the research of measures of criminal justice response to prohibitions in the field of traffic safety and vehicle operation. It is noted that the primary role in state response to violation of criminal justice prohibitions in the field of traffic safety and vehicle operation is given to punishment, but no less important role is paid to other alternative to prohibition measures of criminal justice nature based on the concussion (special confiscation) or the encouragement (exemption from criminal responsibility or serving a sentence). It is concluded that the normative regulations of threats of application of certain punitive measures of criminal justice nature in sanctions of the articles of this section of the Special part in which the legislator defines the threat of application of various types of punishment for committing the crimes stipulated in crimes’ dispositions, needs specification from the point of view of the system interconnection, along with the provisions of the General Part of the Criminal Code of Ukraine, whereas the practice of application of special confiscation its further distribution and development, considering the proposed recommendations of its delimitation with the so called criminal procedural confiscation as means of criminal procedural concussion. In particular, it is noted that such clarification may be implemented either by enforcing additional penalties specified in the sanctions of Part 1, 2, 3 of Article 286, part 1 of Article 287 of the Criminal Code of Ukraine, to the common list of types of punishments, with their separate meaningful definition in the corresponding articles of the section X of the General part of the Criminal Code of Ukraine, or by covering normative definition in sanctions of the specified articles of section XI of the Special part of threats of application of such additional types of punishments according to the existing parts of the Criminal Code of Ukraine. In this regard the sanctions of Article 286 and 287 of the Criminal Code of Ukraine propose to make appropriate changes. As for the practice of applying special confiscation for committing crimes in the field of traffic safety and vehicle operation, it is recommended that the question of its implementation should be based on the fact that the subject of special confiscation may be defined in paragraph 1 of Part 1 of Art. 96-2 of the Criminal Code - items 6, 6-1 part 9 of Art. 100 of the Criminal Procedure Code, paragraph 2, part 1 of Art. 96-2 of the Criminal Code - item 2 part 9 of Art. 100 of the CPC, paragraph 3, part 1 of Art. 96-2 of the Criminal Code - item 5 part 9 of Art. 100 of the CPC, paragraph 4, part 1 of Art. 96-2 of the Criminal Code - item 1 part 9 of Art. 100 of the CPC items of the material world that possess a certain property value, and are usually considered as physical evidence in criminal proceedings initiated on the fact of committing certain crimes in the field of traffic safety and vehicle operation.

The Typical Traffic Accident in Lithuania In Comparison with Sweden

Every day we strive to improve the environment and make it as comfortable as possible, creating new products and new technologies that are literally changing people’s lives. Transport is one of the most important engines of development in the world and, unfortunately, it is one of the most painful taking into account how many people’s lives we are losing in it. Ensuring safe traffic, stabilizing a number of accidents, reducing accidents on motor roads and streets are the most important tasks in the field of transport in Lithuania and the EU today. Lithuania could not be left behind when the EU countries pursued an important goal of halving the number of fatalities by the end of 2010 compared to 2001. Substantial road accident rates are recorded in cities with the highest concentration of road users. The aim of this article is to identify the typical accidents for Lithuanian cities and to compare them with the case of Sweden, which is one of the leading countries in the field of traffic safety. The five largest cities in Lithuania been selected for the analysis, where typical traffic accidents are identified. The analysis will help develop recommendations for changes in traffic infrastructure to ensure safe traffic.

PROTOCOL: Effectiveness of road safety interventions: An evidence and gap map.

The Decade of Action for Road Safety 2011-2020, officially proclaimed by the UN General Assembly in March 2010, sought to reduce morbidity and mortality due to road traffic injuries (RTI) significantly. While there is reasonable agreement internationally on safer designs of motor vehicles (except locally produced vehicles like three-wheeled scooter taxis, tuk-tuks, jeepneys, etc.), there is a lack of evidence based interventions in road and infrastructure design, police enforcement and post-crash care. Researchers in the field of traffic safety have been aware of the existence of counterintuitive results in their area of work for more than four decades. The fact that many interventions do not result in reductions in RTI is mainly because a large number of studies only measure intermediate outcomes like change in behaviour or knowledge and not the actual results in the field. The scope of this evidence and gap map (EGM) is to cover relevant studies in road safety sector from all countries and present the effectiveness of interventions in terms of mainly traffic crash injuries as its outcome. The interventions adopted in this EGM are classified into five broad categories: Human factors, vehicle factors and protective devices, road design, infrastructure and traffic control, post-crash pre-hospital care and legal and institutional framework. In order to come closer to accomplishing targets for road safety, it is important to allocate resources to promote interventions that are effective in achieving outcomes in the context of road safety. A mapping will provide a comprehensive overview of existing knowledge in the area of road safety and its effectiveness across the world. The map will guide programme managers to high quality evidence and inform targeted commissioning of future research.

Catalyzing traffic safety advancements via data linkage: Development of the New Jersey Safety and Health Outcomes (NJ-SHO) data warehouse

Objective: Our objective is to describe the development of the New Jersey Safety and Health Outcomes (NJ-SHO) data warehouse, a unique and comprehensive data source that integrates various state-level administrative databases in New Jersey to enable the field of traffic safety to address critical, high-priority research questions.Methods: We have obtained full identifiable data from the following statewide administrative databases for the state of New Jersey: (1) driver licensing database; (2) Administration Office of the Courts data on traffic-related citations; (3) police-reported crash database; (4) birth certificate data; (5) death certificate data; and (6) hospital discharge data as well as (7) childhood electronic records from New Jersey residents who were patients of the Children’s Hospital of Philadelphia pediatric health care network and (8) census tract–level indicators. We undertook an iterative process to develop a linkage algorithm in LinkSolv 9.0 software using records for individuals born in select birth years (1987 and 1988) and subsequently execute the linkage for the entire study period (2004–2017). Several metrics were used to evaluate the quality of the linkage process.Results: We identified a total of 62,685,619 records and 19,247,363 distinct individuals; 10,352,998 of these individuals had more than one record brought together during the linkage process. Our evaluation of this linkage suggests that the linkage was of high quality.Conclusions: The resulting NJ-SHO data warehouse will be one of the most comprehensive and rich traffic safety data warehouses to date. The warehouse has already been utilized for numerous studies and will be fully primed to support a host of rigorous studies, both in and beyond the field of traffic safety.

Research on safe driving behavior of transportation vehicles based on vehicle network data mining

AbstractIn recent years, with the rapid development of China's economy and the growth of people's travel demand, road transport industry has developed rapidly. However, at the same time, the traffic safety problems caused by the accelerated growth of transport vehicles are becoming more and more serious. Driver's driving behavior is closely related to traffic safety. With the help of data mining technology, we can make full use of the system data collected by road transportation industry to identify the bad driving behavior of transport vehicles and get seven secondary indicators of traffic safety evaluation indicators: overspeed, accelerated, decelerated, fatigue driving, idle preheating, overspeed idling, and flameout taxiing. According to the indicators, the occurrence times and duration are further subdivided into 14 three‐level indicators. Then, by using the analytic hierarchy process, through the construction of comparison judgment matrix and consistency checking, the corresponding weight of each evaluation index is determined with the help of the entropy method, and the formation safety of transport vehicles is evaluated. The results show that drivers with more fatigue driving, acceleration, and deceleration have higher driving risk. Transportation enterprises and relevant departments need to focus on their monitoring. The combination of data mining, data analysis algorithm, and traffic safety field in machine learning provides a demonstration for the study of safe driving behavior of transport vehicles in China and has a guiding significance for the supervision and training of drivers' driving behavior and reducing road safety risks.