Kernel density estimation and K-means clustering to profile road accident hotspots

Identifying road accident hotspots is a key role in determining effective strategies for the reduction of high density areas of accidents. This paper presents (1) a methodology using Geographical Information Systems (GIS) and Kernel Density Estimation to study the spatial patterns of injury related road accidents in London, UK and (2) a clustering methodology using environmental data and results from the first section in order to create a classification of road accident hotspots. The use of this methodology will be illustrated using the London area in the UK. Road accident data collected by the Metropolitan Police from 1999 to 2003 was used. A kernel density estimation map was created and subsequently disaggregated by cell density to create a basic spatial unit of an accident hotspot. Appended environmental data was then added to the hotspot cells and using K-means clustering, an outcome of similar hotspots was deciphered. Five groups and 15 clusters were created based on collision and attribute data. These clusters are discussed and evaluated according to their robustness and potential uses in road safety campaigning.     

Cross-analysis of hazmat road accidents using multiple databases

Road selection for hazardous materials transportation relies heavily on risk analysis. With risk being generally expressed as a product of the probability of occurrence and the expected consequence, one will understand that risk analysis is data intensive. However, various authors have noticed the lack of statistical reliability of hazmat accident databases due to the systematic underreporting of such events. Also, official accident databases alone are not always providing all the information required (economical impact, road conditions, etc.). In this paper, we attempt to integrate many data sources to analyze hazmat accidents in the province of Quebec, Canada. Databases on dangerous goods accidents, road accidents and work accidents were cross-analyzed. Results show that accidents can hardly be matched and that these databases suffer from underreporting. Police records seem to have better coverage than official records maintained by hazmat authorities. Serious accidents are missing from government's official databases (some involving deaths or major spills) even though their declaration is mandatory.     

Quantifying safety benefit of winter road maintenance: Accident frequency modeling

This research presents a modeling approach to investigate the association of the accident frequency during a snow storm event with road surface conditions, visibility and other influencing factors controlling for traffic exposure. The results have the premise to be applied for evaluating different maintenance strategies using safety as a performance measure. As part of this approach, this research introduces a road surface condition index as a surrogate measure of the commonly used friction measure to capture different road surface conditions. Data from various data sources, such as weather, road condition observations, traffic counts and accidents, are integrated and used to test three event-based models including the Negative Binomial model, the generalized NB model and the zero inflated NB model. These models are compared for their capability to explain differences in accident frequencies between individual snow storms. It was found that the generalized NB model best fits the data, and is most capable of capturing heterogeneity other than excess zeros. Among the main results, it was found that the road surface condition index was statistically significant influencing the accident occurrence. This research is the first showing the empirical relationship between safety and road surface conditions at a disaggregate level (event-based), making it feasible to quantify the safety benefits of alternative maintenance goals and methods.     

Accident prediction models for urban roads

This paper describes some of the main findings from two separate studies on accident prediction models for urban junctions and urban road links described in [Uheldsmodel for bygader-Del1: Modeller for 3-og 4-benede kryds. Notat 22, The Danish Road Directorate, 1995; Uheldsmodel for bygader- Del2: Modeller for straekninger. Notat 59, The Danish Road Directorate, 1998] (Greibe and Hemdorff, 1995, 1988).The main objective for the studies was to establish simple, practicable accident models that can predict the expected number of accidents at urban junctions and road links as accurately as possible. The models can be used to identify factors affecting road safety and in relation to 'black spot' identification and network safety analysis undertaken by local road authorities.The accident prediction models are based on data from 1036 junctions and 142 km road links in urban areas. Generalised linear modelling techniques were used to relate accident frequencies to explanatory variables.The estimated accident prediction models for road links were capable of describing more than 60% of the systematic variation ('percentage-explained' value) while the models for junctions had lower values. This indicates that modelling accidents for road links is less complicated than for junctions, probably due to a more uniform accident pattern and a simpler traffic flow exposure or due to lack of adequate explanatory variables for junctions.Explanatory variables describing road design and road geometry proved to be significant for road link models but less important in junction models. The most powerful variable for all models was motor vehicle traffic flow.     

An approach to accidents modeling based on compounds road environments

The most common approach to study the influence of certain road features on accidents has been the consideration of uniform road segments characterized by a unique feature. However, when an accident is related to the road infrastructure, its cause is usually not a single characteristic but rather a complex combination of several characteristics. The main objective of this paper is to describe a methodology developed in order to consider the road as a complete environment by using compound road environments, overcoming the limitations inherented in considering only uniform road segments. The methodology consists of: dividing a sample of roads into segments; grouping them into quite homogeneous road environments using cluster analysis; and identifying the influence of skid resistance and texture depth on road accidents in each environment by using generalized linear models. The application of this methodology is demonstrated for eight roads. Based on real data from accidents and road characteristics, three compound road environments were established where the pavement surface properties significantly influence the occurrence of accidents. Results have showed clearly that road environments where braking maneuvers are more common or those with small radii of curvature and high speeds require higher skid resistance and texture depth as an important contribution to the accident prevention.     

Multidisciplinary in-depth investigations of head-on and left-turn road collisions

To enhance traffic safety, a multidisciplinary Road Accident Investigation Team was established in Denmark for a 2-year trial period. The objective was to conduct in-depth investigations of specific types of accidents, and to identify effective preventive measures. The team consisted of a road engineer, a vehicle inspector, a police superintendent, a psychologist and a physician. Seventeen serious head-on collisions as well as 17 left-turn collisions were analysed. In collecting data, police reports were supplemented by the team's investigation of accident sites and vehicles involved, and interviews were carried out with the involved road users and witnesses. The drivers, to whom the accident factors were primarily related in the head-on collisions, were characterised by their conscious risk-taking behaviour. They were all males; several of them were under age 40 and had earlier traffic and/or drug convictions. The main accident factors were excessive speed, drunk driving and driving under the influence of illegal drugs. In the left-turn accidents, the most common accident factors were attention errors, and it was also noted that elderly drivers ( > 74) were over-represented. The synergy effect of working as a multidisciplinary team proved fruitful. It resulted in a more precise knowledge of the road accident circumstances and of contributing factors leading up to the accidents. Due to the great demand on resources, only a limited number of accidents could be analysed, but the results provide a basis for further and more targeted research.     

Rough set approach for accident chains exploration

This paper presents a novel non-parametric methodology--rough set theory--for accident occurrence exploration. The rough set theory allows researchers to analyze accidents in multiple dimensions and to model accident occurrence as factor chains. Factor chains are composed of driver characteristics, trip characteristics, driver behavior and environment factors that imply typical accident occurrence. A real-world database (2003 Taiwan single auto-vehicle accidents) is used as an example to demonstrate the proposed approach. The results show that although most accident patterns are unique, some accident patterns are significant and worth noting. Student drivers who are young and less experienced exhibit a relatively high possibility of being involved in off-road accidents on roads with a speed limit between 51 and 79 km/h under normal driving circumstances. Notably, for bump-into-facility accidents, wet surface is a distinctive environmental factor.     

Models relating traffic safety with road environment and traffic flows on arterial roads in Addis Ababa

This paper presents the study carried out to develop accident predictive models based on the data collected on arterial roads in Addis Ababa. Poisson and negative binomial regression methods were used to relate the discrete accident data with the road and traffic flow explanatory variables. Significant accident predictive models were found with a number of significant explanatory variables. The results show that the existing inadequate road infrastructure and poor road traffic operations are the potential contributors of this ever-growing challenge of the road transport in Addis Ababa. The results also indicate that improvements in roadway width, pedestrian facilities, and access management are effective in reducing road traffic accidents.     

Impact of traffic states on freeway crash involvement rates

Freeway traffic accidents are complicated events that are influenced by multiple factors including roadway geometry, drivers’ behavior, traffic conditions and environmental factors. Among the various factors, crash occurrence on freeways is supposed to be strongly influenced by the traffic states representing driving situations that are changed by road geometry and cause the change of drivers’ behavior. This paper proposes a methodology to investigate the relationship between traffic states and crash involvements on the freeway. First, we defined section-based traffic states: free flow (FF), back of queue (BQ), bottleneck front (BN) and congestion (CT) according to their distinctive patterns; and traffic states of each freeway section are determined based on actual measurements of traffic data from upstream and downstream ends of the section. Next, freeway crash data are integrated with the traffic states of a freeway section using upstream and downstream traffic measurements. As an illustrative study to show the applicability, we applied the proposed method on a 32-mile section of I-880 freeway. By integrating freeway crash occurrence and traffic data over a three-year period, we obtained the crash involvement rate for each traffic state. The results show that crash involvement rate in BN, BQ, and CT states are approximately 5 times higher than the one in FF. The proposed method shows promise to be used for various safety performance measurement including hot spot identification and prediction of the number of crash involvements on freeway sections.     

Scenario analysis of freight vehicle accident risks in Taiwan

This study develops a quantitative risk model by utilizing Generalized Linear Interactive Model (GLIM) to analyze the major freight vehicle accidents in Taiwan. Eight scenarios are established by interacting three categorical variables of driver ages, vehicle types and road types, each of which contains two levels. The database that consists of 2043 major accidents occurring between 1994 and 1998 in Taiwan is utilized to fit and calibrate the model parameters. The empirical results indicate that accident rates of freight vehicles in Taiwan were high in the scenarios involving trucks and non-freeway systems, while; accident consequences were severe in the scenarios involving mature drivers or non-freeway systems. Empirical evidences also show that there is no significant relationship between accident rates and accident consequences. This is to stress that safety studies that describe risk merely as accident rates rather than the combination of accident rates and consequences by definition might lead to biased risk perceptions. Finally, the study recommends using number of vehicle as an alternative of traffic exposure in commercial vehicle risk analysis. The merits of this would be that it is simple and thus reliable; meanwhile, the resulted risk that is termed as fatalities per vehicle could provide clear and direct policy implications for insurance practices and safety regulations.     

Analysis of accident inequality of the Spanish fishing fleet

There is at present a clear tendency to consider safety as a vital factor in the running of a country's fishing sector. However, the planning of the necessary resources and their adequate distribution according to the sector's needs is only possible if detailed information is available about the degree of concentration of the accidentality of that sector.

In this context, the aim of this work is two-fold: firstly, to formalise a methodology for the fishing sector of a country which allows the inequality in the concentration of accidents to be analysed; and secondly, to apply this methodology to the Spanish fishing fleet for the period 1994–2002. Thus, indices are built by regions and by types of vessel for two variables: fishermen and vessels. Results are obtained both for the inequality in the concentration of accidents and their associated Lorenz curves and for the rates and elasticities of fishing sector accidents.     

Multiple-vehicle traffic accidents in Hong Kong

‘Multiple-vehicle traffic accident’ refers to a crash between two or more moving objects. Unlike single-vehicle accidents, not all drivers involving in a multiple-vehicle accident are responsible for the occurrence of the event. Accordingly, variables such as road type, speed limit and number of vehicles involved in the accident are expected to play a much more important role in association with injury severity in multiple-vehicle accidents. To study the factors influencing injury severity of multiple-vehicle traffic accidents, a population-based study was conducted. The traffic accident data was obtained from the Traffic Accident Data System (TRADS), which was developed by the Transport Department, Police Force and Information Technology Services Department, Hong Kong. Multiple-vehicle traffic accidents (N = 10,630) occurring during the 2-year period 1999/2000 were considered. Potential risk factors such as district, human, vehicle, safety, environmental and site factors were examined. Categorizing injury severity into “fatal/serious” and “slight”, a stepwise logistic regression model was applied to the population data set. The district board, time of the accident, driver's gender, vehicle type, road type, speed limit and the number of vehicles involved are significant factors influencing the injury severity. Identification of risk factors for severe traffic accidents provides valuable information to help with new and improved road safety control measures.     

The effects of congestion charging on road traffic casualties: A causal analysis using difference-in-difference estimation

This paper aims to identify the impacts of the London congestion charge on road casualties within the central London charging zone. It develops a full difference-in-difference (DID) model that is integrated with generalized linear models, such as Poisson and Negative Binomial regression models. Covariates are included in the model to adjust for factors that violate the parallel trend assumption, which is critical in the DID model. The lower Bayesian Information Criterion value suggests that the full difference-in-difference model performs well in evaluating the relationship between road accidents and the London congestion charge as well as other socio-economic factors. After adjusting for a time trend and regional effects, the results show that the introduction of the London congestion charge has a significant influence on the incidence of road casualties. The congestion charge reduces the total number of car accidents, but is associated with an increase in two wheeled vehicle accidents.     

Effects of road geometry and traffic volumes on rural roadway accident rates

This paper revisits the question of the relationship between rural road geometric characteristics, accident rates and their prediction, using a rigorous non-parametric statistical methodology known as hierarchical tree-based regression. The goal of this paper is twofold: first, it develops a methodology that quantitatively assesses the effects of various highway geometric characteristics on accident rates and, second, it provides a straightforward, yet fundamentally and mathematically sound way of predicting accident rates on rural roads. The results show that although the importance of isolated variables differs between two-lane and multilane roads, 'geometric design' variables and pavement condition' variables are the two most important factors affecting accident rates. Further, the methodology used in this paper allows for the explicit prediction of accident rates for given highway sections, as soon as the profile of a road section is given.     

Impact of safety belt use on road accident injury and injury type in Kuwait

The enactment of Kuwait's seat belt law in January 1994 provided an opportunity to examine the impact of seat belt use on road accident fatalities and injury types in this affluent Persian Gulf nation. Via a structured data form, the results of injurious/fatal road accidents for more than 1200 accident victims were gathered from the files of the six major government hospitals which treat most traffic accident victims. Statistical analysis of the data showed that seat belt use has had a positive effect in reducing both road traffic fatalities and multiple injuries in Kuwait. The use of seat belts has also affected the nature of the injuries resulting from road traffic accidents. Non-users of belts experienced higher frequencies of head, face, abdominal and limb injuries. Users of belts, on the other hand, suffered higher frequencies of neck and chest injuries. The interrelationship between the victim, his age, and the type of injuries resulting from road traffic accidents is also investigated.     

Bayesian random effect models incorporating real-time weather and traffic data to investigate mountainous freeway hazardous factors

Freeway crash occurrences are highly influenced by geometric characteristics, traffic status, weather conditions and drivers’ behavior. For a mountainous freeway which suffers from adverse weather conditions, it is critical to incorporate real-time weather information and traffic data in the crash frequency study. In this paper, a Bayesian inference method was employed to model one year's crash data on I-70 in the state of Colorado. Real-time weather and traffic variables, along with geometric characteristics variables were evaluated in the models. Two scenarios were considered in this study, one seasonal and one crash type based case. For the methodology part, the Poisson model and two random effect models with a Bayesian inference method were employed and compared in this study. Deviance Information Criterion (DIC) was utilized as a comparison factor. The correlated random effect models outperformed the others. The results indicate that the weather condition variables, especially precipitation, play a key role in the crash occurrence models. The conclusions imply that different active traffic management strategies should be designed based on seasons, and single-vehicle crashes have different crash mechanism compared to multi-vehicle crashes.     

Bayes classifiers for imbalanced traffic accidents datasets

Traffic accidents data sets are usually imbalanced, where the number of instances classified under the killed or severe injuries class (minority) is much lower than those classified under the slight injuries class (majority). This, however, supposes a challenging problem for classification algorithms and may cause obtaining a model that well cover the slight injuries instances whereas the killed or severe injuries instances are misclassified frequently. Based on traffic accidents data collected on urban and suburban roads in Jordan for three years (2009–2011); three different data balancing techniques were used: under-sampling which removes some instances of the majority class, oversampling which creates new instances of the minority class and a mix technique that combines both. In addition, different Bayes classifiers were compared for the different imbalanced and balanced data sets: Averaged One-Dependence Estimators, Weightily Average One-Dependence Estimators, and Bayesian networks in order to identify factors that affect the severity of an accident. The results indicated that using the balanced data sets, especially those created using oversampling techniques, with Bayesian networks improved classifying a traffic accident according to its severity and reduced the misclassification of killed and severe injuries instances. On the other hand, the following variables were found to contribute to the occurrence of a killed causality or a severe injury in a traffic accident: number of vehicles involved, accident pattern, number of directions, accident type, lighting, surface condition, and speed limit. This work, to the knowledge of the authors, is the first that aims at analyzing historical data records for traffic accidents occurring in Jordan and the first to apply balancing techniques to analyze injury severity of traffic accidents.     

An artificial neural network-based expert system for the appraisal of two-car crash accidents

This paper employs artificial neural network (ANN) to develop an accident appraisal expert system. Two ANN models-- party-based and case-based-- with different hidden neurons are trained and validated by k-fold (k=3) cross validation method. A total of 537 two-car crash accidents (1074 parties involved) are randomly and equally divided into three subsets. For the comparison, a discrimination analysis (DA) model is also calibrated. The results show that the ANN model can achieve a high correctness rate of 85.72% in training and 77.91% in validation and a low Schwarz's Bayesian information criterion (SBC) of -0.82 in training and 0.13 in validation, which indicates that the ANN model is suitable for accident appraisal. Furthermore, in order to measure the importance of each explanatory variable, a general influence (GI) index is computed based on the trained weights of ANN. It is found that the most influential variable is right-of-way, followed by location and alcoholic use. This finding concurs with the prior knowledge in accident appraisal. Thus, for the fair assessment of accident liabilities the correctness of these three key variables is of critical importance to police investigation reports.     

The effectiveness of antilock braking systems in reducing accidents in Great Britain

Antilock braking systems (ABS) are fitted to many new cars with the aims of improving their ability to steer while braking heavily and of reducing stopping distances on some road surfaces. This paper presents the findings of a project that assessed the effectiveness of ABS in reducing accidents in Great Britain. A large postal survey was carried out of the owners of modern cars. asking for details of any accidents in which they had been involved during the previous year as well as factors that might influence their likelihood of being involved in an accident. Questions were also asked to test respondents' knowledge of ABS. ABS cars ditfered in several respects from non-ABS cars, as did the two groups of drivers. Consequently, a sophisticated statistical analysis was required to provide unbiased estimates of the effectiveness of ABS. Various results did not achieve statistical significance, but the overall stability of the results indicates that real effects have been measured. They confirm that ABS does have the potential to reduce the number of accidents, but show that this has not been fully achieved. One reason may be that many drivers have little or no knowledge of ABS.