Construction Accidents Research Articles

Authentication control system for the efficient detection of hard-hats using deep learning algorithms

Hard-hats are the most essential safety gear on construction sites. Accidents happen due to the ignorance to wear a hard hat properly. To prevent construction accidents due to the non-usage of hard hats, automatic non-hardhat usage detection techniques have been observed to be more efficient. This paper analyses the usage of deep learning algorithms in detecting construction workers who fail to wear their hard hats properly. The accuracy of the 3 deep learning algorithms, i.e. YOLO v4, v5 and YOLACT++ have been tested using a set of data of Hard-hats collected from the crowdsourcing and web mining. These vision-based deep learning methods and algorithms have been applied and compared in terms of accuracy, scalability, and robustness. The research evaluated the different frames of construction site workers and classified image frames into different categories. The frames were input into the deep learning algorithm as per their visual categories. The objective of the paper is to analyze the present deep learning approaches for the real-time detection of the hardhat on the construction site in a way that the hardhat could be recognized efficiently without any failure and would be able to distinguish the workers who are not wearing their Hard-hats suitably and introduce a new access control system using deep learning methods to solve the problem of efficiently identifying Hard-hats for site workers. The experimental results demonstrate that the high score of precision, recall, and fast speed of the techniques, which would effectively detect non-usage of Hard-hats by site workers at different construction site conditions. This will help improve safety and supervision on construction sites.

Applying decision tree algorithm to explore occupational injuries in the Turkish construction industry

Occupational injuries and fatalities are one of the most significant issues in the construction industry. Variables, such as workers’ behavior, age, worksite condition, and type of activity, play key roles in the occurrence of construction accidents. In recent years, data mining techniques have been successfully used not only in health, economy, and social sciences but also in construction-related fields. In this study, C5.0 decision tree algorithm was used to analyze the accident data obtained from the Social Security Institution of Turkey. A classification tree model was created to discover the associations between the attributes. The results show the relationship between the injury status of workers and the attributes, and the accuracy rate of the model was 70.26%. Meanwhile, according to findings, unsafe conditions, type of accident, and activity type were the most important attributes in the model. Furthermore, the predictor importance of the attributes was compared, and several outcomes were discovered; for instance, the workers’ educational background has greater predictive power than age. On the other hand, the branches of the decision tree pointed out several attribute sequences due to their high rated serious/fatal injury rates. The results of this study can be used in the prevention and mitigation strategies for construction accidents.

Construction Safety during Pandemics: Learning from the Xinjia Express Hotel Collapse during COVID-19 in China.

Many construction accidents occur in China each year, leading to a large number of deaths, injures, and property losses. Due to the outbreak of COVID-19, little attention is paid to construction safety, resulting in severe accidents. To prevent construction accidents and learn to how address safety issues in future pandemics, this study proposed an improved STAMP (Systems Theoretic Accident Modeling and Processes) model to analyze the collapse accident of the Xinjia Express Hotel used for COVID-19 quarantine in China. Through the application of the STAMP approach, the causes of the construction accident and the relationship between various causal factors are analyzed from a systematic perspective. The identified causes are divided into five categories: contractors, management of organizations, technical methods, participants, and interactive feedback. Finally, safety recommendations are drawn from this study to improve construction safety and safety management in pandemics.

Recent Party Wall Disputes

For centuries, party walls have been a common construction practice in many countries. In New York City (NYC), they have been used since the 1700s. The city accounts for about 201,000 attached buildings. The historic NYC speculative construction practice relied heavily on attached row houses built by the same developer; agreements were rarely drafted and the number of party walls or remnants thereof is not certain. This paper examines the issues related to new construction involving existing party walls. Insufficient prior investigations led to redesigns, accidents, or delays. Out of concerns of pounding during earthquakes, recent building codes require structures be separated by a gap, involuntarily complicating even alterations along party walls. The longest delays, though, are caused by adjoining owners opposed to the development or intent to maximize financial gains through litigation. They resist inspections or any physical attachment to walls, even necessary repairs. The study juxtaposes 15 years of building violations, incidents, construction regulations, and legal decisions. It tracks construction accidents that led to building regulations increasingly progressing from empirical to engineered construction safety inspections. In turn, these prompted a 10-fold increase in court petitions based on statutes, but only minor changes in common law. Concerns are raised that some litigations may set aside safety and structural stability issues. Analysis of typical party wall scenarios concludes that in almost all cases development requires licenses to inspect and repair. In their absence, architectural and structural solutions need to account for risks posed by legal uncertainties.

Structural Model of Internal Factors Influencing the Safety Behavior of Construction Workers

AbstractThe immediate cause of construction accidents is attributed to human error. However, few studies have investigated the relationship between individual internal factors and unsafe behaviors ...

UNDERSTANDING CONSTRUCTION SITE SAFETY HAZARDS THROUGH OPEN DATA: TEXT MINING APPROACH

Construction is an industry well known for its very high rate of injuries and accidents around the world. Even though many researchers are engaged in analysing the risks of this industry using various techniques, construction accidents still require much attention in safety science. According to existing literature, it has been found that hazards related to workers, technology, natural factors, surrounding activities and organisational factors are primary causes of accidents. Yet, there has been limited research aimed to ascertain the extent of these hazards based on the actual reported accidents. Therefore, the study presented in this paper was conducted with the purpose of devising an approach to extract sources of hazards from publicly available injury reports by using Text Mining (TM) and Natural Language Processing (NLP) techniques. This paper presents a methodology to develop a rule-based extraction tool by providing full details of lexicon building, devising extraction rules and the iterative process of testing and validation. In addition, the developed rule-based classifier was compared with, and found to outperform, the existing statistical classifiers such as Support Vector Machine (SVM), Kernel SVM, K-nearest neighbours, Naïve Bayesian classifier and Random Forest classifier. The finding using the developed tool identified the worker factor as the highest contributor to construction site accidents followed by technological factor, surrounding activities, organisational factor, and natural factor (1%). The developed tool could be used to quickly extract the sources of hazards by converting largely available unstructured digital accident data to structured attributes allowing better data-driven safety management.

Analysis of Fire Accident Factors on Construction Sites Using Web Crawling and Deep Learning Approach

Fire safety on construction sites has been rarely studied because fire accidents have a lower occurrence compared to construction’s “Fatal Four”. Despite the lower occurrence, construction fire accidents tend to have a larger severity of impact. This study aims at using news media data and big data analysis techniques to identify patterns and factors related to fire accidents on construction sites. News reports on various construction accidents covered by news media were first collected through web crawling. Then, the authors identified the level of media exposure for various keywords related to construction accidents and analyzed the similarities between them. The results show that the level of media exposure for fire accidents on construction sites is much higher than for fall accidents, which suggests that fire accidents may have a greater impact on the surroundings than other accidents. It was found that the main causes of fire accidents on construction sites are violations of fire safety regulations and the absence of inspections, which could be sufficiently prevented. This study contributes to the body of knowledge by exploring factors related to fire safety on construction sites and their interrelationships as well as providing evidence that the fire type should be emphasized in safety-related regulations and codes on construction sites.

Ensuring the safety of construction facilities: economic, environmental and managerial components

The article considers the directions of ensuring the safety of construction objects in the economic, ecological and managerial context. The authors noted that the lack of safety during construction work is a serious problem in this industry. The implementation of the safety program has always been one of the most successful measures to reduce the number of accidents in construction. However, it should be borne in mind that ensuring safety in construction should be based both on competent management of the construction project implementation and on the corresponding economic component, since labor protection management will be effective only if its system is based on coordinated actions of specialists in this field and is supported by appropriate financial costs aimed at financing measures to reduce the impact of negative factors affecting the process of ensuring labor safety on the construction site.

Актуальные вопросы техносферной безопасности в процессе использования строительной техники

Objective: Study of the technosphere safety issues relating to the use of construction equipment. Analysis of regulatory framework in this field. Methods: Study of the main causes of accidents in construction has been carried out. Results: Ways to minimize risks and examples of accidents that threaten the technosphere safety when using construction equipment are given. Practical im-portance: It has been established that it is necessary to reduce the risk of accidents due to human error. This can be done in a variety of ways. For example, in order to avoid accumulated fatigue, one should provide a rational work and rest pattern, carry out professional selection when hiring, conduct tests, in particular for reality awareness, for personal qualities (level of responsibility, punc-tuality, etc.), and conduct professional retraining or qualification upgrade. Regular employee health checks are necessary. It is important to learn how to predict the possible consequences to pro-vide security of the decisions made.

Applications of Computer Vision in Monitoring the Unsafe Behavior of Construction Workers: Current Status and Challenges

The unsafe behavior of construction workers is one of the main causes of safety accidents at construction sites. To reduce the incidence of construction accidents and improve the safety performance of construction projects, there is a need to identify risky factors by monitoring the behavior of construction workers. Computer vision (CV) technology, which is a powerful and automated tool used for extracting images and video information from construction sites, has been recognized and adopted as an effective construction site monitoring technology for the identification of risky factors resulting from the unsafe behavior of construction workers. In this article, we introduce the research background of this field and conduct a systematic statistical analysis of the relevant literature in this field through the bibliometric analysis method. Thereafter, we adopt a content-based analysis method to depict the historical explorations in the field. On this basis, the limitations and challenges in this field are identified, and future research directions are proposed. It is found that CV technology can effectively monitor the unsafe behaviors of construction workers. The research findings can enhance people’s understanding of construction safety management.

Occupational accident analysis according to professionals of different construction phases using association rules

Despite continuous efforts to improve safety, worker safety awareness on construction sites is a major concern as it remains one of the most dangerous industries. The large number of factors involved in accidents and the complexity of the relationships between them make management difficult for managers. Therefore, potential hazards cannot be identified in order to develop effective safety procedures. This study addresses this problem by using the association rule method of data mining to extract knowledge from historical data of construction accidents. It can help managers to identify and provide frequent conditions that can be prevented in future by controlling risks on site. Occupational accidents that have been notified through an official electronic system on Spanish construction sites between 2003 and 2015 are analysed. Data have been divided according to professionals to explore the accidents in each construction phase. The results show patterns and recurrent factors with multiple relationships in all phases of the construction works. This is the case for the outsourcing variable which is a critical factor in occupational accidents in all construction phases. Similarly, the results have also shown that risk assessment is not an insurmountable barrier to accidents. Consideration of the different stages of the work provides flexibility in order to improve risk reduction and control actions. The results of the study provide a framework for improving safety practices, providing a valuable reference for all agents involved in the construction industry to improve risk management, preventive measures and action plans.

A Research Framework of Mitigating Construction Accidents in High-Rise Building Projects via Integrating Building Information Modeling with Emerging Digital Technologies

The construction of high-rise building projects is a dangerous vocation due to the uniqueness and nature of the activities, as well as the complexity of the working environment, yet safety issues remain crucial in the construction industry. Digital technologies, such as building information modeling (BIM), have been identified as valuable tools for increasing construction productivity, efficiency, and safety. This research aimed to mitigate the accident safety factors in high-rise building projects via integrating BIM with emerging digital technologies in the construction industry, such as photogrammetry, GPS, RFID, augmented reality, (AR), virtual reality (VR), and drone technology. Qualitative research was conceived in the ground theory approach. Forty-five online interviews with construction stakeholders and qualitative data analysis were carried out using the NVivo 11 software package. According to the findings, interviewees were more motivated to use photogrammetry and drone technologies in high-rise building projects in order to increase construction safety. Positive, negative, and neutral attitudes about BIM integration with emerging digital technologies were discovered. Furthermore, a research framework was developed by consolidating research findings that articulate the measures and future needs of BIM integration with other digital technologies to mitigate construction accidents in high-rise building projects. The framework also renders practical references for industry practitioners towards effective and safer construction.

THE PREVENTIVE PRIORITY PLAN BASED ON THE CAUSALITY ANALYSIS OF THE CONSTRUCTION ACCIDENT

The case of construction accident that occurred mid-2019 and seized a lot of attention in the surrounding community is a construction accident on the implementation of underpass construction project located in Yogyakarta. The underpass excavation wall in this project collapsed then led two vehicles are fall. Although the types of accidents are almost identical to each project, it does not mean that the same reason causes the accidents. Various methods can carry out efforts to prevent work accidents, one of which is with assessment method and risk analysis using Analytical Hierarchy Process (AHP) which sub indicators are determined using Fault Tree Analysis (FTA). The method conducted with a review in the site by referring to Ministerial Regulation No. 21 year 2019 about the SMKK (Construction Safety Management System) guidelines. This research was conducted to identify the factors and indicators of management of thesupervisory consultant and the contractor. They had a significant influence and contribution to the implementation of the Yogyakarta Kentungan Underpass construction project. The results of this early-stage study served into two outcomes. First, the accuracy of the implementation of construction safety management system based on the assessment of the contractor is 85.938% and the percentage level of accuracy of the supervisory consultant is 97.29%. Both percentages fall into the category of Satisfactory Implementation Assessment because the valuation range is included between 85% to 100%. Second, after analyzing the risk using AHP method, the indicator that is used as a reference priority for the construction safety system of underpass construction projects and has the highest risk level that can causean underpass project construction accident from the contractor's point of view is the sub-indicator of supporting facilities and infrastructure with a risk level value of 0.042 whereas from the supervisory consultant’ perspective is the sub-indicator about to measuring the dimensions of the road building installed in the site with a risk level value of 0.052.

Integrating feature engineering, genetic algorithm and tree-based machine learning methods to predict the post-accident disability status of construction workers

The construction industry is among the riskiest industries around the world. Hence, the preliminary studies exploring the consequences of occupational accidents have received considerable attention in research society. This study aims to develop a comprehensive framework to predict the post-accident disability status of construction workers. The dataset comprising 47,938 construction accidents recorded in Turkey was subjected to a detailed multi-step feature engineering approach, including data encoding, data scaling, dimension reduction, and data resampling. Predictions were performed through four tree-based ensemble machine learning models: Random Forest, XGBoost, AdaBoost, and Extra Trees, as well as a state-of-the-art optimization method for hyperparameter tuning, Genetic Algorithm (GA). GA-XGBoost presented the highest prediction rate with 0.8292 in terms of accuracy and 0.8120 with respect to AUROC. The findings may aid in predicting construction workers' post-accident disability status, resulting in a safer working environment and productivity planning in construction projects.

Limiting reasons for use of personal protective equipment among construction workers: Case studies in Sri Lanka

The Sri Lankan construction industry offers substantial employment opportunities and contributes significantly to national economic growth, but it is also plagued by unacceptably high rates of injuries and fatalities, especially among SME construction organisations. Existing literature disclosed that 90% of construction accidents in Sri Lanka are occurred due to unsafe behaviours of workers where the non-usage of personal protective equipment is prominent. Despite the abundance of research on construction safety, a gap in literature could be identified, when it comes to exploring the reasons behind the non-usage of PPE by construction workers in Sri Lanka. Therefore, this paper aimed to bridge the gap that exists in the existing literature. An exploratory case study was selected as the research strategy to achieve the research aim. Two SME construction projects were selected as cases. Fourteen semi-structured interviews were conducted in both cases with managerial and worker levels personnel. Data analysis was carried out using code-based content analysis. Findings were derived under three main categories, namely, ‘individual’, ‘organisational’, and ‘environmental’. Altogether 18 reasons including 09 reasons under the ‘individual’ category (refer Codes InC/R1 – InC/R9), another 08 reasons under the ‘organisational’ category (refer Codes OrC/R1-OrC/R8), and 01 reason under the ‘environmental’ category (refer Code EnC/R1) were identified in this study. The analysis of these reasons generated knowledge, which can be used by respective industrial safety practitioners in Sri Lanka in understanding the current situation and as a way forward for enhancing the use of PPE among construction workers.

Effectiveness of Serious Games for Safety Training: A Mixed Method Study

AbstractEffective safety training is essential to reduce the number of construction accidents caused by unsafe human actions. The application of serious games in construction safety is growing rapi...

Construction safety knowledge sharing on Twitter: A social network analysis

Many studies show that unsafe behavior is the main cause of construction accidents. Safety education and training are effective means to minimise people’s unsafe behaviors. Apart from traditional face-to-face construction knowledge sharing, social media is a good tool because it is convenient, efficient, and widely used. We applied both social network analysis and sentiment analysis to investigate knowledge sharing on Twitter. Our study is a novel attempt to understand social structure of “construction safety”- related twitter networks and the opinion leaders. We selected and analyzed 6561 tweets of three users’ networks on Twitter – “construction safety”, “construction health” and “construction accident”. We found that three networks had low density and many isolated vertices, which showed that users did not actively interact with each other. The opinion leaders in this study were mostly organizations or government agencies. The top one is “cif_ireland”, the Irish construction industry’s representative body, the Construction Industry Federation. 3200 Tweets of the top opinion leader were analyzed through graph metrics calculation, cluster analysis, sentiment analysis, and correlation analysis. The opinion leader used Twitter as a medium to disseminate the latest safety news. Thus, we may use Twitter to stimulate people's interest on construction safety topics, share construction safety knowledge, opinions and ideas. Besides, our results showed that sentiment valence had no correlation with number of favorites or retweets. Nevertheless, there was a positive correlation between favorites and retweets.

Analisis Kausalitas Kecelakan Konstruksi dengan Pendekatan Analogi Fault Tree Analysis (FTA)

In mid-2019, there was a construction accident during the underpass construction project in Yogyakarta. The underpass excavation wall in this project was collapsed and 2 vehicles were reported fallen. Although such accident sometimes occurs in some projects, it does not mean that these accidents are caused by the same source. Many efforts to prevent accidents have been done by various methods and one of them is an assessment by observation at construction sites referring to Government Regulation 05 2014 concerning SMK3 (Occupational Safety and Health Management System) in the Public Works Sector Construction. The details about the implementation of construction work are described in PUPR Decree No. 21 in 2019 in term of the Construction Safety Management System (SMKK) Guidelines. This research was conducted to identify factors and indicators of management consultants, supervisors and contractors who have a major impact and contribution to the underpass construction project in Kentungan, Yogyakarta. The percentage level of accuracy in the application of the construction safety management system based on the assessment of the contractor was 85.938% and for the supervisory consultant the percentage level of accuracy was 97.29%. Both percentages are included in the satisfactory category since the assessment ranges are between 85% and 100%. Based on these two assessments, an evaluation was carried out using a Fault Tree Analysis to determine the causality flow of construction accidents.

Interrelation between policies and safety culture on safety performance and project performance in the construction sector

The construction industry sector as a contributor to economic development in a country has problems in its implementation. Construction accidents that often occur can have an adverse impact on companies but also for the state. So that it is necessary to identify the relationship between policies and what Safety Culture has the most influence on safety performance and project performance on a construction project. The purpose of this study is to find out what safety policy and culture variables have the most influence on safety performance and project performance in the construction sector. This study uses primary data in the form of a survey of 193 respondents, as well as secondary data from literature which is then validated by experts. The results of the respondent questionnaire survey were then analyzed using the SEM-PLS method, in order to obtain a pattern of relationships between safety policy and culture variables on safety performance and project performance. The result of the research is that safety policies and incentives must be implemented by companies in the construction sector to provide good control of all aspects such as security objectives, procedural mechanisms, construction assessments and resource mobilization.

Sustainability in Construction Work: A Perspective on Accidents and Building Failure Mitigation in Indonesia

Sustainability in construction sector implementation depends to a wide range of level at national, regional, and local level. Also, it depends on the social and cultural aspect. Construction site safety is an essential aspect of sustainable construction. This paper proposes to identify the causes of accidents and building failure; to mitigate construction safety and building failure, and to describe the development and implementation of safety construction in order to improve safety culture according to the Law of Indonesia Republic No. 2/2017 of Construction Service and Decree of Minister of Public Works and Housing No. 21/PRT/M/2019 of Implementation Guideline of Construction Safety Management. Furthermore, the awareness of d from considering the underlying causes of accidents. This paper suggested, for the prevention of COVID-19 control and the accordance of construction safety; the optimization of digital services in coordination, supervision, control, and administrative governance is urgently needed. Moreover, the development of information technology and legal basis are required to achieve zero construction accidents and high quality infrastructure for both the service providers and users.