Accident Prediction Models Research Articles

Prediction of road accidents: comparison of two Bayesian methods

In this paper, two Bayesian methods for the development of accident prediction models are compared: the well-acknowledged Empirical Bayes (EB) method and a recently developed method based on Bayesian Probabilistic Networks (BPNs). Brief descriptions of the two methods are provided and their commonalities, differences, advantages and disadvantages are discussed. Both methods can be used to develop models for the multivariate prediction of accident events and can be included in road infrastructure safety management systems such as road safety impact assessments or road safety audits. Using a comprehensive data-set taken from the Austrian rural motorway network, it is shown that the predictions of both models are in good accordance with the data. It is observed that the BPN models show a higher degree of correlation with the data than the models developed using the EB method, as measured through the higher values of the correlation coefficients (∼5–10%).

Analysis of in Accident Influence Factors Based on Degree of Grey Correlational Model

It is the problem how to search the main factors in various factors on accident. The gray correlation can not only improve the efficiency of the data which have existed, but also remedy the limitation of that carrying out systems analysis by mathematical statistics. From the overall perspective of human-machine-environment, accident prediction model is established and the influencing factors are analyzed of accidents in this paper. The grey correlation degree of the influencing factors is calculated. At last, prediction model of examples is examined. The result shows that the model is applicable and reliable in forecasting the main factors and the relations between them, thus providing reference for traffic administrative department to avoid traffic accidents.

Development of a safety performance function for motorcycle accident fatalities on Malaysian primary roads

This study uses a generalized linear model approach, i.e. negative binomial regression, to develop a predictive model for motorcycle fatal accidents on Malaysian primary roads. For the modeling process, a huge data inventory has been carried out, integrating the road geometry features, fatal accident records and traffic censuses from 3 selected states for the past 3-year period. The results show that motorcycle fatalities per kilometer on primary roads are statistically significantly affected by the average daily number of motorcycles and the number of access points per kilometer. The model established for this study can also be regarded as the first motorcycle safety performance function in Malaysia and probably in Asia. Also noted in this study is the need to establish a proper and systematic road geometry and traffic census inventory in order to develop better accident prediction models for Malaysia in the future.

A tool for safety evaluations of road improvements

Road safety impact assessments are requested in general, and the directive on road infrastructure safety management makes them compulsory for Member States of the European Union. However, there is no widely used, science-based safety evaluation tool available. We demonstrate a safety evaluation tool called TARVA. It uses EB safety predictions as the basis for selecting locations for implementing road-safety improvements and provides estimates of safety benefits of selected improvements. Comparing different road accident prediction methods, we demonstrate that the most accurate estimates are produced by EB models, followed by simple accident prediction models, the same average number of accidents for every entity and accident record only. Consequently, advanced model-based estimates should be used. Furthermore, we demonstrate regional comparisons that benefit substantially from such tools. Comparisons between districts have revealed significant differences. However, comparisons like these produce useful improvement ideas only after taking into account the differences in road characteristics between areas. Estimates on crash modification factors can be transferred from other countries but their benefit is greatly limited if the number of target accidents is not properly predicted. Our experience suggests that making predictions and evaluations using the same principle and tools will remarkably improve the quality and comparability of safety estimations.

Road Accident Prediction Model for the Roads of National Significance of Lithuania

This summary of the author’s PhD thesis defended on 20 December 2012 at the Vilnius Gediminas Technical University. The thesis is written in Lithuanian and is available from the author upon request. Chapter 1 describes the analysis of road infrastructure safety management procedures and their implementation. Chapter 2 gives the overview of accident prediction models and the principles of their development. Chapter 3 presents the designed accident prediction algorithm for the roads of national significance of Lithuania, the developed mathematical accident prediction models for homogenous groups of roads and junctions, the implemented network safety ranking and the determined road sections with a potentially high accident concentration. Chapter 4 describes the testing and analysis of software intended for the implementation of accident prediction algorithm.

Urban Road Network Safety Model at the Transportation Planning Process

The transportation planning process is considered to be the initial step to incorporate the safety analyses of a transport system. Recently, tools have been created for this incorporation, although the vast majority has been applied at an area level. Despite the capacity of these tools to provide safety information, they are unable to identify hazardous locales in the network. The primary objective of this article was to develop a tool based on accident prediction models, which enable the forecasting of the highest accident-risk entities (i.e., nodes or links) using the information available as well as meeting the main issues that are decided at the planning level. Analyzing the influence of macrolevel road design variables on accident risk was the second objective, providing knowledge for planners and decision makers. To accomplish these objectives, generalized linear modeling techniques were employed to develop models for nodes and links using data from Porto, Portugal. The result analysis demonstrates that the additional macrolevel variables are statistically significant and improves the model. Thus, the results lead to a general conclusion that the proposed models are the suitable tool because they embody the balance between the needs and constraints inherent to the planning level.

비선형 회귀분석과 구조방정식을 이용한 지방부 4지 신호교차로의 사고요인분석

사고발생의 주요지점인 신호교차로 교통사고 발생건수는 해마다 증가하고 있어 교통사고를 감소시키기 위한 원인 규명이 매우 필요하다. 국내에서 연구되어진 기존의 교통사고예측 모형들은 대부분 Poisson 모형 등의 비선형 회귀분석을 이용한 사고원인분석이 주를 이루고 있다. 비선형 Econometrics 분석기법들이 사고의 성격을 분석하는데 가장 중요한 통계적 기법이기는 하지만, 도로에서 발생하는 교통사고의 원인분석적 차원에서 접근하면 이런 사고예측 모형들만 가지고 사고발생의 설명변수들을 규명하는데 구조적인 한계가 발생한다. 이는 이러한 통계적 방법들이 사고의 예측력을 높이는데 중점을 두고, 이를 위해 소수의 유효한 설명변수들만을 모형식에 포함시키기 때문이다. 따라서 사고에 대해 보다 구체적인 원인규명을 위해서는 비선형회귀분석모형의 개발과 동시에 비선형 Econometrics 분석기법의 단점을 보완하는 또 다른 통계적 노력이 필요하다. 이에 본 연구에서는 Poisson기법을 이용하여 지방부 4지 신호교차로의 사고예측모형을 개발하였고, 동시에 복합적인 인과관계를 증명하는데 다중변수관계를 포괄적으로 측정하여 탐색하는 구조방정식을 이용하여 사고모형을 개발하여 Poisson 모형의 결과값과 비교 분석하였다. Traffic accidents at signalized intersections have been increased annually so that it is required to examine the causation to reduce the accidents. However, the current existing accident models were developed mainly by using non-linear regression models such as Poisson methods. These non-linear regression methods lack to reveal the complicated causation for traffic accidents, though they are the right choice to study randomness and non-linearity of accidents. Therefore, it is required to utilize another statistical method to make up for the lack of the non-linear regression methods. This study developed accident prediction models for 4 legged signalized intersections with Poisson methods and compared them with structural equation models. This study used structural equation methods to reveal the complicated causation of traffic accidents, because the structural equation method has merits to explain more causational factors for accidents than others.

ANALYSIS OF FATAL-SERIOUS ACCIDENTS AND DANGEROUS VEHICLE MOVEMENTS AT ACCESS POINTS ON MALAYSIAN RURAL FEDERAL ROADS

Traffic accidents have been recognized as one of the major causes of human and economic losses in both developed and developing countries. In 2010, Malaysia recorded a total of 414,421 accidents, resulting in an average of 19 deaths from road accidents every single day. This research analyzed the factors relevant to fatal and serious accidents on rural federal roads in Malaysia. The objectives was to identify the dangerous vehicle movements and factors posing significant risks for fatal-serious accidents at access points (non-signalized minor junctions) and to suggest countermeasures. This research consists if seven Chapters. Firstly, Chapter 1 provides a discussion of accident trends and traffic studies in general. In Chapter 2, the scope was then narrowed down to focus on the accident black spot in order to identify the hazardous or black spot sections. Chapter 3 further examines the quantitative accident records and traffic characteristics for each of the selected sections. Next, Chapter 4 focuses on vehicle movements at non-signalized intersections. Chapter 5 provides the methodology and procedures adopted in the development of accident prediction models. Chapter 6 focuses on the development of gap acceptance model. Finally, Chapter 7 provides the development of serious conflict model. This research carries out numerous surveys to observe various traffic movements, including right and left turns, from minor and major roads, in addition to many other characteristics, in order to construct accident analysis models. One of the findings is that right-turn motorcycles caused serious conflicts and right turn movement was considered to be the most dangerous movement.

Development of Canadian National Pedestrian Crossing Control Guide

In 2010 the Transportation Association of Canada began the 2-year process of updating the 1998 pedestrian crossing control manual. The resulting document, the Pedestrian Crossing Control Guide, is expected to promote uniformity across the country with respect to the approach used in the provision of pedestrian crossing control. This standardization is done through the development of a decision support tool to assist in the decision-making process when the need for pedestrian crossing control is established and in identification of the type of crossing control to use for the location's characteristics. The development of the new Pedestrian Crossing Control Guide for Canada is discussed, and findings of the research that led to its development are presented. The findings fall into two areas: existing Canadian and international pedestrian crossing control practices and safety performance of different pedestrian crossing control devices. Principal conclusions from this research are (a) international practice is changing toward providing guidance rather than formal, numerical warranting procedures in the decision-making process for the provision of pedestrian crossing control; (b) there are pedestrian crossing control treatments for which there is no available literature regarding safety performance, and the available literature for other treatments lacks rigorous safety evaluations; and (c) further research is needed regarding the safety performance of pedestrian crossing control devices, particularly in the areas of understanding pedestrian collisions and developing accident prediction models.

고령운전자 운전 및 신체특성을 반영한 교통사고 분석 연구

65세 이상 고령운전자의 경우 지난 10년 새 교통사고건수는 3만 7,000건에서 27만 4,000건으로 무려 640.5% 증가되었다. 이는 전체사고에서 차지하는 비율이 1.2%에서 3.1배 증가한 3.7%를 차지하고 있는 것으로 교통안전 관련기관에서는 여러 대책을 강구하고 있다. 무엇보다 고령운전자의 행동특성 및 신체특성에 대한 심층연구를 통해 안전대책과 연계하는 방안이 중요하다 할 수 있다. 본 연구에서는 고령운전자의 행동특성을 측정할 수 있는 운전자 적성검사(Driving Aptitude) 항목과 교통사고 자료를 토대로 고령운전자 운전특성과 사고특성을 연결한 실증연구를 수행하였다. 영향모형 개발을 위해 활용한 방법론은 영과잉 회귀모형을 적용하였고, ZIP 회귀모형과 ZINB 회귀모형에 대하여 베이지안 추론을 이용한 사고예측 모형을 선택하였다. AAE분석결과 ZIP 회귀모형이 적합하며, 3가지 변수속도예측, 주의전환, 인지능력이 고령자사고와 영향관계에 있음을 확인할 수 있었다. The number of traffic accidents caused by elderly drivers over the age of 65 has surged over the past ten years from 37,000 to 274,000 cases. The proportion of elderly drivers' accidents has jumped 3.1 times from 1.2% to 3.7% out of all traffic accidents, and traffic safety organizations are pursuing diverse measures to address the situation. Above all, connecting safety measures with an in-depth research on behavioral and physical characteristics of elderly drivers will prove vital. This study conducted an empirical research linking the driving characteristics and traffic accidents by elderly drivers based on the Driving Aptitude Test items and traffic accident data, which enabled the measurement of behavioral characteristics of elderly drivers. In developing the Influence Model, we applied the zero-inflated Poisson (ZIP) regression model and selected an accident prediction model based on the Bayesian Influence in regards to the ZIP regression model and the zero-inflated negative binomial (ZINB) regression model. According to the results of the AAE analysis, the ZIP regression model was more appropriate and it was found that three variables? prediction of velocity, diversion, and cognitive ability? had a relation of influence with traffic accidents caused by elderly drivers.

직광에 의한 눈부심 현상이 터널 출구부 안전성에 미치는 영향 연구

PURPOSES : In Korea, over 70 percent of the land consists of mountainous and rolling area. Thus, tunnels continue its upward trend as road network are extended. In these circumstances, the importance of tunnel has been increased nowadays and then its safety investigation and research should be performed. This study is focus on confirming and improving the safety of tunnel. On tunnel hood, sunglare effect can irritate driver`s behavior instantly and this can result in incident. METHODS : The study of this phenomenon is rarely conducted in domestic and foreign papers, so there is no proper measure for this. This study analyzes the driving environment of the effect of sunglare effect on tunnel hood. RESULTS : Traffic accidents stem from complex set of factors. This study build the Traffic Accident Prediction Models to find out the effect of sunglare effect on tunnel`s hood. The independent variables are traffic volume, geometric design of road, length of tunnel and road side environment. Using these variables, this model estimates accident frequency on tunnel hood by Poisson regression model and Negative binomial regression model. Although Poisson regression model have more proper goodness of fit than Negative binomial regression model, Poisson regression model has overdipersion problem. So the Negative binomial regression model is used in this analysis. CONCLUSIONS : Consequently, the model shows that sunglare effect can play a role in driving safety on tunnel hood. As a result, the information of sunglare effect should be noticed ahead of tunnel hood so this can prevent drivers from being in hazard situation.

Use of Accident Prediction Models in Identifying Hazardous Road Locations

The paper introduces the possibility of using accident prediction models for the identification of hazardous road locations. The application of this method is presented with an example of secondary rural roads in the South Moravian region which are classified into road segments homogeneous in terms of basic geometric and traffic characteristics. The prediction model is represented by a generalized linear model which, on the basis of the available data, determines the expected number of accidents for individual types of road segments. A critical road segment is defined as a segment where the reported number of accidents significantly exceeds the number of expected accidents on roads with similar geometric and traffic characteristics. This method can be used as an effective tool for road network safety management.

Prediction of Mine Accidents Based on Fractal Theory

The mine accident prediction model was established on the basis of the fractal theory. The model has made an accurate check by the existing accident data. The predict results are 73 and 45, and the average relative error rate is 4.8%, which is rather satisfactory than ever compared to the actual data. Finaly, the example based on the model is used to make a prediction to the accidents numbers in June 2012-August 2012, and the predict results are 48, 43 and 44.

How does a modal shift from short car trips to cycling affect road safety?

Governments aim to promote a shift from car to bicycle, but concerns about road safety seem to represent an important argument against this encouragement. This study examines the road safety impact of a modal shift from short car trips to cycling in Dutch municipalities. The road safety effect is estimated using Accident Prediction Models (APMs) that account for the non-linearity of risk. APMs are developed utilizing Negative Binomial regression. This study is the first to develop APMs using crash and mobility data from municipalities, and utilizing these models to estimate the effects of changing modal splits of current car and bicycle use to modal splits that actually exist in these municipalities. The results suggest that, under conditions such as in Dutch municipalities, transferring short trips made by cars to bicycles does not change the number of fatalities, but increases the number of serious road injuries. The neutral effect on fatalities, despite the high fatality risk for cyclists, can be explained by there being fewer cars on the road to pose a risk to others, the shorter length of bicycle trips compared to the car trips they replace, and the “safety in numbers” phenomenon. The rise in the number of serious road injuries is due wholly to the high number of cycling crashes with no other vehicle involved. The effect of a modal shift is dependent on the age of the population in which the shift is concentrated, and can be influenced by measures affecting cyclists’ injury risk.

Safety Performance Function for Motorways using Generalized Estimation Equations

Accident prediction models (APMs) are useful tools for estimating the expected number of crashes over a road network which are typically used in the screening of sites with promise for safety improvements. This study shows a procedure of analysis for motorways network offering a comparison between the conventional analytical techniques based on GLM (Generalized Linear Model) and a different approach based on GEE (General Estimating Equation). The GEE model, incorporating the time trend, is compared in terms of results and reliability in the estimation with conventional models (GLM) that do not take into account the temporal correlation of accident data.

Accidents Prediction Model based on Speed Reduction on Spanish Two-Lane Rural Highways

The speed reductions can affect to the safety of the road. The Interactive Highway Safety Design Model (IHSDM) Design Consistency Module presents an analysis of the relation between the speed reduction and the accidents for horizontal curves on American two-lane rural highways. In this paper a similar study is performed for Spanish two-lane rural highways. A model for predicting accidents through regression analysis is presented using speed reduction between successive tangents and horizontal curves and between successive curves. Significant parameters related to exposure and geometry as explanatory variables are used.

Travel Time in Case of Accident Prediction Model

The aim of this paper is to estimate the travel time along a motorway section, both in undisturbed condition and taking into account a perturbation due to an accident. The estimated travel time is calculated adding the travel time under normal traffic conditions, the time used settling the accident area and the time needed to dissolve the queue. To be applied the model requires the knowledge of accident characteristics, the traffic flow at the accident time and the value of the reduced capacity during the accident management. The model refers to traffic conditions and accident management procedures typical of motorways.

Safety Effect of U-Turn Conversions in Tehran: Empirical Bayes Observational Before-and-After Study and Crash Prediction Models

Directional midblock median openings with left-turn lanes and loons were installed on major highways in Tehran, Iran, to prohibit direct left turns from major and minor roadways and to prevent through movements of minor roadways. Therefore, traffic lights were removed and intersections were converted to U-turns. The safety effect of this treatment was estimated by an empirical Bayesian method that indicated there was an increase of approximately 13.22% in crashes. Moreover, accident prediction models for crash types and frequency were developed to examine the geometry and traffic factors contributing to the crashes at U-turn conversions and to explain the reason some sites showed a decrease in the number of crashes while others showed a large increase. The results of data analysis showed that the increase in weaving length and median opening length resulted in the decrease in angle crashes. Also, the increase in the turn radius resulted in the decrease in angle and total crashes. Total crashes and crash types increased with the average daily traffic (ADT) increase on major roadways and U-turns. Consequently, the result of safety analysis with close examination of each site demonstrated that it is necessary to mention geometric specifications in order to improve the efficiency of the treatment. Therefore, it can be concluded with no reasonable doubt that with a certain range of traffic volume and right geometric specification, the treatment may be safe.

Bayesian analysis for the bivariate Poisson regression model: Applications to road safety countermeasures

Abstract We consider a bivariate Poisson regression model to analyze discrete count datawhen two dependent variables are present. We estimate the regression coecients as-sociated with several safety countermeasures. We use Markov chain and Monte Carlotechniques to execute some computations. A simulation and real data analysis are per-formed to demonstrate model tting performances of the proposed model.Keywords: Accident prediction model, bivariate Poisson distribution, Gibbs sampler,Metropolis-Hastings algorithm, safety countermeasure. 1. Introduction Analysis of discrete count data has been done in various elds, including applied sciences,economics, and transportation engineering. Several models have been proposed in recentdecades to analyze these count data, especially trac crash data. Modeling these data beginswith the multiple linear regression model (MLR) in conjunction with normality assumptionsand homoscedasticity on error terms. The MLR is conceptually sound and computationallyfeasible in estimating regression coecients and explaining correlations between variables.However, these conditions are not compatible with characteristics of crash data. Jovanis andChang (1986) initially propose the Poisson regression model (PRM) to circumvent theselimitations. However, because the Poisson distribution has the same mean and variance, itdoes not often reect typical characteristics such as substantial overdispersion contained incount data. A great deal of work regarding model building for crash data has been basedon the negative binomial regression model (NBRM). See Persaud (1991, 1994), Persaud andDzbik (1993), Lord and Persaud (2004) for the related work based on the NBRM.

Development of an Accident Prediction Model for Intersections of Dhaka City, Bangladesh

Road accidents are increasing at an alarming rate. Every year more than 1.17 million people die in road crashes around the world. The majority of these deaths, about 70 percent occur in developing countries .As a developing country, Bangladesh is not out of this situation. The road safety situation in Bangladesh has been deteriorating with rapid growth in population, motorisation, urbanisation and lack of investment in road safety. The combination of rapid urbanization and motorization has made the problem even severe . For our paper at first we collect data to analysis the severity of accident in Bangladesh. We collect the data of accidents & rearrange these with respect to weather ,collision type, day of week etc .For this arrangement we collect the data of accident for the last five years . Our main concern were the intersections of Dhaka city. We then select twenty five intersections and collect data of road width and number of approaches. Then we develop a model of accident prediction with the collected data. The major findings of our project is we found that accidents increase in good weather ,it may be because in good weather drivers may be more relax and less conscious as they think that everything is seen clearly .Another finding is as Dhaka is a populated city, number of accident with pedestrian is much higher than other type (with vehicle ,other objects etc.) of accidents . Again number of accident increase with increase in number of approaches in a intersection and decrease with increase in road width. From this prediction model we can get the approximate number of accident that can happen per year and we can take proper steps and precautions such as speed breakers , road dividers ,proper signs , marking ,speed limit ,proper signal design to avoid such accidents . General Terms Road safety issue.