Accident Prediction Research Articles

IoT system architecture for monitoring and analyzing public transport data

The crucial role of public transport in the economy and modern city development is widely acknowledged. However, contemporary public transport systems are confronted with several challenges that require resolution. These challenges include real-time monitoring, data management, passengers flow optimization, and road accident prediction. The Internet of Things (IoT) presents a promising avenue for the development of modern public transport management systems. By leveraging a diverse range of technologies, such as sensors, edge devices, cloud computing, and various communication infrastructures, IoT systems can enable the creation of robust and automated public transport infrastructure. In this research, we propose an architecture for a public transport monitoring and management system. The proposed system can effectively collect, store, and monitor public transport data, thereby facilitating efficient management and timely response to risks that arise in the transport system. Implementation of such a system would enable public transport administrators to monitor and swiftly respond to potential problems such as overloaded passenger flows, emergencies, and technical issues with transport systems.

Improved gray correlation analysis and combined prediction model for aviation accidents

PurposeThe purpose of this paper is to identify the key influencing factors of aviation accidents and to predict the aviation accidents caused by the factors.Design/methodology/approachThis paper proposes an improved gray correlation analysis (IGCA) theory to make the relational analysis of aviation accidents and influencing factors and find out the critical causes of aviation accidents. The optimal varying weight combination model (OVW-CM) is constructed based on gradient boosted regression tree (GBRT), extreme gradient boosting (XGBoost) and support vector regression (SVR) to predict aviation accidents due to critical factors.FindingsThe global aviation accident data from 1919 to 2020 is selected as the experimental data. The airplane, takeoff/landing and unexpected results are the leading causes of the aviation accidents based on IGCA. Then GBRT, XGBoost, SVR, equal-weight combination model (EQ-CM), variance-covariance combination model (VCW-CM) and OVW-CM are used to predict aviation accidents caused by airplane, takeoff/landing and unexpected results, respectively. The experimental results show that OVW-CM has a better prediction effect, and the prediction accuracy and stability are higher than other models.Originality/valueUnlike the traditional gray correlation analysis (GCA), IGCA weights the sample by distance analysis to more objectively reflect the degree of influence of different factors on aviation accidents. OVW-CM is built by minimizing the combined prediction error at sample points and assigns different weights to different individual models at different moments, which can make full use of the advantages of each model and has higher prediction accuracy. And the model parameters of GBRT, XGBoost and SVR are optimized by the particle swarm algorithm. The study can guide the analysis and prediction of aviation accidents and provide a scientific basis for aviation safety management.

Estimating accident-prone freeway sections: simulation and accident prediction model

Accident-prone sections are usually the most dangerous areas on a freeway. Identifying and studying them is therefore very important. In this study, accident-prone sections were estimated using a 77 km long freeway section in Zhejiang province, China as an example. Accident data and horizontal alignment data of the freeway were obtained. Two statistical methods – the improved cumulative frequency method considering equivalent accident numbers and the accident matrix method – were used to identify the accident-prone sections of the freeway. Additionally, a new method that combines vehicle dynamic simulation (using the CarSim software program) and speed consistency theory was developed and used to estimate the accident-prone sections of the freeway. To provide design advice, an accident prediction model was established by analysing the relationships between horizontal alignment geometric parameters and accident data. Shown to have a certain reliability, the proposed method can be used by designers to verify the safety condition of newly designed freeways and thus enhance freeway safety. The established model, which is logically reasonable and has a certain precision, could be a valuable reference for freeway designers.

A new fusion method to predict coal mine roof accidents

AbstractIn the context that coal remains the main energy source of China now, the safety of coal mine production is still worth our attention. For the factors influencing the roof accident of coal mine roadway have great complexity and uncertainty, a new risk prediction method of coal mine roof accidents integrating T‐S fuzzy fault tree and Bayesian network (BN) is proposed. The constructed method determines the BN and the conditional probability tables according to the established T‐S fuzzy fault tree. The fault state and fuzzy fault rate of root nodes are described according to the fuzzy number. And the forward inference of Bayesian is used to calculate the probability of the accidents on the roadway roof based on the fault probability of the root nodes and actual fault probability during construction respectively, to realize the risk prediction of roof accidents. Finally, practical data are used to verify the new fusion risk evaluation method by taking two mines as cases. The results show that the influencing factors calculated by the new fusion risk prediction method are completely consistent with the actual situation, confirming the effectiveness and reliability of this method, which providing new ideas for the research about the risk prediction of coal mine roof accidents.

Examining Car Accident Prediction Techniques and Road Traffic Congestion: A Comparative Analysis of Road Safety and Prevention of World Challenges in Low-Income and High-Income Countries

Road accidents are a significant negative outcome of transportation systems, causing injuries, fatalities, traffic congestion, and economic losses. As cities expand and the number of vehicles on the road increases, traffic accidents (TAs) have become a significant problem. Studies have shown that urban development plays a more significant role in transportation safety than previously thought. Low-income countries have higher fatality rates than high-income countries, according to the Permanent International Association of Road Congress (PIARC) and the World Health Organization (WHO). Predicting and preventing the occurrence of accidents and congestion is necessary worldwide, especially in developing countries where fatality rates are higher. The objective of this study is to examine and make a comparative analysis in low-income and high-income countries of the existing literature on the global challenge of car accidents and use its prediction techniques to enhance road safety and reduce traffic congestion. The study evaluates various approaches such as logistic regression, decision tree, random forest, deep neural network, support vector machine, random forest, K-nearest neighbors, Naïve Bayes, empirical Bayes, geospatial analysis methods, and UIMA, NSGA-II, and MOPS algorithms. The research identifies current challenges, prevention ideas, and future directions for preventing accidents and congestion on the road network. Integrating GIS-based spatial statistical methods and temporal data and utilizing advanced optimization algorithms and machine learning methods can result in accurate prediction models that can help identify accident hotspots and reduce congestions and enhance traffic safety and mitigate their occurrence. Effectively preventing urban traffic congestion requires the integration of spatial data into precise accident prediction models. By employing spatial analysis, road safety planning can be enhanced, high-risk areas can be identified, interventions can be evaluated, and resources can be optimally allocated to facilitate effective road safety measures and decision-making, especially in settings with limited resources. Therefore, it is crucial to consider ML and spatial analysis techniques and advanced optimization algorithms to enhance traffic flow control, in road safety research and transport planning efforts.

Design of Safety Tracking Device for Worker's Safety And Monitoring

Safety Tracking is the process of tracing a person’s ware bouts and their vitals and health in case of an emergency or accident. A device which sends or saves this data is considered as a safety tracking device. This device may help multiple sensors attached to the device itself or attached to the person there by reading and sending their ware boats and data within the parameter of the workspace in a company to a live supervisor or data storage so that it can be reviewed in case an accident occurs. This data can be used to study any accidents involving that person and device preventive measures of that accident again. The novel system can acquire the real-time working condition information of faculties such as pipe flow, pressure, temperature, humidity of the environment, current & voltage of the electrical equipment, valve switch, relay action, alarming message it can upload the collected data to the monitoring center to the client/server architecture. Based on these data, an electrical early warning model depending on the change in surroundings based on neural work is proposed. A personal safety evaluation model based on ontology with the usage of protege is established, which facilitate the on-line monitoring and control of building fire protection information, the prediction of accidents and improve building safety level evaluation.

Statical Analysis of Road Accident in Indapur City

Abstract: Accident analysis studies aim at the identification of high rate accident location, safety deficient areas and the accidents prone zones. For this purpose the road accident data for seven consecutive years, pertaining for a city has to be used. The road geometry will be measured in accident prone location to find out the cause of accident, based on these result, suggestion are to be provided to reduce the frequency of accidents at that particular place. Accidents prediction is done by regressing traffic volume with accident data to obtain an equation which could apprehend the forth coming accidents in the future. Preventive measures regarding the improvement of traffic condition for minimizing accidents rate are suggested

Comparison of random forest and support vector machine regression models for forecasting road accidents

One of the world’s concerns today is the rate of road traffic accidents (RTA). The overwhelming majority of these accidents occur in low and middle-income countries. RTA are one of the leading causes of death in Rwanda. RTA prediction is crucial for both transportation management and intelligent transportation systems (ITS) development. This paper adopted the use of two modelling techniques, Random forest (RF) and Support vector machine (SVM) for short-term road accident forecasting. The data used to evaluate the models was obtained from the Police. The lower error indices of MAE, MSE, RMSE and higher coefficient of determination (R2) were accuracy measures in comparing the models. The RF model performed better than the SVM model as it revealed higher R2=0.91 compared to the SVM model that was with R2=0.86. Machine learning methods are promising tools for the prediction of road accidents. Prediction positively influences safety enhancements and regulation formulation to prevent future accidents. The appropriate prediction method would help policymakers and healthcare providers adjust their contributions to the accident management process.

Prediction of Fatalities at Northern Indian Railways’ Road–Rail Level Crossings Using Machine Learning Algorithms

Highway railway level crossings, also widely recognized as HRLCs, present a significant threat to the safety of everyone who uses a roadway, including pedestrians who are attempting to cross an HRLC. More studies with new, proposed solutions are needed due to the global rise in HRLC accidents. Research is required to comprehend driver behaviours, user perceptions, and potential conflicts at level crossings, as well as for the accomplishment of preventative measures. The purpose of this study is to conduct an in-depth investigation of the HRLCs involved in accidents that are located in the northern zone of the Indian railway system. The accident information maintained by the distinct divisional and zonal offices in the northern railways of India is used for this study. The accident data revealed that at least 225 crossings experienced at least one incident between 2006 and 2021. In this study, the logistic regression and multilayer perception (MLP) methods are used to develop an accident prediction model, with the assistance of various factors from the incidents at HRLCs. Both the models were compared with each other, and it was discovered that MLP supplied the best results for accident predictions compared to the logistic regression method. According to the sensitivity analysis, the relative importance of train speed is the most important, and weekday traffic is the least important.

Characteristics analysis and situation prediction of production safety accidents in non-coal mining

Safety accident prediction is the prerequisite for accident prevention and the basis for safety management decision-making. To realize the accurate prediction of non-coal mine safety production situation, the evolution characteristics of non-coal mine safety production situation are analyzed from two perspectives of system characteristics and temporal characteristics, and the complexity of non-coal mine safety production system is elaborated from several perspectives, and its predictability is revealed. For the non-stationary non-coal mine safety production situation, CEEMDAN is used to progressively refine the non-coal mine safety production situation into several high-frequency trend components and low-frequency disturbance components by telescoping translation operations. Aiming at the correlation between the multi-modal components, the multi-modal components are reconstructed according to the distribution characteristics of the fuzzy entropy of the multi-modal components, and the detail, random, trend and residual components are obtained to characterize the composition of the non-coal mine safety production situation. Finally, by assuming the existence of unobservable hidden state sequences and their corresponding observable sequences, the relationship between the hidden states, and the observed states individually and between them is studied, and the HMM prediction model is constructed to achieve accurate prediction of the reconstructed multi-modal components. The results show that the accuracy evaluation indexes such as MAE, MSE and RMSE of the multimodal HMM prediction model for non-coal mine safety production situation prediction is better than those of the comparison model, and the prediction effect under different prediction steps is better than that of the comparison model, and the prediction accuracy is higher. The research is helpful for safety decision-makers to accurately grasp the changes in mine safety production and make correct safety decisions, which can provide theoretical guidance for the safety planning of non-coal mines.

Research on the prediction model of hazardous chemical road transportation accidents

In recent years, hazardous chemicals road transport accidents have occurred frequently, causing huge casualties and property losses, and accident risk assessment has become the focus of researchers' research. To predict the risk probability value of hazardous chemical road transport accidents, first, we compiled data on road transportation accidents of hazardous chemicals in China in the past five years. And the nine nodes in the Bayesian network (BN) structure were defined in combination with relevant classification standards. The optimal Bayesian network structure for hazardous chemical road transport accidents was determined based on the K2 algorithm and the causalities between the nodes. Second, the node conditional probabilities were derived by parameter learning of the model using Netica, and the validity of the model was verified using the 5-fold cross-validation method. Last, the Bayesian network model of hazardous chemical road transport accidents is used to analyze accident examples, and the accident chain of “rear-end-leakage” is predicted, and the accident is most likely to be disposed of within 3–9 h. The study shows that the derived accident prediction model for hazardous chemical road transportation can reason reasonably about the evolution of accident scenarios and determine the probability values of accident risks under different parameter conditions.

A Review of Road Traffic Accident Prediction Methods

With the continuous development of urban traffic and the acceleration of urbanization, traffic accidents have become an important issue for urban safety and social stability. In order to prevent and reduce the occurrence of traffic accidents, traffic accident prediction technology has gradually become a hot spot for research. This paper analyzes road traffic accident prediction techniques from articles included in relevant English journals and provides a detailed introduction to the road traffic accident prediction techniques that are already in existence. This paper introduces the current status of research on traffic accident prediction techniques, including traditional statistical analysis methods, machine learning methods, neural network methods, time series analysis methods and techniques based on spatio-temporal data mining, and analyses the advantages and disadvantages of each road traffic accident prediction method. These methods are able to analyse the influencing factors of traffic accidents, build prediction models, improve prediction accuracy and provide strong support for road traffic accident prevention effects for urban traffic safety. Finally, the main difficulties faced in road traffic accident prediction and the future development trend of road traffic accident prediction is discussed. The work done in this paper can provide necessary theoretical support for relevant researchers and save the time needed for literature review.

An Ultra-Low-Power-Consumption Urban Sewer Methane Concentration Monitoring System Based on Ultrasound

Methane is the main cause of sewer explosion accidents, and the available monitoring methods mainly use portable gas sensors for on-site detection. However, these methods cannot grasp the dynamic changes in methane in a sewer in real time or make good predictions of methane explosion accidents. Here, we present a low-power online monitoring system for sewer methane in order to ensure the safety of urban sewers. A low-power ultrasonic gas sensor was used to monitor the methane content in biogas. Due to the impacts of changes in CO2, temperature, and humidity in the sewer on the ultrasonic methane measurement results, a corresponding compensation method was proposed. The effectiveness of the compensation method was verified through experiments, which measured the methane concentration under different influences, and the methane values measured before and after compensation were compared. The power consumption was only 1.28 mW when the system worked in intermittent operation mode, and it could operate for about 1.5 years using a lithium battery with a capacity of 5 Ah. The experimental results showed that gas detection accuracy could meet commercial requirements and compensated for the impacts of carbon dioxide, temperature, and humidity.

Comparison of traffic accident injury severity prediction models with explainable machine learning

ABSTRACT Traffic accidents are still the main cause of fatalities, injuries and significant delays in highways. Understanding the accident contributing factor is imperative to increase safety in a traffic network. Recent research confirms that predictive modeling is an important tool to comprehend accident contributing factors. However, little effort has been put forward to explain complex machine learning models and their feature effects in accident prediction models. Thus, this study aims to build predictive models based on different machine learning methods and tries to explain the most contributing factors by using Shapley values which was developed based on game theory. Decision Trees, Neural Networks with Multilayer Perceptron (MLP), Support Vector Classifier, Case-Based Reasoning and Naive Bayes Classifier were used to predict the injury severity in accidents. Belt usage, alcohol consumption and speed violations were found as the most effective features and MLP gave the highest accuracy among all the applied predictive models.

Correction: Cho et al. A Proposed Waiting Time Algorithm for a Prediction and Prevention System of Traffic Accidents Using Smart Sensors. Electronics 2022, 11, 1765

The authors wish to make the following corrections to their paper [...]

Model Prediksi Kecelakaan Kendaraan Sepeda Motor pada Ruas Jalan di Kota Ambon

This study aims to model the prediction of motorcycle vehicle accidents in Ambon City. Factors reviewed in this study include socioeconomic and travel patterns, driving equipment and preparation, driving habits, and driving behavior. The survey was conducted using interview and questionnaire survey methods with a total of 250 respondents. The research method used is data analysis using Structural Equation Modeling (SEM). The results of motorcycle accident modeling show that the first biggest influence on the prediction of an accident is the driver's behavior characteristic variable, with the indicator that describes the cause of a traffic accident is the indicator of driving over the speed limit. Thus when a motorbike driver drives his vehicle fast and exceeds the speed limit, the higher the possibility that the driver will experience a traffic accident. So it is necessary to have cooperation between the police and related parties in dealing with accidents and reducing the risk of traffic accidents such as providing outreach or information, through newspaper or electronic media to the people in Ambon City regarding the dangers of driving over speed or speeding while driving on the road Ambon City.

Accident Severity Detection Using Machine Learning A Review

One of the greatest challenges in today's world is traffic accidents. It results in fatalities, accidents, and property damage. Making a model that can accurately predict traffic accidents is difficult. The objective of this project is to create a classification system for injuries based on a set of influential factors, including the environment, vehicle speed, driver behaviour, etc. Using data related to traffic accidents, several algorithms are utilized, including AdaBoost, Logistic Regression (LR), Naive Bayes (NB), and Random Forests (RF). Some of the best algorithms are the most effective, including Random Forest, Naive Bayes, and Ada Boost. Compared to LR, NB, and AdaBoost, the RF algorithm performed better, with 75.5% accuracy. To employ various machine learning classification algorithms for traffic accident prediction, the goal of this study is to uncover the underlying causes of road traffic accidents. then decide which prediction model is most likely to help decrease these highway accidents. This paper's goal is to review different authentication procedures offered by numerous scholars around the world.

Black Spot Identification and Road Accident Prediction Model on Cebu South Coastal Road (CSCR)

Millions of people die in road accidents yearly, causing significant damage to the economy and humanity. The main focus of the study is to analyze road accidents through Black Spot Identification and to establish a Prediction Model on the Cebu South Coastal Road (CSCR)-N840 Highway. The data gathered from government agencies were digitized using SPSS and MS Excel. The study revealed that the year 2018 has the highest number of accident cases with 555 (46.52%) and the lowest severity ratio of 0.41. In contrast, 2019 has the lowest frequency of accident cases with 159 (13.33%) and a severity ratio of 0.72. Through the APW system, the CSCR-N840 Highway’s top black spot locations were at 2.6 km, 1.2 km, 2.3 km, 0.9 km,2.2 km, 5.3 km, 4.6 km, 4.7 km, 3.7 km, 5.9 km, 7.6 km, 7.7 km, 8.2 km, 8.5 km, 6.5 km, 10.2km, 11.4 km, 9.4 km, 12.1 km, and 12.0 km. Also, the researchers presented a heat mapping through QGIS for visual analysis, where severe road traffic accidents usually occur on the Talisay side of CSCR N840 Highway due to 13 junctions, 7 intersections, and 6 curvatures. Lastly, in the developed regression model the accident rate decreases gradually with an increase in the traffic volume. Also, Poisson prediction model, as the accident probability increases, the accident rate may either increase or slowly decrease.

Attention-Based Residual Dilated Network for Traffic Accident Prediction

Traffic accidents directly influence public safety and economic development; thus, the prevention of traffic accidents is of great importance in urban transportation. The accurate prediction of traffic accidents can assist traffic departments to better control and prevent accidents. Thus, this paper proposes a deep learning method named attention-based residual dilated network (ARDN), to extract essential information from multi-source datasets and enhance accident prediction accuracy. The method utilizes bidirectional long short-term memory to model sequential information and incorporates an attention mechanism to recalibrate weights. Furthermore, a dilated residual layer is adopted to capture long term information effectively. Feature encoding is also employed to incorporate natural language descriptions and point-of-interest data. Experimental evaluations of datasets collected from Austin and Houston demonstrate that ARDN outperforms a range of machine learning methods, such as logistic regression, gradient boosting, Xgboost, and deep learning methods. The ablation experiments further confirm the indispensability of each component in the proposed method.

Prediction of severity of aviation landing accidents using support vector machine models

The purpose of this study was to apply support vector machine (SVM) models to predict the severity of aircraft damage and the severity of personal injury during an aircraft approach and landing accident and to evaluate and rank the importance of 14 accident factors across 39 sub-categorical factors. Three new factors were introduced using the theory of inattentional blindness: The presence of visual area surface penetrations for a runway, the Federal Aviation Administration’s (FAA) visual area surface penetration policy timeframe, and the type of runway approach lighting. The study comprised 1,297 aircraft approach and landing accidents at airports within the United States with at least one instrument approach procedure. Support vector machine models were developed in using the linear, polynomial, radial basis function (RBF), and sigmoid kernels for the severity of aircraft damage and additional SVM models were developed for the severity of personal injury.The SVM models using the RBF kernel produced the best machine learning models with a 96% accuracy for predicting the severity of aircraft damage (0.94 precision, 0.95 recall, and 0.95 F1-score) and a 98% accuracy for predicting the severity of personal injury (0.99 precision, 0.98 recall, and 0.99 F1-score). The top predictors across both models were the pilot’s total flight hours, time of the accident, pilot’s age, crosswind component, landing runway number, single-engine land certificate, and any obstacle penetration. This study demonstrates the benefit of SVM modeling using the RBF kernel for accident prediction and for datasets with categorical factors.