Severe Traffic Accidents Research Articles

Geographical Analysis and Mapping of Road Traffic Accident Occurrence and Severity in Nigeria

The advantage of automobile transportation does not overcome its shortcomings. Foremost among these is road traffic accident which is serious cause of death in the whole world today. This study examined and mapped rate of reported cases of road accidents across the 36 States and the federal capital of Nigeria between 2013 and 2015. Data acquired from Federal Bureau of Statistics was analysed using descriptive and inferential statistical methods. Bar charts, graphs, dot map and thematic map were prepared to depict the spatial distribution of the occurrences and fatality classification while regression analysis was used to predict the future situation of road accident in Nigeria. Results showed that; highest rate of accidents 36.9% occurred in the year 2013 with 5,539 deaths. Ogun State recorded highest number of accidents with 9.7% in 2013, Lagos State with 15.4% in 2014 and Ogun State with 6.1% in 2015 which can be attributed to the strategic position of these two States as the gate ways to Nigeria economy. The regression result shows the strong positive relationship between numbers of recorded cases of road accident and death from road traffic accident with regression R value of 0.78 and R² of 0.61 respectively.

LAW -theory and practice No. 4 / 2021

The exogenous characteristics of traffic participants, such as: alcoholism, fatigue and psychoactive substances, have a significant impact on a safe behaviour in traffic, especially the motor vehicle drivers. In that sense, they represent the factors that can directly influence the unsafe behaviour in traffic. The influence of the exogenous characteristics on a safe behaviour of traffic participants has been analysed on the basis of the statements in documents as well as the results of numerous empirical studies. For the purposes of this paper, there have been selected and analysed the statistical data on the influential factors of traffic accidents for the period from 2010 to 2019 in Republic of Serbia. After reviewing the statistical data, both a qualitative and quantitative content analyses were performed. In addition to the statistical method, there were also used the content analysis methods, empirical method, descriptive method, comparative methods, as well as deduction and induction methods, in order to analyse the trend and presence of these influential factors of traffic accidents in Republic of Serbia. The statistical data being processed in this paper, originated from the database of the Traffic Safety Agency of Republic of Serbia. The results of the research show the extent to which the exogenous characteristics affect a safe behaviour of traffic participants, as well as the severity of the consequences of traffic accidents. Observed individually, the listed characteristics have a different intensity of influence on a safe behaviour in traffic. In this regard, from the external characteristics of traffic delinquents, the most common is the drunk driving as an influential factor, which especially affects the severity of traffic accidents in Republic of Serbia.

RFCNN: Traffic Accident Severity Prediction Based on Decision Level Fusion of Machine and Deep Learning Model

Traffic accidents on highways are a leading cause of death despite the development of traffic safety measures. The burden of casualties and damage caused by road accidents is very high for developing countries. Many factors are associated with traffic accidents, some of which are more significant than others in determining the severity of accidents. Data mining techniques can help in predicting influential factors related to crash severity. In this study, significant factors that are strongly correlated with the accident severity on highways are identified by Random Forest. Top features affecting accidental severity include distance, temperature, wind_Chill, humidity, visibility, and wind direction. This study presents an ensemble of machine learning and deep learning models by combining Random Forest and Convolutional Neural Network called RFCNN for the prediction of road accident severity. The performance of the proposed approach is compared with several base learner classifiers. The data used in the analysis include accident records of the USA from February 2016 to June 2020. Obtained results demonstrate that the RFCNN enhanced the decision-making process and outperformed other models with 0.991 accuracy, 0.974 precision, 0.986 recall, and 0.980 F-score using the 20 most significant features in predicting the severity of accidents.

A review on neural network techniques for the prediction of road traffic accident severity

Abstract The occurrence rate of death and injury due to road traffic accidents is rising increasingly globally day by day. For several decades, the focus of research has been on getting a deeper understanding of the significant factors that influence the risk of road traffic fatalities. In today's modern world, neural network (NN) approaches play a crucial role in identifying the contributing factors that describe the frequency and severity of road accidents. Over the years, many researchers used neural network models for predicting the impact of such factors on road accident injury severity. Deep learning methods such as the recurrent neural network (RNN) and the convolutional neural network (CNN) has recently been successfully used for the prediction of road accidents and demonstrate their high accuracy and efficiency. This study overview and summarizes the different forms of neural network models such as the single layer perceptron (SLP) neural network, the multilayer layer perceptron (MLP) neural network, the radial basis function (RBF) neural network, the recurrent neural network, and the convolutional neural network used as a prediction method for the severity of road crash injuries and includes a discussion of future planning and difficulties. This article also summarizes the model input parameter or independent variable and output or dependent variable, as well as various performance assessment methods.

An Alternative Method for Traffic Accident Severity Prediction: Using Deep Forests Algorithm

Traffic safety has always been an important issue in sustainable transportation development, and the prediction of traffic accident severity remains a crucial challenging issue in the domain of traffic safety. A huge variety of forecasting models have been proposed to meet this challenge. These models gradually evolved from linear to nonlinear forms and from traditional statistical regression models to current popular machine learning models. Recently, a machine learning algorithm called Deep Forests based on the decision tree ensemble has aroused widespread concern, which was proposed for the first time by a research team of Nanjing University. This algorithm was proved to be more accurate and robust in comparison with other machine learning algorithms. Motivated by this benefit, this study employs the UK road safety dataset to propose a novel method for predicting the severity of traffic accidents based on the Deep Forests algorithm. To verify the superiority of our proposed method, several other machine learning algorithm-based perdition models were implemented to predict traffic accident severity with the same dataset, and the prediction results show that the Deep Forests algorithm present good stability, fewer hyper-parameters, and the highest accuracy under different level of training data volume. It is expected that the findings from this study would be helpful for the establishment or improvement of effective traffic safety system within a sustainable transportation system, which is of great significance for helping government managers to establish timely proactive strategies in traffic accident prevention and effectively improve road traffic safety.

Effects of Human Factors on Public Use of Standing-Type Personal Mobility Vehicle

To significantly reduce the occurrence of severe traffic accidents, reducing the number of vehicles in urban areas should be considered. Personal mobility is essential for realizing this reduction, which requires consideration of the last-/first-mile problem. The overall objective of our research is to solve this problem using standing-type personal mobility vehicles as transportation devices; however, to evaluate the feasibility of such vehicles as future mobility devices, it is necessary to evaluate their operation under real-world conditions. Therefore, in this study, experimental and survey data relating to the velocity, stability, safety, and comfort of a standing-type personal mobility device are obtained to evaluate its performance in three different scenarios. The results show that the personal mobility vehicle is socially well received and can be safely operated on sidewalks, irrespective of the gender or age of the driver; moreover, the results suggest that subjects who routinely use a bicycle are adept at avoiding and absorbing the impacts of small holes and bumps, thereby yielding reduced acceleration values (in all directions) and pitch, roll, and yaw rates. This is anticipated to benefit the future development of personal mobility devices and help realize effective and accessible public transport systems, as well as reduce the number of vehicles in urban areas.

Critical Factors Analysis of Severe Traffic Accidents Based on Bayesian Network in China

The purpose of this study is to minimize the negative influences of the severe traffic accidents in China by profoundly analyzing the complex coupling relations among accident factors contributing to the single-vehicle and multivehicle traffic accidents with the Bayesian network (BN) crash severity model. The BN model was established by taking the critical factors identified with the improved grey correlation analysis method as node variables. The severe traffic accident data collected from accident reports published in China were used to validate this model. The model’s efficiency was validated objectively by comparing the conditional probability obtained by this model with the actual value. The result shows that the BN model can reflect the real relations among factors and can be seen as the target network for the severe traffic accidents in China. Besides, based on BN’s junction tree engine, five-factor combination sequences for the number of deaths and three-factor combination sequences for the number of injuries were ranked according to the severity degree to reveal the critical reasons and reduce the massive traffic accidents damage.

Determination of Black Site Area Based on Equivalent Accident Number Analysis: Case Study National Roads in Ambon City

This study was conducted to determine accident-prone areas (black sites) on national roads in Ambon City using the Equivalent Accident Number (EAN) and Upper Control Limit (UCL) criteria. Primary data was obtained by direct survey. Meanwhile, secondary data was obtained from various sources related to the number of traffic accidents in Ambon City. The data were analyzed using simple statistical methods and tabulated based on the number of accidents in 2019. The analysis results showed that the high severity of traffic accidents in Ambon City was 91.95% caused by driver behavior factors. Three other factors that cause traffic accidents include drunkenness, carelessness, and drowsiness. The study results showed five black site areas on national roads in Ambon City based on EAN value higher than the UCL value. These locations include roads: Jenderal Sudirman, Pierre Tendean, Wolter Monginsidi, Laksdya Leo Wattimena, and Putuhena. Meanwhile, the Sisingamangaraja road segment has a higher EAN value than the UCL value but not the national road segment (province road segment). Based on these results, several things need to be done to overcome the accident rate. Therefore, national road management agencies and stakeholders, especially those related to the black site area, are advised to: build road medians, add zebra cross-shaped crossing facilities and be equipped with shelters in the road median, complete traffic signs installed with signs that read accident-prone area, build pedestrian protective fences, and traffic management engineering.

Road accident prediction and model interpretation using a hybrid K-means and random forest algorithm approach

Road accident severity is a major concern of the world, particularly in underdeveloped countries. Understanding the primary and contributing factors may combat road traffic accident severity. This study identified insights and the most significant target specific contributing factors for road accident severity. To get the most determinant road accident variables, a hybrid K-means and random forest (RF) approaches developed. K-means extract hidden information from road accident data and creates a new feature in the training set. The distance between each cluster and the joining line of k1 and k9 calculated and selected maximum value as k. k is an optimal value for the partition of the training set. RF employed to classify severity prediction. After comparing with other classification techniques, the result revealed that among classification techniques, the proposed approach disclosed an accuracy of 99.86%. The target-specific model interpretation result showed that driver experience and day, light condition, driver age, and service year of the vehicle were the strong contributing factors for serious injury, light injury, and fatal severity, respectively. The outcome demonstrates the predictive supremacy of the approach in road accident prediction. Road transport and insurance agencies will be benefited from the study to develop road safety strategies.

A novel public dataset for multimodal multiview and multispectral driver distraction analysis: 3MDAD

Driver distraction and fatigue have become one of the leading causes of severe traffic accidents. Hence, driver inattention monitoring systems are crucial. Even with the growing development of advanced driver assistance systems and the introduction of third-level autonomous vehicles, this task is still trending and complex due to challenges such as the illumination change and the dynamic background. To reliably compare and validate driver inattention monitoring methods, a limited number of public datasets are available. In this paper, we put forward a public, well-structured and complete dataset, named Multiview, Multimodal and Multispectral Driver Action Dataset (3MDAD). The dataset is mainly composed of two sets: the first one recorded in daytime and the second one at nighttime. Each set consists of two synchronized data modalities, both from frontal and side views. More than 60 drivers are asked to execute 16 in-vehicle actions under a wide range of naturalistic driving settings. In contrast to other public datasets, 3MDAD presents multiple modalities, spectrums and views under different time and weather conditions. To highlight the utility of our dataset, we independently analyze the driver action recognition results adapted to each modality and those obtained of several combinations of modalities.

Optimization design of highway cable barriers based on collision safety consideration

The severity of traffic accident on the highway has raised more and more public concerns on the crash safety of road traffic. In order to reduce the severity of crashes on the highway, various traffic barrier systems have been adopted. Among these, the cable barriers play a very important role in highway crashes by protecting vehicles, absorbing collision energy, changing the vehicle’s going direction, etc. In this study, the multi-objective optimization was made with objectives of crash safety indicators of cars and design variables of dimensional sizes of cable barriers. The coupled finite element model of the car together with the cable barrier system was established, and full-scale crash simulations between the car and the cable barrier system were carried out on design sample points. The nonlinear regressions of objectives were constructed by using the radial basis function. The Pareto sets and the optimal solution were obtained by using the multi-island genetic algorithm. The optimal solution showed improved performance compared to the original design, which can provide efficient guidance for the design of highway cable barriers.

Pedal Misapplication: Interruption Effects and Age-Related Differences.

ObjectiveThis study aimed to investigate whether pedal misapplication occurs more frequently when a pedal task is interrupted for a longer period of time.BackgroundMisapplication of a vehicle’s brake and accelerator pedals can cause severe traffic accidents, especially for older drivers. The present study provides empirical support for the hypothesis that pedal misapplication occurs more frequently when drivers are interrupted for longer periods of time and is demonstrated more prominently in older drivers.MethodsForty younger participants and 40 older participants were asked to perform a pedal choice response task (stepping on either a brake or accelerator pedal) that had been preceded by an interruption task (i.e., touch number task).ResultsPedal misapplications occurred more frequently when the pedal choice response task was preceded by the touch number task for a longer interval (about 120 s) than for a shorter interval (about 30 s). Furthermore, the time-related increase in pedal misapplications was greater for older participants.ConclusionPedal misapplication increases when the pedal task is interrupted for a longer time period, especially for older adults.ApplicationThe findings contribute to our understanding of when and where pedal misapplications tend to occur.

The Effect of Road Surface Roughness to Recommended Speed of Vehicles

Road safety is one of the major concerns of the transportation system planners and managers in any nation. The principle goal of road safety is to reduce the frequency and severity of traffic accidents. The design and manufacturing of high-quality road directly play an important role in achieving better road safety. This research presents the model describing the relationship between road surface roughness with the vehicle’s recommended safe velocity. The result shows that the road surface roughness measured by the International Roughness Index (henceforth IRI) is indirectly proportional to the vehicle’s recommended safe velocity. In particular, if the recommended safe velocity is 100 km/h, the surface roughness IRI should not exceed 1.9 m/km. An implication of this is the possibility that using the simulation on MATLAB Simulink software should have the appropriate IRI concerning the designed speed.

Analysis of Traffic Accident Severity at Intersection Using Logistic Regression Model

Accident severity analysis is an important issue in the field of traffic safety study, and intersections are also locations of relatively high accident rates in the roadway network. Therefore, the main purpose of this study is to establish a prediction model of intersection severity based on the binary logistic regression model of data mining technology. The data source of intersection accident is obtained from the Taichung City Police Department in Taiwan in 2018 and there are 27461 valid samples. The dependent variable is the severity of intersection accident. The independent variables include 9 variables such as month, time of accident, weather condition, light conditions, road type, road surface condition, traffic control type, accident type and vehicle type, and are analyzed by the forward selection (Wald). The research results show that time of accident, road surface condition, accident type and vehicle type have significant effects. The confusion matrix is used to verify the reliability of the model, and the results can be used as the references for reducing the degree of accident injury at the intersection in the future.

Contralateral obturator nerve transfer for femoral nerve restoration: a case report

Background Femoral nerve injury may occur in severe traffic accident injuries with pelvic fracture. Sural nerve grafts or ipsilateral obturator nerve transfer may be used to restore femoral nerve function. We report a new procedure transferring the contralateral obturator nerve to restore femoral nerve function. Case description A 30 year-old male suffering complete lumbar plexus rapture received a contralateral obturator nerve transfer in our hospital. At 2 years follow up he had gained Medical Research Council Grade 3 muscle strength in his 23th months follow-up, with normal gait, Lower Extremity Functional Scale score of 58.75% and Femoral Nerve Motor Function Scale score 61%. Conclusion The contralateral obturator nerve transfer is a reliable alternative if the nerve graft or ipsilateral obturator nerve cannot be performed.

Analysis of the Risk Factors Affecting the Severity of Traffic Accidents on Spanish Crosstown Roads: The Driver’s Perspective

Globally, road traffic accidents are an important public health concern which needs to be tackled. A multidisciplinary approach is required to understand what causes them and to provide the evidence for policy support. In Spain, one of the roads with the highest fatality rate is the crosstown road, a particular type of rural road in which urban and interurban traffic meet, producing conflicts and interference with the population. This paper contributes to the previous existing research on the Spanish crosstown roads, providing a new vision that had not been analyzed so far: the driver’s perspective. The main purpose of the investigation is to identify the contributing factors that increment the likelihood of a fatal outcome based on single-vehicle crashes, which occurred on Spanish crosstown roads in the period 2006-2016. In order to achieve this aim, 1064 accidents have been analyzed, applying a latent cluster analysis as an initial tool for the fragmentation of crashes. Next, a multinomial logit (MNL) model was applied to find the most important factors involved in driver injury severity. The statistical analysis reveals that factors such as lateral crosstown roads, low traffic volumes, higher percentages of heavy vehicles, wider lanes, the non-existence of road markings, and finally, infractions, increase the severity of the drivers’ injuries.

Analysis of traffic accident severity in Baghdad city using Binary Logistic Regression Model

Severity of accident is an important issue to researchers in road safety since this work is interested not only with the prevention of accidents but also with the factors that enhance in reduction of their severity. One of the ways to achieve the latter is to determine the potential factors that influence the severity of accident. This research can be considered as one of the few studies in this approach in Iraq, especially in Baghdad City, where the analysis of accidents has not been carried out for many years since 2003, especially analysis of accidents’ severity. Therefore, it is essential to establish baseline information on accident severity. The data utilized in this research consists of a sample size of (268) observations and it was collected manually from traffic officers due to the deficiency in record system (as there is no specific archive system for registered accident reports). The results from binary logistic regression model indicate that there are three variables significantly associated with severity of accidents namely; site, vehicle body type, and cause of accident.

Did the supreme court liquor shop ban in 2017 on highways impact the incidence and severity of road traffic accidents

Background: Alcohol intoxication plays a major role in the causation of road traffic accidents (RTAs) and assault. On April 1, 2017, the honorable Supreme Court of India banned liquor shops on all national and state highways to a distance of 500 m from them. Out of 231 liquor shops, 178 were closed in Vellore district after the ban. This, we assumed, would have reduced the number of drunken drivers and pedestrians, resulting in the fall in the number and severity of the accidents. Materials and Methods: This is a retrospective observational study done in a tertiary hospital in South India. All RTA patients presented to the emergency department (ED) 1 month before the liquor shop ban (March 2017) were included in the preban group and who presented to the ED 1 month after the liquor shop ban (April 2017) were included in the postban group; their incidence and severity of trauma were assessed and compared. A bivariate analysis was done to identify the relationship between these variables and potential determinants, and their 95% confidence interval (CI) was calculated. For all tests, a two-sided P

Dentify factors and reasons affecting the severity of an accident

An analysis using decision trees to identify factors affecting the severity of traffic accidents was carried out. At the first stage, a distinction was made between the types of incidents that lead to consequences of varying severity, and at the second stage, the points of traffic rules are highlighted that are most often violated and lead to accidents with a high level of injury. Keywords traffic accident; decision trees; traffic rules

Road Accident Analysis and Prediction using Machine Learning Algorithmic Approaches

Ongoing studies have anticipated that in 2030, car crashes will be the fifth driving reason for death around the world. The main cause of car crashes is difficult to decide these days because of a complex mix of qualities like the mental condition of the driver, road conditions, climate conditions, traffic, and infringement of traffic rules to give some examples. The expenses of fatalities and driver wounds because of car crashes incredibly influence the general public. The use of machine learning methods in the field of road accidents is picking up speed nowadays. The organization of machine learning classifiers has swapped conventional data mining methods for creating higher outcomes and exactness. This work presents a review of different existing businesses related to accident prediction utilizing the machine learning area. Wounds because of road accidents are one of the most pervasive reasons for death separated from health-related issues. The investigation of road accident seriousness was finished by running an accident dataset through a few machine learning arrangement calculations to see which model played out the best in characterizing the accidents into severity classes, for example, slight, extreme, and fatal. It was seen that calculated relapse to perform multilevel order gave the most noteworthy exactness score. It was additionally seen that variables, for example, the number of vehicles, lighting conditions, and road highlights assumed a part in deciding the seriousness of the accident. Engineers and analysts in the car business have attempted to plan and manufacture more secure vehicles, yet auto collisions are unavoidable. Examples associated with hazardous accidents could be identified by building up a prediction model that naturally orders the sort of injury severity of different traffic accidents. These social and roadway designs are valuable in the improvement of traffic security control strategies. Significantly, estimates be founded on logical and target reviews of the reasons for accidents and the seriousness of injuries. This paper presents a few models to predict the seriousness of the injury that happened during traffic accidents utilizing machine-learning paradigms. We considered networks prepared to utilize machine learning methods. Analysis results uncover that among the machine learning ideal models considered different standards paradigm approaches.