Types Of Accidents Research Articles

An open paradigm dataset for intelligent monitoring of underground drilling operations in coal mines

The underground drilling environment in coal mines is critical and prone to accidents, with common accident types including rib spalling, roof falling, and others. High-quality datasets are essential for developing and validating artificial intelligence (AI) algorithms in coal mine safety monitoring and automation field. Currently, there is no comprehensive benchmark dataset for coal mine industrial scenarios, limiting the research progress of AI algorithms in this industry. For the first time, this study constructed a benchmark dataset (DsDPM 66) specifically for underground coal mine drilling operations, containing 105,096 images obtained from surveillance videos of multiple drilling operation scenes. The dataset has been manually annotated to support computer vision tasks such as object detection and pose estimation. In addition, this study conducted extensive benchmarking experiments on this dataset, applying various advanced AI algorithms including but not limited to YOLOv8 and DETR. The results indicate the proposed dataset highlights areas for improvement in algorithmic models and fills the data gap in the coal mining, providing valuable resources for developing coal mine safety monitoring.

Machine Learning Predictive Models for Survival in Patients with Brain Stroke

Background: This study aims to harness the predictive power of machine learning (ML) algorithms for accurately predicting mortality and survival outcomes in brain stroke (BS) patients. Methods: A total of 332 patients diagnosed with BS were enrolled in the study between April 21, 2006, and December 22, 2007, and then followed for 15 years (until 2023). Mortality outcomes were modeled using various statistical techniques, including the Cox model, decision trees, random survival forests (RSF), support vector machines (SVM), gradient boosting, and mboost. The best-performing model was selected based on diagnostic performance metrics: specificity, sensitivity, precision, accuracy, area under the receiver operating characteristic curve (AUC), positive likelihood ratio, negative likelihood ratio, and negative predictive value. Results: The results indicate that ML models in small sample sizes, particularly the SVM, outperformed the Cox model in predicting mortality and survival over 15 years, achieving an accuracy of 85% and an AUC of 0.765 (95% CI 0.637-0.83). Furthermore, the study identified important variables, including blood pressure history, waterpipe smoking, lack of physical activity, type of cerebrovascular accident, current smoking status, sex, and age, which provide valuable insights for clinicians in risk assessment. Conclusion: Our study showed that the SVM model outperforms the Cox model in predicting 15-year mortality and survival, particularly in small sample sizes. Moreover, the identification of key risk factors such as blood pressure history, waterpipe smoking, lack of physical activity, type of cerebrovascular accident, current smoking status, sex, and age highlights the need for their consideration in clinical assessments to enhance patient care.

Characteristics of Injuries in Road Traffic Accident Victims: An Autopsy Study at Srinagarind Hospital, Khon Kaen University, Thailand

Objective: This ambidirectional cohort study aimed to investigate injury characteristics in road traffic accident (RTA) victims based on autopsy cases at the Department of Forensic Medicine, Srinagarind Hospital, Faculty of Medicine, Khon Kaen University, Thailand. Material and Methods: Autopsy cases from September 2022 to August 2024 were reviewed, with data collected from autopsy reports and crime scene photographs. Injury characteristics, types of RTAs, time of accidents, and victim demographics were analyzed in 57 RTA cases. Results: The results revealed noteworthy differences in injury patterns between types of RTAs. Fractures at the skull base (Car 38%, Motorcycle 75%, Pedestrian 28%; p < 0.01), heart lacerations (Car 46%, Motorcycle 10%, Pedestrian 28%; p < 0.05), and fractures of the right radius (Car 7.7%, Motorcycle 2.7%, Pedestrian 28%; p < 0.05), right ulna (Car 7.7%, Motorcycle 2.7%, Pedestrian 28%; p < 0.05), left tibia (Car 23%, Motorcycle 8%, Pedestrian 71%; p = 0.001), and left fibula (Car 23%, Motorcycle 8%, Pedestrian 71%; p < 0.05) were associated with specific accident types. Conclusion: This study highlights the observed differences in injury characteristics across various types of RTAs at Srinagarind Hospital, Faculty of Medicine, Khon Kaen University, Thailand. Key injuries, including fractures atthe base of the skull, heart lacerations, and fractures of the right radius, right ulna, left tibia, and left fibula, were significantly associated with particular types of accidents. These results can serve as a guide for determining the causes of death, especially in RTA cases, particularly in areas lacking forensic pathologists.

Human-animal interactions, occupational health and well-being in pig slaughterhouses of Colombia: Exploring worker perceptions and practices.

Human-animal interactions, occupational health and well-being in pig slaughterhouses of Colombia: Exploring worker perceptions and practices.

Transient local effects analysis during typical accidents of a heat pipe cooled reactor

Transient local effects analysis during typical accidents of a heat pipe cooled reactor

Analisis Titik Lokasi Kecelakaan di Ruas Jalan Tol Palimanan – Kanci

Traffic accidents on toll roads, including the Palimanan – Kanci (Palikanci) Toll Road, are a major concern due to high vehicle volume and other factors such as driver fatigue, weather conditions, and compliance with traffic regulations. This study aims to identify accident-prone locations and formulate mitigation measures. The research employs a quantitative analysis method using both primary and secondary data. Based on accident location identification for the Palimanan – Kanci Toll Road from 2022 to 2024, using the Equivalent Accident Number (EAN) and Upper Control Limit (UCL) methods per 1 km, 11 accident-prone locations were identified. However, two locations had the highest accident rates: Lane A at KM 210 – 211 and Lane B at KM 195 – 196. The most common cause of accidents was driver inattention and drowsiness, with the predominant accident type being rear-end collisions. The result of this study can serve as a reference for mitigation efforts to reduce accidents on the Palimanan – Kanci Toll Road.

Evaluation of the Cases of Mortality Related with Electric Current

Objective: Electric shock is defined as occurence of injury or fatality following contact with electric welding. Methods: In our study, the forensic files of 209 subjects for whom a causal link was found between electric current and mortality between 2010 and 2014 were examined retrospectively. Results: The subjects were evaluated in terms of demographic properties, the origin of the event, distributions by months, locations of the event, autopsy findings, presence of hospitalization, type of accident, if crime scene investigation was performed or not and if investigation was performed about suspicious devices in the scene of crime by a technical legal expert. Conclusion: Investigation of the cause of death is initiated in the crime scene in all forensic cases of mortality. In cases of mortality related with electric current, the cause and origin of death can be explained by way of a detailed crime scene investigation when macroscopic and microscopic findings are absent.

A RESPONSABILIDADE CIVIL DO EMPREGADOR POR DANOS MORAIS DECORRENTE DE ACIDENTE DE TRABALHO: UMA ANÁLISE DA JURISPRUDÊNCIA DO TRT-RN

This article aims to analyze the employer’s civil liability for moral damages arising from work-related accidents, with an emphasis on the decisions of the Regional Labor Court of the 21st Region (TRT-RN). The research adopts a qualitative approach, based on bibliographic review and jurisprudential analysis, focusing on two leading decisions — one from each Chamber of TRT-RN — concerning typical accidents and occupational diseases. The study discusses the distinction between subjective and objective liability in Brazilian law, highlighting the application of the social risk theory in specific contexts. The analysis revealed that TRT-RN tends to adopt a cautious stance, requiring robust evidence of causation to justify compensation. It is concluded that the employer’s liability for moral damages in the workplace mostly depends on the proof of fault or the existence of a risky activity that justifies the application of strict liability.

Medicolegal Evaluation of Non-Fatal Occupational Accidents (Şanlıurfa-Turkey)

Abstract Background/Aims: This study aims to describe injuries resulting from occupational accidents treated at a university hospital in Şanlıurfa, Turkey. The study provides information on age, gender, date of occupational accident, occupational accident sector, type of occupational accident, location of the wound, presence of brain/visceral lesion, type of wound, and discharge status. Methods: In the study, hospital records for the 10-year period between 2014-2023 were retrospectively examined to determine occupational accident cases. Patient data were obtained from the hospital information management system. Occupational accident sectors were classified and injury locations were categorized. Results: A total of 127 occupational accident cases were identified, with 92.9% being male and 7.1% female. The mean age was 35.3 ±11.03 years. The construction sector (32.3%) was found to have the highest case rate. The most common injury types were cuts/crushing/cutting/penetration wounds (36.2%), fractures (27.8%), and blunt traumatic injuries (26.0%). Upper extremity trauma was the most frequent injury location (40.94%), followed by head trauma (14.96%) and lower extremity trauma (10.24%). Brain/internal organ lesions were present in 7 cases. Conclusion: Our study emphasizes the importance of understanding injury patterns to improve workplace safety. In our study it is thought that work safety measures should be changed especially in the construction sector and protective measures for upper extremity injuries should be increased. Considering the regional and provincial differences in occupational accidents in our country, there is a need for multi-centered and larger dataset studies that include detailed statistical data on occupational accidents, sectors, and types of injuries.

Unveiling construction accident causation: a scientometric analysis and qualitative review of research trends

The construction industry, a cornerstone of global economic growth, faces frequent safety accidents due to its complex environments and multi-party collaboration, impeding sustainable development. These incidents arise from interlinked causal factors, including human error, management shortcomings, technical failures, and environmental conditions. This study systematically reviews construction accident causation research by integrating scientometric analysis and qualitative methods, using VOSviewer to analyze literature from Scopus and Web of Science databases, with 110 peer-reviewed articles selected through a validated Boolean search strategy. VOSviewer was used for bibliometric visualization to map research trends, co-authorship networks, and keyword co-occurrences. In addition, a qualitative synthesis was conducted to review common data sources and examine key issues, including risk factor identification, accident type classification, causality analysis, and the optimization of research strategies. The study aims to systematically review the current state of construction accident causation research, highlighting key trends in data-driven and AI-based safety interventions. Findings reveal a shift toward data-driven, intelligent approaches, with artificial intelligence techniques—such as large models (capable of understanding complex patterns from massive datasets), graph neural networks (suitable for modeling relationships between contributing factors), and natural language processing (for extracting insights from textual accident reports)—enhancing accident prevention and risk prediction. Challenges persist, however, in data quality, causal exploration depth, and interdisciplinary integration. These findings underscore the need for further advancements in data accuracy and model scalability, which could inform more effective safety management practices and policy frameworks. Key contributions include filling the bibliometric gap in this field, offering a novel framework combining quantitative and qualitative insights, and highlighting advanced technology applications, thus providing theoretical and practical guidance for future safety management. Future research is recommended to leverage AI, foster interdisciplinary collaboration, and develop precise prevention systems to address these gaps.

Survey-Based Analysis of High-Risk Accident Types and Smart Safety Technology Adoption Preferences in Construction Sites

Survey-Based Analysis of High-Risk Accident Types and Smart Safety Technology Adoption Preferences in Construction Sites

Unveiling key aspects of safety management in mega construction projects: a perspective on different levels and types of accidents

PurposeThe purpose of this study is to explore the key risk factors and accident formation mechanisms for different levels and types accidents (DLTAs) in mega construction projects (MCPs). Furthermore, by pinpointing key risk factors and causal chains of DLTAs, the research outcomes provide theoretical foundations for accident prevention and prediction.Design/methodology/approachThis study extracts text semantic features by coupling Word2Vec, latent Dirichlet allocation (LDA) topic model and the Bayesian network model to delve into the intricate couplings among risk factors of DLTAs. First, based on the Word2Vec, LDA topic model to identify safety risk factors. Second, association rule mining is employed to uncover the relationships among the DLTAs risk factors. Finally, the Bayesian network is constructed, leveraging the results from text mining and association rule mining, to delve into the key risk factors and the underlying mechanisms of DLTAs formation.Findings(1) 28 secondary risk factors, 48 rules associating risk factors with accident levels and 41 rules associating risk factors with accident types were identified. (2) The more severe the accident level, the more risk factors are involved, and timely measures should be taken to prevent the interaction of multiple risk factors. The key causal chains differ among different types of accidents, thus prevention and control measures, as well as emergency response plans, should be formulated specifically for each type of accident. (3) The key risk factors for MCPs include: Low safety awareness, Wildcat operation, Improper safety protection, Improper maintenance of equipment, Linkage fault safety device failure, Poor geological conditions, Poor ventilation conditions, Improper on-site risk identification, Improper management of safety hazards, Improper safety inspection, Improper safety education and training, Safety responsibility is not implemented, Improper special construction scheme.Practical implicationsMCPs are characterized by high complexity, and their construction sites are fraught with numerous risk factors, potentially leading to DLTAs. These accidents, differing in their characteristics, pose significant challenges to the safety management and control of MCPs. Notably, there is a conspicuous lack of focus on the specific characteristics of DLTAs, which represents a significant gap in the field.Originality/valueThe contributions of this study are threefold. First, this study focuses on DLTAs, which are an important perspective on safety management. Second, based on text mining and association rule mining to build a Bayesian network, providing guidance for risk coupling mining. Third, understanding the characteristics of DLTAs plays a crucial role in pre-accident prevention, in-accident rescue and post-accident disposal.

Assessment of the Potential of a Front Brake Light to Prevent Crashes and Mitigate the Consequences of Crashes at Junctions

Safe vehicles are an important pillar in reducing the number of accidents or mitigating the consequences of a collision. Although the number of autonomous safety systems in vehicles is increasing, retrofitted systems could also help reduce road accidents. A new retrofit assistance system called Front Brake Light (FBL) helps the driver to assess the intentions of other road users. This system is mounted at the front of the vehicle and works similarly to the rear brake lights. The objective of this study is to evaluate the safety performance of an FBL in real accidents at junctions. Depending on the type of accident, between 7.5% and 17.0% of the accidents analysed can be prevented. A further 9.0% to 25.5% could be positively influenced by the FBL; i.e., the collision speed could be reduced. If the FBLs were visible to the driver of the priority vehicle, the number of potentially avoidable accidents would increase to a magnitude of 11.5% to 26.2%. The range of accidents in which the consequences can be reduced increases to between 13.8% and 39.2%.

ENSEMBLE DEEP LEARNING FRAMEWORK FOR TRAFFIC ACCIDENT DETECTION IN SMART CITIES

Effective accident detection techniques are essential for improving safety and expediting traffic management in smart cities due to the dynamic and unpredictable nature of road traffic. In addition to providing a thorough overview of various traffic accident types, such as rear-end collisions, T-bone collisions, and frontal impact accidents, this paper provides an in-depth investigation study of popular accident detection techniques, illuminating the subtleties of other cutting-edge approaches. By combining RGB frames with optical flow data, our innovative method presents the I3D-CONVLSTM2D model architecture, a lightweight solution specifically designed for accident detection in smart city traffic surveillance systems. Our experimental study's empirical analysis highlights how effective our model design is. With a remarkable Mean Average Precision (MAP) of 87%, the I3D-CONVLSTM2D RGB + Optical-Flow (trainable) model performed better than its competitors. Our results provide more insight into the difficulties caused by data imbalances, especially when dealing with a small number of datasets, road configurations, and traffic situations. In the end, our study shows the way to an advanced vision-based accident detection system that is ready for immediate incorporation into edge IoT sensors in smart city infrastructures.

Preliminary analysis of typical accidents of CFETR helium-cooled solid breeder blanket system based on COSINE

Abstract Blankets are an important component of fusion reactors and the key object of thermal design and safety analysis. The helium-cooled solid breeder (HCSB) blanket is one of the three candidate tritium breeding blanket concepts for the Chinese Fusion Engineering Test Reactor (CFETR). Fusion reactors’ thermal design and safety analysis are mostly based on fission reactor procedures worldwide. In this paper, based on the system safety analysis module cosSyst in the COSINE code package of China’s independently developed system safety analysis code for pressurized water reactors, functional development was carried out for the helium-cooled blanket of fusion reactor, and helium physical property envelope and corresponding heat transfer model were added. The modified code was used to analyze three typical accidents with the blanket and the combined helium cooling system (HCS): In-Vessel LOCA, In-Box LOCA, and Ex-Vessel LOCA. The research findings indicate that under the three accident scenarios, the first wall and the cooling loop system maintained their structural integrity, with no melting or exceeding pressure limits.

Factors associated with land transport accidents in the State of Espírito Santo

Objective: Verify the factors associated with the land transport accidents victims assisted by the Mobile Urgency Care Service in the state of Espírito Santo. Methods: Cross-sectional study with retrospective data collection from a sample of 2,502 pre-hospital printed care reports from Mobile Urgency Care Service in 2015, of these, 438 were victims of land transport accidents. Information was collected regarding: sex, age, life cycle, ethyl breath, vehicle involved, severity of trauma and outcome of the occurrence. Severity was established using the Revised Trauma Scale. Chi-square test was performed. Results: Land transport accidents represented 50.2% of the external causes victims assisted. Most of the victims were male (73.7%), adults (81.9%), had no ethyl breath (88.8%) and victims of minor trauma (95.3%). The Motorcycle was the vehicle most frequently involved (56.1%). It was found as factors associated (p <0.05) with the type of land transport accident: life cycle (adult and collision; elderly and run overs), vehicle (automobile - run over and collision; motorcycle and bicycle - falling) and severity of trauma (major and run over; minor and fall). Conclusion: The data reveals the main factors associated with land transport accidents, guiding the pre-hospital care to these occurrences. It is necessary to intensify specific educational measures for each risk group.

Text mining and association rules-based analysis of 245 cement production accidents in a cement manufacturing plant

Accidents such as collapses, fires, explosions and mechanical injuries occur frequently in cement manufacturing plants. Understanding the causes of past accidents is essential to prevent future incidents and reduce safety risks. Hence, this article analyzes cement accident cases based on a unified report analysis framework. By integrating text mining technology, the article identifies patterns in cement production accidents and establishes a cement accident causation analysis model to support safety management decisions. First, 245 accident records were categorized using the latent Dirichlet allocation model to identify causal factors. Subsequently, a systematic accident causal analysis based on the 24Model was proposed to establish a unified report framework. An improved Apriori algorithm was then developed for multidimensional, multilayer correlation rule mining in cement enterprises, enhancing text mining efficiency. By applying this algorithm, the study quantitatively analyzed correlations between accident types, causative factors and their interactions. Finally, targeted safety management recommendations were formulated.

The Full Lifecycle Evolution Model of Accidents: A Case Study of Underground Metal Mines in China

Analyzing the mechanisms of accidents is essential for clarifying the accident evolution process, devising preventive measures, and achieving proactive accident management. To address the potential issues in existing accident causation theories, such as the unclear distinction between direct causes and incomplete accident evolution pathways in enterprise-level accident prevention analysis, this study systematically reviewed the elements involved in safety management activities and their interrelationships. We identified the central role of human factors in the accident evolution process and developed a full lifecycle evolution model for industrial accidents, which begins with hazard identification and follows a safety management logic as its primary framework. This model provides a clear pathway for constructing enterprise-level risk control lists and accident prevention schemes. The model’s effectiveness was validated through its application to China’s underground metal mining industry. Drawing on Chinese laws and regulations as well as accident investigation reports, this study identifies 11 common types of accidents in underground metal mines and maps their evolution pathways from a complex systems perspective. Quantitative data from 61 accident reports were used to pinpoint the core factors and critical pathways leading to these various accidents. The study also analyzes prevention strategies and proposes new countermeasures to control the propagation of accident risks. Practical applications of the model demonstrate that emphasizing human factors enhances the effectiveness and accuracy of enterprise-level accident analysis and risk management.

A review of machine learning for analysing accident reports in the construction industry

Recently, there has been a growth in the research interest on applied machine learning (ML) in safety analysis in the construction industry. The increased interest is part of a search for improved prevention of occupational accidents with a focus on text analysis and natural language processing (NLP). However, ML-based approaches have been less adapted compared to their perceived benefits due to barriers of implementation and challenges in analysing safety records in the construction sector. And the current literature has been criticized for a lack of clarity around the description of methodologies, interpretation, and the context of the application. Therefore, this work aims to review the latest developments in research applying ML to accident report analysis in construction. A review of the published literature on ML-based analysis of construction accident reports was carried out and organized in terms of the data pre-processing, algorithms, testing and implementation and further organized based on data structure. The results of the review found limitation related to data availability besides the manual structuring and the less use of unsupervised learning reflect complexity of handling textual accident data. Moreover, types of accidents happen in proportionally varying frequencies and need careful tackling outside basic assumptions of data pre-processing in addition to the general need for data pre-processing comparative studies and automated pipelines. The review also showed that data mining (DM) and unsupervised learning were less used especially with semi-structured and unstructured datasets reflecting maybe inefficient natural language processing (NLP) application with these types of learning. Among the reviewed articles, only four out of six prototypes were externally validated on construction environment thus we propose that future efforts would benefit from incorporating a standardized development method that also explicit how ML safety recommendation informs decision making. Future research should experiment and ascertain different choices in the pre-processing stage, validating the performance of the ML models and implementation in the construction practices. Finally, there are more advanced NLP methods that could be applied if domain specific repositories were available such as relation extraction and there are various advances that could be explored including large language models (LLMs).

Age-related differences in the effect of mental fatigue on obstacle crossing in virtual reality

In Japan, falls are the most common type of occupational accident, with inattention being one of its primary causes. Both mental fatigue and aging contribute to inattention and decline in physical performance; however, how these factors interact to affect physical performance is not fully understood. This study compared the effects of mental fatigue on physical movements between younger (aged 25–34 years) and middle-aged adults (aged 55–64 years) and examined age-specific fall risks. A total of 34 participants rated their fatigue using the visual analog scale, performed the psychomotor vigilance task as a measure of sustained attention, and completed an obstacle-crossing task in a virtual reality environment to measure toe clearance and swing time. Results showed that mental fatigue increased fall risk across all ages, with age-specific contributing factors. For middle-aged adults, reduced balance control and lower sensitivity to fatigue heightened fall risk. Meanwhile, in younger adults, mental fatigue combined with energy-efficient strategies raised fall risk. These findings highlight unique age-related risk factors exacerbated by mental fatigue, underscoring the importance of early guidance and education before middle age.