Traffic Safety Management System Research Articles

Modeling Urban Freeway Rear-End Collision Risk Using Machine Learning Algorithms

A large amount of traffic crash investigations have shown that rear-end collisions are the main type collisions on the freeway. The purpose of this study is to investigate the rear-end collision risk on the freeway. Firstly, a new framework was proposed to develop the rear-end collision probability (RCP) model between two vehicles based on Generalized Pareto Distribution (GPD). Secondly, the freeway rear-end collision risk (F-RCR) was defined as the sum of the rear-end collision probability of each vehicle and divided into three levels which was high, median, and low rear-end collision risk. Then, different machine learning algorithms were used to model F-RCR under the condition of an unbalanced dataset. The result of the RCP model showed continuous change and can identify the dangerous condition quickly compared to the traditional models even when the speed of the leading vehicle is faster than the following vehicle. When the vehicle distribution was unbalanced on road and the speed difference between adjacent lanes and the traffic volume was large, F-RCR will increase. Multi-Layer Perceptron (MLP) was found to be more suitable for modeling F-RCR. The framework provided in this research was transferrable and can be used in the freeway proactive traffic safety management system.

Improving Spatiotemporal Transferability of Real-Time Crash Likelihood Prediction Models Using Transfer-Learning Approaches

A real-time crash likelihood prediction model is an important component of the proactive traffic safety management system. Over the past decades, numerous models have been proposed for predicting real-time crash likelihood and achieved promising results. However, most studies have ignored the model transferability, especially for deep-learning models. The transferability of a model could be defined as applying the model to new data which obtain from different locations or periods. The purpose of this study is to improve the spatiotemporal transferability of a deep-learning crash likelihood prediction model by using transfer-learning approaches. Trajectory and crash data from five arterials in Florida were used in this study. A two-layer long short-term memory (LSTM) model was developed to predict real-time crash likelihood. Two scenarios were created for investigating spatial and temporal transferability of the developed model. Experimental results suggested that the model could be accurately transferred to new data by using the fine-tuning transfer-learning approach. In the framework of this research, the transferred models achieved higher predictive accuracy than models which were directly developed on the new data. Moreover, the spatial transfer learning outperformed the temporal transfer learning in predictive accuracy. For example, when the percentage of test data was 70%, the spatial transferred model had an average area under the curve (AUC) of 0.74. while the temporal transferred model had an average AUC of 0.65. Results from this study could be applied to transfer pretrained crash likelihood prediction models to new locations when few crashes are available.

Optimal Layout of Heterogeneous Sensors for Traffic Accidents Detection and Prevention

Sensors layout plays an important role in proactive traffic safety management system for accidents detection and prevention. However, traffic accidents uncertainty and sensors heterogeneity are difficulty for sensors optimal layout on road network. To solve the problems, an optimal layout method of heterogeneous sensors is presented. In the method, a traffic accident risk distribution assessment model is established to reduce the uncertainty influence of traffic accidents and obtain the stable spatial distribution of accident risk on road network. Then heterogeneous sensors optimal layout model is established to maximize the coverage quality on road network traffic accident risk with the constraints of sensors types, cost, accidents detection error, and so on. A two-stage heuristic method is proposed by pruning search algorithm and AO-GI-MO algorithm to optimize sensors types, numbers and positions. Stability, convergence, consistency, reliability experiments are carried out to validate the proposed method. The results show the proposed method could deal with traffic accidents uncertainty efficiently and achieve the optimal layout of heterogeneous sensors on road network.

A hybrid machine learning model for predicting Real-Time secondary crash likelihood

Secondary crashes usually occur within the spatio-temporal impact ranges of primary crashes, which could cause traffic disturbance and increase traffic safety problems. However, existing studies only focused on predicting the likelihood of crashes leading to secondary crashes without considering the likelihood of the occurrence of secondary crashes. In addition, previous studies did not consider the real-time implementation of secondary crash likelihood prediction models and included too many features that were not available in real-time. A real-time secondary crash likelihood prediction model aims to predict the likelihood of secondary crashes in a short period (e.g., 5–10 min) and update every minute. The main objective of this paper is to develop a machine learning model to predict secondary crash likelihood in real-time. Two XGBoost models were developed for predicting the likelihood of crashes leading to secondary crashes and the likelihood of the occurrence of secondary crashes, respectively. A hybrid model was proposed to combine the results from the two developed models. Results indicated that the proposed hybrid model significantly improved the accuracy of secondary crash likelihood prediction. The proposed model has the potential to be applied in proactive traffic safety management system and prevent the occurrence of secondary crashes. Moreover, experimental results suggested that several features related to real-time traffic flow conditions were crucial for predicting secondary crash likelihood, such as the average traffic volume and average occupancy.

Strategic Management Indicators for Sustainable Road Traffic Management

Human is very critical and important asset of any nation. Human security is the prime need. Also, at organizational level, the business success depends on the human efficiency. Hence, strategic management is very important to achieve effective performance. This paper assessed various indicators and attributes of strategic management. However, the limitation of this study was to focus on strategic management used in traffic management used bypublic security sector ofAbu Dhabi. Evaluation involved 29 common attributes of strategic management identified from literature. These were categorized into five indicators aslearning & training; traffic setting; emergency response; road engineering & vehicle safety; and strategiesbeing enforced. Analysis of the data collected through Questionnaire survey with officials involved in traffic management was done with mean score method. Results of the analysis showed that review and develop a driver training program and licensing mechanismis the top ranked attribute in the domain of learning & training. The respondents highlighted effective traffic control in pedestrian and cyclist safety areas and seatbelts as very useful in the indicator traffic setting. Top indicators in the indicator emergency response are development of effective systems for geographical positioning of traffic accidents andspreading a culture of prioritising emergency vehicles in emergency situations. Develop an integrated traffic safety management system (ITSMS) is the most useful attribute related to road engineering & vehicle safety indicator. While in the indicator strategies being enforced, the respondents mentioned that the attribute at top rank is developing smart traffic settings to minimize the accidents.

Bus crash risk evaluation: An adjusted framework and its application in a real network

Greater attention to bus safety can lead to relevant benefits for public transport companies in terms of higher service performance, reliability, and lower insurance costs. Therefore, measuring the crash risk on bus routes provides an opportunity to improve the safety performance of transit operators. Previous research has explored the effects of many factors regarding the frequency and severity of bus crashes, whereas only a handful of studies have defined some crash risk indexes. Conversely, to the best of our knowledge, almost no research has been done regarding the crash risk in the bus transit network that integrates frequency, severity, and the exposure factors. This paper proposes a new framework to assess the crash risk for each transit bus route by the integration of safety factors, prediction models and risk methods. More precisely, this framework identifies several safety factors and specifies the risk components in terms of frequency, severity and exposure factors that may affect bus crashes. Then, it models their relationships to build a bus crash risk function. Lastly, according to the values returned by the previous function, the crash risk for each route is computed and a safety performance ranking for each route is provided. The feasibility of this framework is demonstrated in a real case study by using bus crash data provided by a mid-sized Italian bus operator. The findings show that transit managers could implement this framework in a road traffic safety management system to evaluate the risk of crashes on routes, monitor the safety performance of each route and qualify each route according to recent safety norms.

A method that improves the safety states of technical means of control and management

The main focal points of improving the traffic safety management system are as follows. First, one must coordinate the interaction among all functional branches, their structural divisions and subsidiaries involved in the transportation process, based on common approaches to managing processes related to traffic safety. Second, one should implement the approaches and requirements that are congruent with international standards; to maintain a positive level of traffic safety culture through awareness of the importance and social responsibility of the holding employees when performing work that affects traffic safety, with simultaneous integration of mandatory and strict rules of conduct in all production processes. Third, one is to improve the regulatory framework. Train traffic safety is ensured at all stages of the life cycle of rolling stock, traffic support systems and infrastructure elements. Nevertheless, failures and malfunctions are detected during the operation. This article presents one of the methods for increasing the train traffic safety in the automation and telemechanics system.

Selected Aspects of the Road Traffic Safety Management System

The article is an attempt to present the two modern concepts of safety management systems. The first is the sunflower pyramid used especially in Europe, the second is the ISO 39001 standard (Road Safety Management System) of international scope. The idea and possibilities offered by use of both concepts of safety management, as well as an attempt to assess the impact of their actions on decrease in fatalities in selected EU countries, were presented. As a result of the conducted analyses, a downward trend was noted as to the number of certificates issued for compliance with the ISO 39001 standard in the world, which may indicate an appearance of the more adequate management systems, or other tools or concepts to improve the road safety, or inadequate education society and low level of awareness in this area of stakeholders, including politicians, scientists, producers, drivers (professional and reliable), as well as other road users, including unprotected ones.

Assessing the Risk of Bus Crashes in Transit Systems

Although public transport buses may be considered a safe transportation mode, bus safety is a crucial issue from the perspectives of operators, passengers and local authorities owing to the relevant implications it generates. Therefore, assessing the risk of crashes on bus routes may help improve the safety performance of transit operators. Much research has identified patterns of bus crashes to understand the effects of many factors on the frequency and the severity of them. Conversely, to the best of our knowledge, the research measuring the risk of crashes in bus transit networks is seldom faced. This paper adjusts existing methods to assess the safety on bus transit networks by the integration of safety factors, prediction models and risk methods. More precisely, first, the methodology identifies several safety factors as well as the exposure risk factors. Second, this methodology specifies the risk components in terms of frequency, severity and exposure factors that may affect bus crashes and models their relationships in a risk function. Third, this methodology computes the risk of crashes for each route and provides a ranking of safety performance. A real case study demonstrates the feasibility of this methodology using 3,457 bus crashes provided by a mid-sized Italian bus operator. This experiment shows that transit managers could adopt this methodology to perform an accurate safety analysis on each route. Moreover, this methodology could be implemented in a road traffic safety management system in order to evaluate the risk of crashes on routes, monitor the safety performance of each route and qualify each route according to recent safety norms.

Підвищення рівня безпеки руху на залізничному транспорті за рахунок оптимізації роботи системи управління безпекою руху поїздів

Ensuring a high level of safety on rail transport is currently one of the top priorities for both the state and organizations responsible for railway transportations. An analysis on the recent level of the transportation process safety shows that the current system of railway traffic safety management in the context of the industry reforming needs to be significantly adjusted. The existing traffic safety management system requires the introduction of new technologies that meet the modern development of the transport industry in the world and ensure a high level of reliability and safety of railway transport. The article analyzes the need to create a risk management system in order to improve the functional and operational safety of the railways of Ukraine. Correlation of the scale of risks with the size of the expenditures for measures to improve traffic safety will allow, under resource constraints, to make management decisions that meet economic criteria. An effective means of ensuring high safety and reliability indicators of railway transport in Ukraine in the context of the risk management development can be the development of a comprehensive methodology (new software product) concerning risks and resources management on the railway network based on the international standard ISO 55001, the main purpose of which is to manage assets. The use of the new software product on the railway network will allow, in conditions of financial resources shortage to increase the service life of railway transport facilities to the limited state based on risk measurement and to reallocate investments in support of their reliability and safety. Based on the evaluation of the reliability and safety indicators of the functioning of infrastructure facilities and rolling stock, the proposed system will ensure the optimal allocation of resources and risk management for facilities related to the safety and reliability of transportation.

Using bus critical driving events as surrogate safety measures for pedestrian and bicycle crashes based on GPS trajectory data

Pedestrian and bicycle safety is a key component in traffic safety studies. Various studies were conducted to address pedestrian and bicycle safety issues for intersections, road segments, etc. However, only a few studies investigated pedestrian and bicycle safety for bus stops, which usually have a relatively larger volume of pedestrians and bicyclists. Moreover, traditional reactive safety approaches require a significant number of historical crashes, while pedestrian and bicycle crashes are usually rare events. Alternatively, surrogate safety measures could proactively evaluate traffic safety status when crash data are rare or unavailable. This paper utilized critical bus driving events extracted from GPS trajectory data as pedestrian and bicycle surrogate safety measures for bus stops. A city-wide trajectory data from Orlando, Florida was used, which contains around 300 buses, 6,700,000 GPS records, and 1300 bus stops. Three critical driving events were identified based on the buses’ acceleration rates and stop time; hard acceleration, hard deceleration, and long stop. The relationships between critical driving events and crashes were examined using Spearman’s rank correlation coefficient. All three events were positively correlated with pedestrian and bicycle crashes. Long stop event has the highest correlation coefficient, followed by hard acceleration and hard deceleration. A Bayesian negative binomial model incorporating spatial correlation (Bayesian NB-CAR) was built to estimate the pedestrian and bicycle crash frequency using the generated events. The results were consistent with the correlation estimation. For example, hard acceleration and long stop events were both positively related to pedestrian and bicycle crashes. Moreover, model evaluation results indicated that the proposed Bayesian NB-CAR outperformed the standard Bayesian negative binomial model with lower Watanabe-Akaike Information Criterion (WAIC) and Deviance Information Criteria (DIC) values. In conclusion, this paper suggests the use of critical bus driving events as surrogate safety measures for pedestrian and bicycle crashes, which could be implemented in a proactive traffic safety management system.

Suggestions for automation of document flow system at railway freight classification yard

Upon condition of the mandatory application of the traffic safety management system in the railway transport system, as well as to add the demands for the carrier of cargo, amendments to the draft law on the railway transport operation have been introduced, which include new requirements: carriers of cargo are required to operate the traffic safety management system. The parameters and quality indicators of the railway transportation process include: the accuracy of the timeline travel time, the value of the service speed, the amount of energy consumed, the cost of maintenance work, the preservation of cargo commodity qualities, etc. In addition to the common problems that attract the attention of railway science, comprehensive automation of processes is a critical task. To address the delay in sending documents, the authors have designed and modeled a device that ensures the automatic redirection of documents by pneumatic tubes. Automation of the pneumatic tubes operation will make it possible to speed up the process of transferring documents to prepare for the departure of freight trains, improve the performance quality of the freight classification yard, increase the capacity of the freight classification yard, as well as eliminate human interference and improve the safety of trains. The project’s technological performance indicators have been determined. This practice will have an economic impact of 4,439.2 thousand rubles per year. The payback period is 2 years.

Creation of a mobile application for digitizing technological processes of a railway station

The article considers the main directions of improving the traffic safety management system in railway transport in the context of the transition to a higher level of reliability. The transition of the railway industry from information control systems to fully control systems can be ensured by combining automated information systems that are integrated on the road network into production processes. Within the framework of the project to ensure the safety of the transportation process, it is advisable to provide for the implementation of work on equipping the infrastructure of JSC Russian Railways with modern innovative technical means - automated systems for inspecting trains and wagons using laser scanners. The work of the complex to identify and prevent situations that threaten the safety of traffic along the route is considered, the introduction of which will ensure the transition to unmanned technologies when organizing the control of goods and rolling stock at loading stations and along the route. The use of the resource mobile workstation of a cargo and baggage pick-up unit at a railway station will speed up the process of accepting wagons for transportation, reduce the time for processing transportation documents, improve the quality of the railway station, significantly optimize the work process of a cargo and baggage pick-up unit, increase labor productivity, eliminate the influence of the human factor in carrying out this type of work. The technical and economic result of using this complex at the railway stations of Russian Railways is the provision of an increased level of safety on the railways.

RISK MANAGEMENT IN AIR NAVIGATION SERVICES

The need to develop and adopt legal standards for safety management was identified at the Conference of General Directors of Civil Aviation dedicated to the global strategy of aviation safety (Montreal, March 20-22, 2006) and additionally supported by the recommendations of the Safety Conference (Montreal, March 29 - April 1, 2010). The year 2006 saw the introduction of issues related to the safety management system to the Convention’s annexes. The existing fundamental rules related to SMS were included in the annexes: 1 - Personnel licensing, 6 - Operation of Aircraft, 8 - Airworthiness of Aircraft, 11 - Air Traffic Services, 13 - Aircraft Accident and Incident Investigation, and 14 - Aerodromes. In addition, due to the dynamic development of aviation and, at the same time, the growing need to create the highest standards in the field of safety management systems, the Air Navigation Commission established the Safety Management Panel (SMP) to develop the content of Annex 19. After several years of reconciliation and consultation, this document was finally adopted by the ICAO Council in 2013. It has become the ipso facto document that provides the basis for creating an effective safety management system, as it is compatible and also adapted to the most effective practices indicated in the ICAO Doc 9859 Safety Management Manual. Annex 19 sets out the responsibility of States, the safety management system and the collection of information related to safety. The National Civil Aviation Safety Programme and the structure of this system were also dealt with. The whole idea is to support states in the process of hazard identification and risk management. The purpose of the article was: to highlight selected elements of the risk management process in a practical dimension, to present the principles for assessing the degree of risk by an air navigation service provider, and to identify ways of improving this process. Searching for an answer to the main research problem contributed to achieving this goal. The research problem was expressed in the form of a question: How does the air navigation service provider manage the risk under the air traffic safety management system in order to achieve compliance with regulatory requirements and to achieve the assumed parameters (indicators) in the area of safety? With regard to the main research problem, the following research hypotheses were formulated: 1. I believe that an air navigation service provider undertakes an assessment of the degree of possible danger in civil aviation to identify hazards in air traffic as part of a safety management system. 2. I suppose that the air navigation service provider manages the risk in a manner consistent with the provisions of law and by using procedures included in normative documents.

A Zero-Inflated Ordered Probit Model to Analyze Hazmat Truck Drivers’ Violation Behavior and Associated Risk Factors

There are few studies on the violation of truck drivers, especially the hazmat truck driver, although truck driver's violation may cause serious casualties. This paper aims to investigate hazmat truck drivers' violation behavior and identify associated risk factors. Different data sources in intelligent transportation system (ITS) including hazmat transportation management system and traffic safety management system are extracted and emerged together. Three years (2016-2018) of violation data that comprised 11612 trip record in China are employed in this research. Based on Bayesian theory, this study proposes zero-inflated ordered probit (ZIOP) model and three alternative models to exploring the relationship between hazmat truck drivers' violation frequency and the key risk factors. The results show that ZIOP model can handle excessive zero observation problem of violation data properly and differentiate between `always-zero group' drivers and drivers who did not violate the traffic rules during research period but would do so in different surroundings. The results also indicate that the violation probability and the violation frequency level of hazmat truck drivers are influenced by driver characteristics, freight order attributes, and drivers' violation records. This research provides guidance for driving training and safety education of hazmat truck drivers, and will be helpful in building better driving simulation models.

Evaluating bus accident risks in public transport

Public transit buses may be considered a safer transportation mode as opposed to others (e.g., private cars). However, safety is a crucial issue regarding transit buses from the perspectives of operators and passengers due to the relevant implications it generates. Therefore, evaluating the accident risk on bus routes provides an opportunity to improve the safety performance of transit operators. Previous research identified patterns of bus accidents and shed light on understanding the effects of many factors regarding frequency and severity of bus accidents. However, no studies have investigated accident risks in bus transit, while considering frequency, severity and exposure factors in a single function.This paper proposes a new methodology for evaluating the accident risk for each transit bus route. At first, the methodology identifies the risk components in terms of frequency, severity and exposure factors that may affect bus accidents. Next, it integrates these terms, to build a risk bus accident function providing a ranking of safety performance for each route.The feasibility of this methodology is demonstrated in a real case study using 3,457 bus accidents provided by a mid-sized Italian bus operator. This experiment shows that transit managers could adopt this methodology to perform an accurate safety analysis on each route. Moreover, this methodology may be implemented in a road traffic safety management system for bus transit operators interested in the monitoring of safety performance, in the evaluation of the risk of accidents on routes, and in the certification process according to recent safety norms.

Identification of Traffic Accident Hotspots using Geographical Information System (GIS)

Limiting the number andseverity of traffic accidents is one of the major goals of road traffic safety management.The alarming rate of road accidents globally emphasizes the importance of an effective traffic safety management system. Identification of accident hotspots is the first step towards implementation of efficient traffic safety management.Until the arrival of Geographical Information System (GIS),traffic accident analyses have been performed based ontraditional statistical methods alone. The advent of GIS-based techniques has led toimproved traffic accident analysis by employing spatial statistics,enabling engineers and researchers to account for variation in the spatial characteristics of hotspot locations in the analysis. This paper discusses the different spatial and statistical methods that are employedintraffic accident hotspots identification. An example application of Planar Kernel Density Estimation (PKDE)for hotspot identification is presented based on crash data for Des Moines city of Iowa state. The effect of varying bandwidths in creating density mapsis investigated and the optimum bandwidth to obtain distinct hotspots is identified as 500 m for the chosen study area.The paper also discusses the scope for future research in traffic accident hotspot analysis.

Premises of the creation of a digital traffic safety management system

Aim.The digital transformation of the traffic safety management system in JSC RZD involves top-level integration with the operating processes of all business units in terms of integral assessment of the risk of possible events and achievement of specified indicators. The result will be the merger of the traffic safety management system with the processes of all levels of the company’s management enabled by an integrated intelligent system for managing processes and services whose functionality includes real-time traffic safety management.Methods. The paper uses system analysis of existing approaches and methods of processing of large quantities of structured and unstructered data.Results. The paper examines the development stages of train traffic safety management, as well as automated information and control systems that enable traffic safety management. General trends in the creation of systems for collection and processing of information are analyzed. The applicability of such technologies as Big Data, Data Mining, Data Science as part of advanced control systems is shown. The paper examines the performance of the above technologies by analyzing the effect of various factors on the average daily performance of a locomotive, where, at the first level, such factors as average daily run of a locomotive, average trainload are taken into consideration; at the second level, the focus is on the service speed, locomotive turnover at station, etc.; at the sixth level, the focus is on the type of locomotive, its technical state, etc. It is shown that statistical methods of factor analysis and link analysis combined with such other methods of Data Mining as methods of simulation and prediction, the average daily performance of a locomotive can be planned proactively. The author proposes a procedure of migration towards a digital traffic safety management system that would be based on models of interaction of safety and dependability factors of all railway facilities at all railway levels of hierarchy, as well as in association with other factors that have no direct relation to dependability, yet affect the safety of the transportation process.Conclusions. The primary benefit of migration towards Big Data consists in the development of a dynamic model of traffic safety, the elimination of human factor in control systems. Most importantly, it enables the creation within the Russian Railways company (JSC RZD) of an integrated intelligent process and service management system that enables real-time traffic safety management. An extensive process of development and deployment within the company of the URRAN Single Corporate Platform (SCP) enabled executive decision support as regards risk-based functional dependability and safety of transportation facilities. Thus, the URRAN SCP sets the stage for the digital transformation of the traffic safety management system in JSC RZD.

Improving Road Traffic Safety Through the Use of Innovative Technologies

The use of innovative technologies is the most effective and promising way to improve the road traffic safety management system. The relevance of the work is expressed in the need for continuous implementation of innovations in the context of growing disproportion between the sharp increase in the number of vehicles, high traffic intensity, and imperfection of road traffic management (problems of existing infrastructure, poor information support for road users, etc.), which results in road traffic injuries and deaths. In the course of the research, it was found that in the context of the Republic of Adygea, using rumble strips installed at the road shoulder reduces the number of run-off-road collisions by 30%, while using centerline rumble strips reduces the number of cross-over incidents and resultant head-on collisions by 15%.

Real-time crash prediction models: State-of-the-art, design pathways and ubiquitous requirements

Proactive traffic safety management systems can monitor traffic conditions in real-time, identify the formation of unsafe traffic dynamics, and implement suitable interventions to bring unsafe conditions back to normal traffic situations. Recent advancements in artificial intelligence, sensor fusion and algorithms have brought about the introduction of a proactive safety management system closer to reality. The basic prerequisite for developing such a system is to have a reliable crash prediction model that takes real-time traffic data as input and evaluates their association with crash risk. Since the early 21st century, several studies have focused on developing such models. Although the idea has considerably matured over time, the endeavours have been quite discrete and fragmented at best because the fundamental aspects of the overall modelling approach substantially vary. Therefore, a number of transitional challenges have to be identified and subsequently addressed before a ubiquitous proactive safety management system can be formulated, designed and implemented in real-world scenarios. This manuscript conducts a comprehensive review of existing real-time crash prediction models with the aim of illustrating the state-of-the-art and systematically synthesizing the thoughts presented in existing studies in order to facilitate its translation from an idea into a ready to use technology. Towards that journey, it conducts a systematic review by applying various text mining methods and topic modelling. Based on the findings, this paper ascertains the development pathways followed in various studies, formulates the ubiquitous design requirements of such models from existing studies and knowledge of similar systems. Finally, this study evaluates the universality and design compatibility of existing models. This paper is, therefore, expected to serve as a one stop knowledge source for facilitating a faster transition from the idea of real-time crash prediction models to a real-world operational proactive traffic safety management system.