Search

Construction safety accidents have become increasingly frequent in recent years, leading to numerous casualties and substantial property losses. These incidents are often attributed to inadequate supervision on construction sites and workers' low safety awareness. Traditional manual management methods, which are labor-intensive and resource-consuming, are no longer effective. Therefore, this study proposes a novel single-stage model based on YOLOv8s, designed for two primary purposes: detecting workers' personal protective equipment and monitoring and recognizing when workers enter hazardous areas. The model provides real-time feedback on detection results to reduce the incidence of construction accidents. Additionally, a brief design for distance calculation was introduced. The model was trained for 200 iterations on a Roboflow dataset comprising 103,500 annotated images. Experimental results showed that YOLOv8s outperformed YOLOv8n, YOLOv5s, and YOLOv5n in detection performance, achieving a mean average precision with the intersection over union (IoU) threshold set to 50% (mAP50) of 84.0%, precision of 85.0%, and recall of 60.5% across 9 detection classes. By leveraging artificial intelligence technology, this study aims to offer an effective method for enhancing construction site safety, which can be further improved with additional images and a more robust network architecture. [ABSTRACT FROM AUTHOR]

Currently, the incidence of accidents involving falls from height at construction sites caused by workers climbing guardrails is still high. Traditional unsafe behavior management mainly relies on a safety patrol of construction-site supervisors, which consumes considerable laborpower and time. There is still a critical need for an automated safety management method to identify unsafe guardrail climbing behavior. This study proposes a worker behavior identification method based on visual data fusion of a worker's surrounding environment and posture data. Videos of seven participants' guardrail climbing behavior through multiangle and multidistance cameras were analyzed to verify this method. By analyzing the environment and posture of the participants, three methods based on environment, posture, and fusion data were used to detect the stage of guardrail climbing action of the workers and compare them with the ground truth labeled by safety experts. The precision and recall of worker guardrail climbing behavior based on the fusion method were 82% and 83% respectively, which is better performance than that obtained using a single method. The data fusion–based method avoids the misjudgment generated by a single detection method and can identify the guardrail climbing behavior more accurately. Practical Applications: Guardrail climbing is a typical unsafe behavior that exposes workers to a high risk of falling from height. However, there is a lack of research on the interaction between workers and guardrail systems in the construction industry. This study provides a nonintrusive method for automating detection and management of guardrail climbing behavior on construction site. Using existing surveillance cameras, this method can be deployed at low cost with slight interference with workers. Based on the detection, appropriate interventions are expected to effectively reduce workers' unsafe behaviors during construction and improve safety on site. The detection of guardrail climbing, which is one of the variety of unsafe behaviors associated with falls from height, can enrich the intelligent construction safety management system effectively. Moreover, this study also provides reference and quantitative indicators (e.g., a guardrail climbing unsafe behavior database) for risk assessment and early warning of workers who are exposed to risk of fall from height. [ABSTRACT FROM AUTHOR]

Work-related musculoskeletal disorders (WMSDs) represent a significant health challenge for workers in construction environments, often arising from prolonged exposure to ergonomic risks associated with manual labor, awkward postures, and repetitive motions. These conditions not only lead to diminished worker productivity but also incur substantial economic costs for employers and healthcare systems alike. Thus, there is an urgent need for effective tools to assess and mitigate these ergonomic risks. This study proposes a novel monocular 3D multi-person pose estimation method designed to enhance ergonomic risk assessments in construction environments. Leveraging advanced computer vision and deep learning techniques, this approach accurately captures and analyzes the spatial dynamics of workers' postures, with a focus on detecting extreme knee flexion, a critical indicator of work-related musculoskeletal disorders (WMSDs). A pilot study conducted on an actual construction site demonstrated the method's feasibility and effectiveness, achieving an accurate detection rate for extreme flexion incidents that closely aligned with supervisory observations and worker self-reports. The proposed monocular approach enables universal applicability and enhances ergonomic analysis through 3D pose estimation and group pose recognition for timely interventions. Future efforts will focus on improving robustness and integration with health monitoring to reduce WMSDs and promote worker health. [ABSTRACT FROM AUTHOR]

Personal protective equipment (PPE), including helmets, harnesses, and lanyards, is pivotal in preventing falls from heights at construction sites. However, ensuring consistent and correct usage of PPE presents a significant challenge. To address this issue, this study introduces an enhanced You Only Look Once, version 8 model (YOLOv8), a computer-vision-based AI model tailored for real-time multiclass PPE monitoring on portable edge devices. A pioneering large-scale multiclass PPE data set is curated to facilitate model training. Balancing detection accuracy with a lightweight design, we augment YOLOv8 through the integration of the coordinate attention module, ghost convolution module, transfer learning, and merge-nonmaximum suppression. The proposed model surpasses the original YOLOv8 and state-of-the-art models, showcasing improved accuracy and reduced computational cost. Deployed on the edge device Jetson Xavier NX, the model achieves precise PPE detection (mAP50 : 92.52%) in real-time, operating at 9.11 frames per second. These findings establish a robust foundation for the efficient and real-time automated safety monitoring of construction sites, promising substantial enhancements to worker safety and data privacy within the construction industry. [ABSTRACT FROM AUTHOR]

Due to the dynamic nature of work environments and conditions in construction, it is necessary to perform a job hazard analysis (JHA) prior to the commencement of hazardous jobs, and regularly review and update it. JHA is considered an intellectual activity subject to substantial influence by the experience and knowledge of the individuals conducting the analysis. Given the manual nature of JHA in current practice, its thorough preparation and use are time-consuming and laborious; thus, there is a great need to automate it. Against this background, this research aimed to develop a conceptual ontological model that can support the automation of JHA processes, including the tacit knowledge possessed by experts to facilitate automation. A JHA document analysis and a qualitative Delphi study were adopted to identify the concepts and associations embedded in JHA. An abductive data analysis approach was used with the guidance of a theoretical understanding of the systems model of construction accident causation to analyze the data collected from JHA documents and interviews. The findings offer valuable insights into important entities, subentities, and relationships that are associated with hazard identification and risk assessment, which form the basis for developing a conceptual ontological model. Such an ontology can facilitate the automation of JHA with an enhanced level of reasoning capability, through which the efficiency and effectiveness of JHA on construction sites can be improved. [ABSTRACT FROM AUTHOR]

Construction activities are often conducted in outdoor and harsh environments and involve long working hours and physical and mental labor, which can lead to significant mental fatigue among workers. This study introduces a novel and non-invasive method for monitoring and assessing mental fatigue in construction workers. Based on cognitive neuroscience theory, we analyzed the neurophysiological mapping of spontaneous mental fatigue and developed multimodal in-ear sensors specifically designed for construction workers. These sensors enable real-time and continuous integration of neurophysiological signals. A cognitive experiment was conducted to validate the proposed mental fatigue assessment method. Results demonstrated that all selected supervised classification models can accurately identify mental fatigue by using the recorded neurophysiological data, with evaluation metrics exceeding 80%. The long short-term memory model achieved an average accuracy of 92.437%. This study offers a theoretical framework and a practical approach for assessing the mental fatigue of on-site workers and provides a basis for the proactive management of occupational health and safety on construction sites. [ABSTRACT FROM AUTHOR]

To address the common issues of lacking indicator system identification, causal relationship quantification, and path simulation analysis in the current research on safety performance in prefabricated construction, a method for improving safety performance in prefabricated construction based on the decision-making trial and evaluation laboratory (DEMATEL) and NK model is proposed. Firstly, through theoretical analysis and literature review, the indicator system for safety performance in prefabricated construction is identified using the grounded theory. Secondly, expert research and quantitative analysis are combined to analyze the causal relationship of the indicators using the DEMATEL method. Then, the DEMATEL method is integrated with the NK model to carry out a key indicator adaptability modeling analysis and three-dimensional simulation. Finally, a case study is conducted to validate the usability and effectiveness of the proposed model and method. The results show that X6 (construction and implementation of safety management system) had the highest impact on the other indicators, and X14 (quality and safety status of prefabricated components) was most influenced by other indicators. X6 (construction and implementation of safety management system), X1 (personnel safety awareness and attitude), X14 (quality and safety status of prefabricated components), and X12 (construction site working environment) were identified as key performance indicators. "X6 (construction and implementation of safety management system) → X1 (personnel safety awareness and attitude) → X14 (quality and safety status of prefabricated components) → X12 (construction site working environment)" was considered the optimal path to improve construction safety performance. [ABSTRACT FROM AUTHOR]

Rapid advances in deep learning and computer vision enable traditional cloud-based decision-making through edge computing with the Artificial Intelligent Internet of Things (AIoT) image sensors (AIoT-IS), thus improving the timeliness and security of image recognition. This study is indented to investigate the potential costs and benefits of AIoT-IS applications. This study summarizes AIoT-IS application scenarios for construction safety monitoring and proposes a cost/benefit analysis method for AIoT-IS implementation projects. According to the case study results, AIoTIS achieves significant benefits, with a Net Present Value Index (NPVI) of 19.17% and a Benefit/Cost Ratio (BCR) of 4.65 as applied to construction site safety monitoring. Interviews with domain experts also provided qualitative feedback, pointing to the directions for future research. The proposed method is applicable for the decision-making of AIoT-IS adoption and the feasibility assessment of other innovative construction technologies. [ABSTRACT FROM AUTHOR]

Collision accidents involving construction vehicles and workers frequently occur at construction sites. Computer vision (CV) technology presents an efficient solution for collision-risk pre-warning. However, CV-based methods are still relatively rare and need an enhancement of their performance. Therefore, a novel three-stage collision-risk pre-warning model for construction vehicles and workers is proposed in this paper. This model consists of an object-sensing module (OSM), a trajectory prediction module (TPM), and a collision-risk assessment module (CRAM). In the OSM, the YOLOv5 algorithm is applied to identify and locate construction vehicles and workers; meanwhile, the DeepSORT algorithm is applied to the real-time tracking of the construction vehicles and workers. As a result, the historical trajectories of vehicles and workers are sensed. The original coordinates of the data are transformed to common real-world coordinate systems for convenient subsequent data acquisition, comparison, and analysis. Subsequently, the data are provided to a second stage (TPM). In the TPM, the optimized transformer algorithm is used for a real-time trajectory prediction of the construction vehicles and workers. In this paper, we enhance the reliability of the general object detection and trajectory prediction methods in the construction environments. With the assistance afforded by the optimization of the model's hyperparameters, the prediction horizon is extended, and this gives the workers more time to take preventive measures. Finally, the prediction module indicates the possible trajectories of the vehicles and workers in the future and provides these trajectories to the CRAM. In the CRAM, the worker's collision-risk level is assessed by a multi-factor-based collision-risk assessment rule, which is innovatively proposed in the present work. The multi-factor-based assessment rule is quantitatively involved in three critical risk factors, i.e., velocity, hazardous zones, and proximity. Experiments are performed within two different construction site scenarios to evaluate the effectiveness of the collision-risk pre-warning model. The research results show that the proposed collision pre-warning model can accurately predict the collision-risk level of workers at construction sites, with good tracking and predicting effect and an efficient collision-risk pre-warning strategy. Compared to the classical models, such as social-GAN and social-LSTM, the transformer-based trajectory prediction model demonstrates a superior accuracy, with an average displacement error of 0.53 m on the construction sites. Additionally, the optimized transformer model is capable of predicting six additional time steps, which equates to approximately 1.8 s. The collision pre-warning model proposed in this paper can help improve the safety of construction vehicles and workers. [ABSTRACT FROM AUTHOR]

Intrusion behavior in hazardous areas is one of the major causes of construction safety accidents including falls from height and strikes by objects. Implementing automatic and preassessment of intrusions to enhance safety performance is of great importance in construction areas. Traditional behavioral safety management mainly relies on manual observation, which makes it difficult to accurately identify detailed changes in behavioral posture, while the results of risk analysis are susceptible to bias due to subjective factors. The emergence of artificial intelligence techniques and computer vision has provided new solutions for human behavior detection in recent years. Accurate vision-based skeleton extraction helps capture detailed behavioral information. Current studies generally focus on intrusion after the occurrence and rarely select metrics considering complex human motion features. It is difficult to accurately assess the potential intrusion risk, resulting in inefficient ex-ante safety management outcomes. This paper presents a novel intrusion assessment approach by integrating human kinematics to extract risk indicators and apply objective assessment methods for risk quantification. An indoor experiment with control groups was conducted by employing skeleton detection technology with safety knowledge to demonstrate its feasibility and effectiveness. The risk levels of the different activities were compared through a control group experimental analysis. The results show that a satisfying accuracy of intrusion assessment can be achieved for different workers. Appropriate warning and intervention methods can be implemented to mitigate the occurrence or reduce the severity of intrusions, thus reducing safety incidents on construction sites. [ABSTRACT FROM AUTHOR]

Purpose: Health and safety is an important issue in workplaces, and despite safety procedures becoming more strict, serious accidents are still happening within the UK construction sector. This demonstrates poor performance in the implementation of safety procedures on construction sites. One of the key challenges is the unwillingness of the site workforce, especially the subcontracted operatives, to adhere to safety provisions on construction sites. As such, this study investigates the strategies for enhancing safe behaviour amongst subcontracted operatives in the UK construction industry. Design/methodology/approach: The study used exploratory sequential mixed method research, involving interviews and questionnaires as means of data collection, and thematic analysis, reliability analysis and exploratory factor analysis as methods of data analysis. Findings: The study suggests that various carrot and stick measures are expected to be put in place as part of the strategies for enhancing safe behaviour amongst subcontracted operatives. These include adequate enforcement of safety practices by the management, operative engagement and motivation, commendation and rewards, site safety targets, leadership style and motivation. Originality/value: Application of the suggested measures could enhance safety on construction sites, as it provides practical measures and solutions for inculcating safety behaviours amongst the site operatives who are most likely to be the victims of site accidents. [ABSTRACT FROM AUTHOR]

Limited research exists on safety leadership and safety climate in developing countries, despite their established importance in the construction industry. This study addresses this gap by investigating how immediate superiors' safety leadership behaviours influence safety climate perceptions among construction professionals in southern India. Using a quantitative approach, the study collected valid questionnaire surveys among 279 construction professionals by convenience sampling across various construction sites. The survey revealed that safety leadership significantly and positively predicts five key safety climate factors: management's commitment to safety, safety equipment and procedures, safety training, communication and openness, and group dynamics and safety culture. These findings highlight the critical role immediate superiors play in shaping safety climate perceptions through their commitment, communication, and employee involvement. This research underscores the importance of investing in safety leadership development to improve safety outcomes, reduce accidents and injuries, and enhance regulatory compliance within the Indian construction industry. [ABSTRACT FROM AUTHOR]

Wearable biosensors, in conjunction with machine learning, have been employed to develop less invasive monitoring techniques for assessing stress among construction workers during fieldwork. However, existing techniques face limitations in terms of scalable field application due to their subject and context dependency; it is difficult to apply them to new people in new contexts without additional labeled data collection. Therefore, this study developed a stress detection technique that incorporates domain adaptation, simultaneously learning a classifier and a subject- and context-independent features, in this way advancing generalizability. The proposed technique consistently demonstrated superior accuracy compared with benchmarks in classifying stress levels within a testing data set whose subjects and contexts were different from those of training data sets. Thus, the technique can advance generalizability across subjects and contexts. This finding can help us to reliably detect stress for new people in new contexts without additional labeled data collection, thereby contributing to scalable field application of wearable-based stress monitoring at construction sites. [ABSTRACT FROM AUTHOR]

The complexity of the wharf components and the harshness of the offshore construction environment increase the safety risk of hazards, which has highlighted the importance and urgency of safety risk management in high-pile wharf constructions. This paper established a visualized digital construction safety risk model for high-pile wharf based on a so-called FAHP method (the combination of fuzzy comprehensive evaluation (FCE) and analytic hierarchy process (AHP) methods). The construction safety risk indicators were constructed as the target layer, the principle layer and the scheme layer, and then the corresponding safety risk assessment algorithm was established. The physical, functional and safety risk assessment parameters of the component in the BIM model were employed to the safety risk assessment algorithm, and the risk assessment level of each sub-process was subsequently classified. The case study indicated that the high-pile wharf construction project included five elements in principle layer and 15 risk indicators in the scheme layer. Moreover, it was demonstrated that the sub-processes with the highest construction risk level were steel pipe pile sinking in wharf construction and steel pipe pile, steel sheath-immersed pile sinking and embedded rock pile construction in approaches to bridge construction with a risk level of III. In this way, the quantitative visualization of the construction safety risk was effectively realized, which facilitates the safety risk management of construction sites and timely warning and response to unexpected safety accidents. [ABSTRACT FROM AUTHOR]

The construction industry is vulnerable to heat-related hazards, necessitating identification of high-risk areas and contributing factors. This study introduces a novel framework that integrates microclimate simulations with geometric modeling, focusing on the often-underestimated role of heat radiation in assessing heat-related hazards in construction environments. By analyzing 2 years of meteorological data from a construction site in College Station, Texas, this research uncovers the inadequacies of the heat index (HI), a widely recognized thermal-physiological model in the US construction sector. Compared with the wet bulb globe temperature (WBGT), the HI displayed notable variations. Specifically, out of 1,719 data points labeled as danger by HI, WBGT recategorized them as low risk (n=62), moderate risk (n=1,264), high risk (n=300), and extreme risk (n=93). These discrepancies are predominantly associated with the influence of heat radiation. Furthermore, this study emphasizes the importance of accounting for the spatially varying nature of heat radiation in construction environments, influenced by factors such as adjacent structure height, surface materials, and shading patterns. The research highlights the need for monitoring site-specific heat radiation and its potential impact on workers' health and safety. Overall, the findings contribute to our understanding of heat-related hazards in construction and offer valuable insights for developing more effective heat-related safety management strategies. [ABSTRACT FROM AUTHOR]

The construction industry suffers from workplace accidents, including injuries and fatalities, which represent a significant economic and social burden for employers, workers, and society as a whole. The existing research on construction accidents heavily relies on expert evaluations, which often suffer from issues such as low efficiency, insufficient intelligence, and subjectivity. However, expert opinions provided in construction accident reports offer a valuable source of knowledge that can be extracted and utilized to enhance safety management. Today this valuable resource can be mined as the advent of artificial intelligence has opened up significant opportunities to advance construction site safety. Ontology represents an attractive representation scheme. Though ontology has been used in construction safety to solve the problem of information heterogeneity using formal conceptual specifications, the establishment and development of ontologies that utilize construction accident reports are currently in an early stage of development and require further improvements. Moreover, research on the exploration of incorporating deep learning methodologies into construction safety ontologies for predicting construction safety incidents is relatively limited. This paper describes a novel approach to improving the performance of accident prediction models by incorporating ontology into a deep learning model. First, a domain word discovery algorithm, based on mutual information and adjacency entropy, is used to analyze the causes of accidents mentioned in construction reports. This analysis is then combined with technical specifications and the literature in the field of construction safety to build an ontology encompassing unsafe factors related to construction accidents. By employing a Translating on Hyperplane (TransH) model, the reports are transformed into conceptual vectors using the constructed ontology. Building on this foundation, we propose a Text Convolutional Neural Network (TextCNN) model that incorporates the ontology specifically designed for construction accidents. We compared the performance of the TextCNN model against five traditional machine learning models, namely Naive Bayes, support vector machine, logistic regression, random forest, and multilayer perceptron, using three different data sets: One-Hot encoding, word vector, and conceptual vectors. The results indicate that the TextCNN model integrated with the ontology outperformed the other models in terms of performance achieving an impressive accuracy rate of 88% and AUC value of 0.92. [ABSTRACT FROM AUTHOR]

Safety academics and practitioners in construction typically use safety prediction models that employ information associated with past incidents to predict the likelihood of future injury or fatality on site. However, most prevailing models utilize only information related to failure (i.e., incident), so they cannot distinguish effectively between success and failure without well-informed comparison. Furthermore, recordable incidents on construction sites are extremely rare, which results in data that are too sparse to make predictions with high statistical power. This paper empirically reviews different approaches to safety to increase the understanding of conditions associated with safety success and failure. Empirical data about business-, project-, and crew-related factors were collected to predict serious injury and fatality (SIF) exposure conditions. A variety of modeling techniques were tested in a machine learning pipeline to identify the most accurate and stable predictive models. Results showed that the multilayer perceptron (MLP) approach best distinguished SIF exposure conditions from safety success conditions using nonlinear decision boundaries. The most influential factors in the models included the crew experience working together, supervisor experience with the crew, total number of workers under the supervisor's purview, and the maturity of leadership development programs for frontline supervisors. This study showed that data sets with both success and failure information yield more reliable and meaningful predictions than data sets with failure alone. Such an approach to safety data collection, analysis, and prediction could be used by future researchers to generate new insights into the causes of serious incidents and the relationships among causal factors. [ABSTRACT FROM AUTHOR]

For practitioners and researchers, construction safety is a major concern. The construction industry is among the world's most dangerous industries, with a high number of accidents and fatalities. Workers in the construction industry are still exposed to safety risks even after conducting risk assessments. The use of personal protective equipment (PPE) is essential to help reduce the risks to laborers and engineers on construction sites. Developments in the field of computer vision and data analytics, especially using deep learning algorithms, have the potential to address this challenge in construction. This study developed several models to enhance the safety compliance of construction workers with respect to PPE. Through the utilization of convolutional neural networks (CNNs) and the application of transfer learning principles, this study builds upon the foundational YOLO-v5 and YOLO-v8 architectures. The resultant model excels in predicting six key categories: person, vest, and four helmet colors. The developed model is validated using a high-quality CHV benchmark dataset from the literature. The dataset is composed of 1330 images and manages to account for a real construction site background, different gestures, varied angles and distances, and multi-PPE. Consequently, the comparison among the ten models of YOLO-v5 (You Only Look Once) and five models of YOLO-v8 showed that YOLO-v5x6's running speed in analysis was faster than that of YOLO-v5l; however, YOLO-v8m stands out for its higher precision and accuracy. Furthermore, YOLOv8m has the best mean average precision (mAP), with a score of 92.30%, and the best F1 score, at 0.89. Significantly, the attained mAP reflects a substantial 6.64% advancement over previous related research studies. Accordingly, the proposed research has the capability of reducing and preventing construction accidents that can result in death or serious injury. [ABSTRACT FROM AUTHOR]

Background: The risk of high-energy trauma injuries on construction sites is relatively high. A delayed response time could affect outcomes after severe injury. This study assessed if an advanced first aid course for first aid response for laypersons (employees or apprentices) in the construction industry or real-time video communication and support with ambulance personnel, or neither, together with access to an advanced medical kit, would have an effect on immediate layperson vital responses in a severe injury scenario. Method: This was a controlled simulation study. Employees or apprentices at a construction site were recruited and randomly allocated into a group with video support or not, and advanced first aid course or not, and where one group had both. The primary outcomes were correct behavior to recognize and manage an occluded airway and correct behavior to stop life-threatening bleeding from a lower extremity injury. Secondary outcomes included head-to-toe assessment performed, placement of a pelvic sling, and application of remote vital signs monitors. Results: Ninety participants were included in 10 groups of 3 for each of 4 exposures. One group was tested first as a baseline group, and then later after having done the training course. Live video support was effective in controlling bleeding. A first aid course given beforehand did not seem to be as effective on controlling bleeding. Video support and the first aid course previously given improved the ability of bystanders to manage the airway, the combination of the two being no better than each of the interventions taken in isolation. Course exposure and video support together were not superior to the course by itself or video by itself, except regarding placing the biosensors on the injured after video support. Secondary results showed an association between video support and completing a head-to-toe assessment. Both interventions were associated with applying a pelvic sling. Conclusion: These findings show that laypersons, here construction industry employees, can be supported to achieve good performance as first responders in a major injury scenario. Prior training, but especially live video support without prior training, improves layperson performance in this setting. [ABSTRACT FROM AUTHOR]

Wearable sensing devices (WSDs) have enormous promise for monitoring construction worker safety. They can track workers and send safety-related information in real time, allowing for more effective and preventative decision making. WSDs are particularly useful on construction sites since they can track workers' health, safety, and activity levels, among other metrics that could help optimize their daily tasks. WSDs may also assist workers in recognizing health-related safety risks (such as physical fatigue) and taking appropriate action to mitigate them. The data produced by these WSDs, however, is highly noisy and contaminated with artifacts that could have been introduced by the surroundings, the experimental apparatus, or the subject's physiological state. These artifacts are very strong and frequently found during field experiments. So, when there is a lot of artifacts, the signal quality drops. Recently, artifacts removal has been greatly enhanced by developments in signal processing, which has vastly enhanced the performance. Thus, the proposed review aimed to provide an in-depth analysis of the approaches currently used to analyze data and remove artifacts from physiological signals obtained via WSDs during construction-related tasks. First, this study provides an overview of the physiological signals that are likely to be recorded from construction workers to monitor their health and safety. Second, this review identifies the most prevalent artifacts that have the most detrimental effect on the utility of the signals. Third, a comprehensive review of existing artifact-removal approaches were presented. Fourth, each identified artifact detection and removal approach was analyzed for its strengths and weaknesses. Finally, in conclusion, this review provides a few suggestions for future research for improving the quality of captured physiological signals for monitoring the health and safety of construction workers using artifact removal approaches. [ABSTRACT FROM AUTHOR]

Over the past decade, global industrial and construction growth has underscored the importance of safety. Yet, accidents continue, often with dire outcomes, despite numerous safety-focused initiatives. Addressing this, this article introduces a novel approach using YOLOv8, a rapid object detection model, for recognizing personal protective equipment (PPE). This method, leveraging computer vision (CV) instead of traditional sensor-based systems, offers an economical, simpler and field-friendly solution. We established the Color Helmet and Vest (CHV) and Safety HELmet dataset with 5K images (SHEL5K) datasets, comprising eight object classes like helmets, vests and goggles, to detect worker-worn PPE. After categorizing the dataset into training, testing and validation subsets, diverse YOLOv8 models were assessed based on metrics including precision, recall and mAP50. Notably, YOLOv8x and YOLOv8l excelled in PPE detection, particularly in recognizing person and vest categories. This innovative CV-driven method promises real-time PPE detection, fortifying worker safety on construction sites. [ABSTRACT FROM AUTHOR]

Construction is known as one of the most dangerous industries in terms of worker safety. Collisions due the excessive proximity of workers to moving construction vehicles are one of the leading causes of fatal and non-fatal accidents on construction sites internationally. Proximity warning systems (PWS) have been proposed in the literature as a solution to detect the risk for collision and to alert workers and equipment operators in time to prevent collisions. Although the role of sensing technologies for situational awareness has been recognised in previous studies, several factors still need to be considered. This paper describes the design of a prototype sensor-based PWS, aimed mainly at small and medium-sized construction companies, to collect real-time data directly from construction sites and to warn workers of a potential risk of collision accidents. It considers, in an integrated manner, factors such as cost of deployment, the actual nature of a construction site as an operating environment and data protection. A low-cost, ultra-wideband (UWB)-based proximity detection system has been developed that can operate with or without fixed anchors. In addition, the PWS is compliant with the General Data Protection Regulation (GDPR) of the European Union. A privacy-by-design approach has been adopted and privacy mechanisms have been used for data protection. Future work could evaluate the PWS in real operational conditions and incorporate additional factors for its further development, such as studies on the timely interpretation of data. [ABSTRACT FROM AUTHOR]

• Vision-based monitoring depends on ladder safety rules. • Worker height estimated by bounding box height ratio. • Correlation of keypoints enhances helmet identification. • Improved regression loss boosts unsafe behavior detection. Introduction: Fatal fall from height accidents, especially on construction sites, persist, underscoring the importance of monitoring and managing worker behaviors to enhance safety. Deep learning showed the possibility of substituting the manual work of safety managers. However, applying detection results to determine compliance with safety regulations has limitations. Method: This study estimated the actual working height depending on the height of the object detection bounding box by specifying the consistent hinge part as a target marker based on ladder manufacturing regulations. Furthermore, an attempt was made to improve the separation between workers, coworkers, and persons unconnected to ladder activities by applying an optimized loss function alongside an attention mechanism. Results: The experimental results showed that an average precision increased from 87.60% to 90.44%. The performance of the monitoring unsafe behavior of ladder worker following the Korea Occupational Safety and Health Agency (KOSHA) guide was evaluated by 91.40 F1-Score, which accumulated sorted according to the working height. Conclusions: Experimental results show the feasibility of the real-time automate safety monitoring in ladder work. Practical Applications: By linking the estimated working height and deep learning multi-detection results to established safety regulations, the proposed method shows the potential to automatically monitoring unsafe behaviors in construction site. [ABSTRACT FROM AUTHOR]

Accidents occur in the construction industry as a result of non-compliance with personal protective equipment (PPE). As a result of diverse environments, it is difficult to detect PPE automatically. Traditional image detection models like convolutional neural network (CNN) and vision transformer (ViT) struggle to capture both local and global features in construction safety. This study introduces a new approach for automating the detection of personal protective equipment (PPE) in the construction industry, called PPE_Swin. By combining global and local feature extraction using the self-attention mechanism based on Swin-Unet, we address challenges related to accurate segmentation, robustness to image variations, and generalization across different environments. In order to train and evaluate our system, we have compiled a new dataset, which provides more reliable and accurate detection of personal protective equipment (PPE) in diverse construction scenarios. Our approach achieves a remarkable 97% accuracy in detecting workers with and without PPE, surpassing existing state-of-the-art methods. This research presents an effective solution for enhancing worker safety on construction sites by automating PPE compliance detection. [ABSTRACT FROM AUTHOR]

In recent years, a lot of attention has been paid to deep learning methods in the context of vision-based construction site safety systems. However, there is still more to be done to establish the relationship between supervised construction workers and their essential personal protective equipment, like hard hats. A deep learning method combining object detection, head center localization, and simple rulebased reasoning is proposed in this article. In tests, this solution surpassed the previous methods based on the relative bounding box position of different instances and direct detection of hard hat wearers and non-wearers. Achieving MS COCO style overall AP of 67.5% compared to 66.4% and 66.3% achieved by the approaches mentioned above, with class-specific AP for hard hat non-wearers of 64.1% compared to 63.0% and 60.3%. The results show that using deep learning methods with a humanly interpretable rule-based algorithm is better suited for detecting hard hat non-wearers. [ABSTRACT FROM AUTHOR]

Workers' motion trajectories or spatial tracks on construction sites contain useful safety-related information. Existing safety management research on worker trajectory typically analyzes the interactions between worker motion trajectory and risk sources. The historical accident-free zone of a group of workers is a reflection of the potential safety zones on a construction site. Few studies have investigated construction workers' trajectory safety risks from the integrated perspectives of group and hazard sources. Therefore this study developed a novel and integrated safety risk diagnosis method combining hazard source and group movement distributions to fully utilize the phone Global Positioning System (GPS) trajectory information of construction workers. The proposed method diagnoses workers' risk exposures by considering workers' trajectories in unsafe and safe areas. In addition, the method uses expert confidence and comprehensive decision indexes to determine the feature weights. Furthermore, the proposed safety risk diagnosis method adopts the grey optimization Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) diagnosis model to diagnose workers' risk management priorities and behavior adjustment direction. An actual project site was used to assess the performance of the proposed diagnostic method. The results show that the developed method provides a quantitative means for project managers to measure workers' spatial-temporal risk exposure, diagnose safety risks, and plan for safety controls. The proposed integrated method provides a new perspective to make full use of workers' trajectory information and helps to provide practical and specific data-driven safety guidance for construction managers and workers. [ABSTRACT FROM AUTHOR]

Vision-based methods for action recognition are valuable for supervising construction workers' unsafe behaviors. However, current monitoring methods have limitations in extracting dynamic information about workers. Identifying hazardous actions based on the spatiotemporal relationships between workers' skeletal points remains a significant challenge in construction sites. This paper proposed an automated method for recognizing dynamic hazardous actions. The method used the OpenPose network to extract workers' skeleton information from the video and applied a spatiotemporal graph convolutional network (ST-GCN) to analyze the dynamic spatiotemporal relationships between workers' body skeletons, enabling automatic recognition of hazardous actions. A novel human partitioning strategy and nonlocal attention mechanism were designed to assign appropriate weight parameters to different joints involved in actions, thereby improving the recognition accuracy of complex construction actions. The enhanced model is called the attention module spatiotemporal graph convolutional network (AM-STGCN). The method achieved a test accuracy of 90.50% and 87.08% in typical work scenarios, namely high-altitude scaffolding scenes with close-up and far views, surpassing the performance of the original ST-GCN model. The high-accuracy test results demonstrate that the model can accurately identify workers' hazardous actions. The newly proposed model is inferred to have promising application prospects and the potential to be applied in broader construction scenarios for on-site monitoring of hazardous actions. [ABSTRACT FROM AUTHOR]

There is a high level of construction safety risk shared among construction workers in tunneling projects due to collaboration on the narrow and semi-enclosed construction site. However, no one has reported on this. Therefore, this paper proposes a new network model to explore risk-sharing features among construction workers based on a two-mode network. That model represents a new personnel safety management tool to provide suitable risk mitigation for tunneling projects. First, the work breakdown structure (WBS)–risk breakdown structure (RBS) method was employed to identify construction activities, risk resources, and construction safety risk factors (CSRFs). Subsequently, the two-mode WBS–RBS matrix was further established. The construction workers' sets were determined based on the organization breakdown structure (OBS)–WBS method and a two-mode OBS–WBS matrix was established. By applying the construction activities in the WBS tree carrying the CSRFs as the link, a two-mode OBS–RBS network was established by converting the two-mode WBS–RBS and OBS–WBS matrices. Hence, taking CSRFs allocated by several construction workers as a basis for network generation, the construction workers' risk-sharing network was further established. Centrality analysis identified the network characteristics and determined the most important construction workers in risk network. For example, this model was employed to explore the whole network characteristics of the Shangwu Tunnel and identify the workers in key positions in the risk-sharing network. Expert interviews demonstrated the model's rationality and practicality. The results show that each construction worker's safety risk-sharing degree in the Shangwu tunnel differed and reached varying levels. However, the staff from the engineering management department were in the key position of the risk-sharing network. Collectively, this model can help construction workers understand their risk-sharing degree to improve their safety awareness and adjust their attitude toward safety accordingly. Moreover, this strategy provides project managers with the necessary information to more effectively allocate safety resources and to be cognizant of the safety quality of each construction worker according to the different risk-sharing degrees. [ABSTRACT FROM AUTHOR]

One of the primary causes of fires at construction sites is welding sparks. Fire detection systems utilizing computer vision technology offer a unique opportunity to monitor fires in construction sites. However, little effort has been made to date in regard to real-time tracking of small sparks that can lead to major fires at construction sites. In this study, a novel method is proposed to detect welding sparks in real-time contour detection with deep learning parameter tuning. An automatic parameter tuning algorithm employing a convolutional neural network was developed to identify the optimum hue saturation value. Additional filtering methods regarding the non-welding zone and a contour area-based filter were also newly developed to enhance the accuracy of welding spark prediction. The method was evaluated using 230 welding spark images and 104 videos. The results obtained from the welding images indicate that the suggested model for detecting welding sparks achieves a precision of 74.45% and a recall of 63.50% when noise images, such as flashing and reflection light, were removed from the dataset. Furthermore, our findings demonstrate that the proposed model is effective in capturing the number of welding sparks in the video dataset, with a 95.2% accuracy in detecting the moment when the number of welding sparks reaches its peak. These results highlight the potential of automated welding spark detection to enhance fire surveillance at construction sites. [ABSTRACT FROM AUTHOR]

Although there have been many studies related to construction site safety that have tried to reduce accidents, no significant improvement has been reported. Because of the complex nature of construction work processes, it is important to have a scenario-based worksite safety management system instead of reports such as safety guidelines and manuals. This study utilizes accumulated construction site accident big data, namely Construction Safety Management Integrated Information (CSI), to establish accident scenarios for different work types. To propose accident occurrence scenarios, the hazard profile managed by CSI and prior research analyses are employed for each work type and cause materials at the construction site. For accident occurrence association rules, we developed a framework based on Work Breakdown Structure–Risk Breakdown Structure (WBS-RBS) for reinforced concrete work, temporary work, and earthwork, considering 25,986 accident cases. Subsequently, association analysis was conducted to derive association rules for each work type. The accident occurrence scenarios were extracted by classifying work types (project type, activity type) and cause materials (object, location). The analysis generated 145 association rules, and 76 association rules for reinforced concrete work, temporary work, and earthwork work were extracted to derive accident scenarios, considering scenarios with high accident frequency. Furthermore, by establishing association rules between work processes, we derived accident types and occurrence rules frequently observed at construction sites. These rules formed the basis for constructing accident occurrence scenarios for each construction type based on WBS-RBS. These findings facilitate the development of appropriate safety management plans and effective accident countermeasures tailored to specific construction types and causes. The developed scenarios will help to improve construction site safety by providing useful information for safety managers and worker training. [ABSTRACT FROM AUTHOR]

This study identifies safety leadership factors affecting construction site safety and organizational safety climate, offering suggestions for adopting optimistic leadership styles and a zero-accident vision. The literature review is done exclusively for identifying factors and improving core knowledge. This study developed a questionnaire to examine the relationships between the organizational safety climate and the safety leadership styles. The questionnaire was distributed to construction companies from all over India. The statistical analysis encompassed 396 verified responses from the survey, yielding an impressive 79.20 percent response rate. The valid responses collected were analysed to find the relative importance index and the association between the categorical variables. The results showed that "personal safety knowledge" ranked the highest while performing the relative importance index analysis. Furthermore, the chi-square analysis found two pessimistic leadership styles, namely "laissez-faire leadership" and "management-by-exception", significantly associated with the safety climate. The study implies that the target audience must avoid adopting the two pessimistic leadership styles to improve the organizational safety climate. This study examines the various safety leadership styles practised among construction professionals for the first time in India. Specifically, it identifies critical factors that affect the organizational safety climate and pessimistic leadership styles that diminish the safety outcomes of the construction site. The results act as an eye-opener for the targeted audience (like senior and middle-level management professionals, academicians, and upcoming researchers) to enhance the safety of construction sites by adopting optimistic leadership styles with an idea of a 'zero accident' construction premises. [ABSTRACT FROM AUTHOR]

A construction site is an open and dynamic space. Construction accidents have been the top-ranked occupational accidents among all industries around the world. Due to the limited quality and quantity of occupational safety supervisors on construction sites, it is difficult to control or prevent risks in real-time. Therefore, a real-time safety warning system based on a deep learning technique (DL) is developed for lifting operations in building construction, called a portable lightweight lifting safety control station (PLSCS). Two modes can be switched manually by the supervisor. If the mode is switched to lifting control mode, PLSCS helps to ensure that nobody is in the hazardous area during lifting operations. The advantages and features of this system are as follows: (1) it warns of the potential safety hazards automatically during the operations; (2) it reduces the workload of occupational safety supervisors; (3) the system is self-powered and easy to carry and deploy. The system was tested and verified in the actual construction site. The results show that the system is useful for improving the safety of lifting operations. [ABSTRACT FROM AUTHOR]

Integrating drones into already dangerous construction sites could expose workers to additional risks and make construction sites more dangerous than before. Several studies have identified various safety challenges of using drones on jobsites. However, limited studies have focused on educating construction workers about the safety challenges of the drone presence in their working environment. This study is the first effort to develop a 360-degree virtual reality (360VR) environment providing a semi-immersive training experience about drone applications in construction, potential safety challenges of working with or near drones, and proposed countermeasures for their safe integration. A repeated measures study design was used to assess the effectiveness of the 360VR training, followed by a system usability assessment. The results indicate that the developed 360VR training significantly improved users' safety knowledge about drones and that the 360VR platform proved to be a sufficiently usable delivery mechanism for this training. The main contribution of this study is to provide a better understanding of 360VR capabilities, as an emerging learning technology, to create virtual learning environments for construction education and training, and, in particular, enhancing trainees' knowledge about working safely with drones. [ABSTRACT FROM AUTHOR]

Purpose: In the study, a five-dimensional-safety risk assessment model (5D-SRAM) is developed to improve the construction safety risk assessment approaches available in the literature. To that purpose, a hybrid multi-dimensional fuzzy-based model is proposed, which provides a comprehensive ranking system for the safety risks existing in a project by considering the contextualization of the construction-related activities resulting in an accident. Design/methodology/approach: The developed 5D-SRAM is based on an amalgamation of different fuzzy-based techniques. Through the proposed fuzzy analytic hierarchy process (AHP) method, the importance weights of essential risk dimensions playing role in defining the magnitude of the construction-related risks are obtained, while a precise prioritized ranking system for the identified safety risks is acquired using the proposed fuzzy technique of order preference similarity to the ideal solution (FTOPSIS). Findings: Through the application of the proposed 5D-SRAM to a real-life case study – which is the case of green building construction projects located in Hong Kong – contributions are realized as follows: (1) determination of a more complete range of risk dimensions, (2) calculation of importance weightings for each risk dimension and (3) obtainment of a precise and inclusive ranking system for safety risks. Additionally, the supremacy of the developed 5D-SRAM against the other safety assessment approaches that are commonly adopted in the construction industry is proved. Research limitations/implications: The developed 5D-SRAM provides the concerned safety decision-makers with not only all the crucial dimensions that play roles toward the magnitude of safety risks posing threats to the workers involved in construction activities, but also they are given hindsight regarding the importance weights of these dimensions. Additionally, the concerned parties are embellished with the final ranking of safety risks in a more comprehensive way than those of existing assessment methods, leading to sagacious adoption of future prudent strategies for dealing with such risks occurring on construction sites. Originality/value: Numerous studies have documented the safety risks faced by construction workers including proposals for risk assessment models. However, the dimensions considered by such models are limited, generally constrained to risk event probability combined with risk impact severity. Overlooking other dimensions that are essential towards the calculation of safety risks' magnitude culminates in overshadowing the further adoption of fruitful mitigative actions. To overcome this shortcoming, this study proposes a novel 5D-SRAM. [ABSTRACT FROM AUTHOR]

Tunnel construction sites pose a significant safety risk to workers due to the low-light conditions that can affect visibility and lead to accidents. Therefore, identifying personal protective equipment (PPE) is critical to prevent injuries and fatalities. A few researches have addressed the challenges posed by tunnel construction sites whose light conditions are lower and images are captured from a distance. In this study, we proposed an improved YOLOX approach and a new dataset for detecting low-light and small PPE. We modified the YOLOX architecture by adding ConvNeXt modules to the backbone for deep feature extraction and introducing the fourth YOLOX head for enhancing multiscale prediction. Additionally, we adopted the CLAHE algorithm for augmenting low-light images after comparing it with eight other methods. Consequently, the improved YOLOX approach achieves a mean average precision of 86.94%, which is 4.23% higher than the original model and outperforms selected state-of-the-art. It also improves the average precision of small object classes by 7.17% on average and attains a real-time processing speed of 22 FPS (Frames Per Second). Furthermore, we constructed a novel dataset with 8285 low-light instances and 6814 small ones. The improved YOLOX approach offers accurate and efficient detection performance, which can reduce safety incidents on tunnel construction sites. [ABSTRACT FROM AUTHOR]

Safety training effectively addresses the inexperience of and lack of knowledge among construction workers, which are some of the most significant contributors to workplace accidents on construction sites. This paper aims to understand the effectiveness of different extended reality (XR) technologies in imparting important construction safety training to construction workers in a virtual environment compared to conventional classroom training sessions. A group of experts were engaged to understand the most effective learning criteria and the impact of XR visualizations, and their responses were analysed using the interval type-2 fuzzy Delphi (IT2FD) method. Following this, a cohort of engineering students were subjected to construction safety training in traditional, augmented reality (AR) and virtual reality (VR) environments. Their feedback was collected using an online questionnaire and the responses were analysed using the interval type-2 fuzzy analytic hierarchy process (IT2F–AHP). The results revealed that addressing the virtual interface design of the training to maintain the attention of trainees and ensuring the virtual environment's resemblance to the actual site and task were the most important factors in ensuring effective knowledge retention by the trainees. AR visualizations were most effective at imparting knowledge, and their interactive nature allowed trainees to retain the learned knowledge. [ABSTRACT FROM AUTHOR]

Considering a large number of Small and Medium-Scale Contractors (SMSCs) dominating the construction industries of many developing nations and the increasingly high rate of tower crane accidents in the industry, this paper seeks to methodically determine the safety risk factors that are significant in influencing construction site safety, especially on sites where the SMSCs operate tower cranes. The paper will further assess the extent to which each safety risk factor affects safety on construction sites. Data for the study was obtained through a literature search, site visual observations, discussions with site operators, and structured questioning of safety and equipment managers of leading construction companies. The study's findings reveal that the operator's low experience level was the most significant factor influencing construction site safety, particularly when operating tower cranes. This paper systematically investigates the key safety risk factors that influence construction site safety when operating tower cranes. The paper presents a clear methodology for identifying and prioritizing the safety risk factors, which may readily apply to other construction equipment. The findings of this paper are expected to play an important role in promoting and enhancing a safety culture for operating tower cranes in construction sites, particularly the project sites operated by the SMSCs. [ABSTRACT FROM AUTHOR]

• Reviewed 140 articles about Prevention through Design (PtD) in construction. • Identified an increasing trend in PtD publications between 2008 and 2020. • Previous work centers on PtD resources/tools/procedures and technology applications. • Findings provide a basis for future research related to PtD. • Findings provide implications for practitioners adopting PtD and selecting PtD tools. Introduction: The concept of addressing and minimizing construction site safety risks in the early phase of a project has generated research interest, especially since the National Institute for Occupational Safety and Health (NIOSH) launched its national Prevention through Design (PtD) initiative in July 2007. In the last decade, several studies on PtD with differeing goals and methods have been published in construction journals. To date, few systematic examinations of the development and trends associated with PtD research have been conducted in the discipline. Method: This paper presents a study of the latest PtD research trends in construction safety management through analysis of publications in prominent construction journals from 2008 to 2020. Both descriptive and content analyses were conducted based on the number of papers published annually and clusters of topics covered in the papers. Results: The study shows an increasing interest in PtD research in recent years. Research topics covered mainly focus on the perspectives of PtD stakeholders, PtD resources/tools/procedures, and technology applications to facilitate PtD implementation in practice. This review study provides an improved understanding of the state-of-the-art of PtD research in terms of accomplishments and research gaps. The study also compares the findings from journal articles with industry best practices related to PtD to guide future research in this domain. Practical Application: This review study is of significant value to researchers to overcome the limitations of the current PtD studies, and to extend the scope of PtD research, and can be used by industry professionals when considering and selecting appropriate PtD resources/tools in practice. [ABSTRACT FROM AUTHOR]

Recognition of safety leading indicators is considered as an important part of safety management in construction projects to prevent hazardous accidents occurrence. In the available literature, the lack of a comprehensive proactive approach for assessing safety, based on active safety leading indicators is tangible. In this study, BIM and knowledge base are integrated to develop a safety management framework, then, this framework is implemented in a case study to assess its performance. Safety leading indicators are extracted from experts' expertise, documents, and best practice, and then the relationships among safety leading indicators, activities, and their attributes are established; these pieces of knowledge are stored in a safety leading indicator knowledge base. To measure the impacts of these indicators on the project, a framework is developed to integrate the knowledge base and building information modeling (BIM). The developed add-on generates a heat-map to visualize the impacts of the safety leading indicators on a daily basis, and it also produces a textual result sheet. To verify the effectiveness and efficiency of the developed tool a survey from professionals is conducted. This tool provides a way to automatically assess the impacts of the safety leading indicators. Using its results, safety managers and project participants can make important decisions to reduce hazards. The results also indicate that accidents occurring in the construction site dropped by 38% after employing the presented framework. [ABSTRACT FROM AUTHOR]

Manual hazard identification by safety managers in construction has practical challenges because each manager identifies environmental hazards from their perception, which can leave many potential hazards unidentified and consequently lead to accidents at the site. Previous studies have revealed that workers experience loss of body balance (LOB) when exposed to slip, trip, and fall (STF) hazards. This study extended previous studies to identify STF hazards by LOB measurement and collective sensing (i.e., data aggregation) techniques and assumed that STF hazards would cause multiple workers' LOBs in a given location. First, this study developed an approach to assess each worker's exposure to STF hazards by LOB analysis. A waist-worn inertial measurement unit sensor was used to extract features of waist movements, which were mapped into a single value to measure LOB scores using the Mahalanobis distance (MD) metric. As an individual worker is exposed to STF hazards, the MD values become larger than without exposure to STF hazards. The developed approach provided an unweighted average recall of 89.13% (without exposures: 90.30%, and with exposures: 87.96%) for detecting individual workers' exposures to STF hazards in an actual construction site. Then, an approach was developed to visualize the location of STF hazards by allocating multiple workers' LOB scores into each individual's Global Positioning System (GPS) data points. The results showed the feasibility of the developed approach to identify STF hazards, potentially helping to prevent STF accidents at construction sites. [ABSTRACT FROM AUTHOR]

Improving the hazard identification ability of workers is an important way to reduce safety accidents at construction sites. Although previous studies have succeeded in improving hazard identification performance, an important gap is that they consider only two factors, the worker's safety experience and objective environmental conditions, to analyze the impact on hazard identification performance. To fill the above gap, a visual cognitive model of hazard identification was established. Sixteen field scenes were selected to represent construction sites in each environmental condition. Eye-movement data were extracted through eye-tracking experiments, and the differences between experts' and novices' gazes during danger recognition in these scenes were analyzed. The results indicate the following: bright construction sites can significantly improve the correct recognition rate and information processing in hazard identification; tidy construction sites can improve the search efficiency and correct recognition rate of hazard identification; safety experience can improve workers' correct recognition rates and information processing; and reducing distractions can effectively improve the correct identification rate of hazards. Overall, optimal site brightness needs to be further studied to improve the efficiency of hazard search and reduce the distraction effect. This study provides recommendations for the direction of safety training and safety management on site. [ABSTRACT FROM AUTHOR]

Purpose: The research was carried out to statistically evaluate the relationship between the safety measures at the construction sites and the actual and perceived knowledge levels of the employees about these measures. Design/methodology/approach: Face-to-face surveys were conducted with the workers. The survey included some perception-based questions about preventive measures at the construction site, as well as determining the level of awareness of employees on occupational health and safety (OHS) practices. The data were analyzed with descriptive statistical methods and bivariate correlation analysis. Findings: The actual knowledge levels of workers on OHS measures in the workplace is significantly lower than their perceived knowledge levels. However, there is a positive, linear and strong relationship between the actual knowledge levels of the employees about some OHS rules applied in the workplace and the general level of knowledge they perceive about themselves. Some protective measures such as occupational safety expert, OHS board, employee representatives, training and information activities at construction sites positively affect the safety awareness of employees. However, low-frequency and documentation-intensive activities such as risk assessment, emergency activities and periodic controls have no or weak correlations. Originality/value: Perception-based opinions of construction site workers on occupational safety issues are transformed into numerical data and analyzed with a quantitative method. [ABSTRACT FROM AUTHOR]

To effectively mitigate heat risks, it is crucial to pinpoint areas of high vulnerability and assess the severity of heat-related threats to construction workers. This paper advances the understanding of heat risks in construction by mapping the associated risks across time and space to support informed decision-making. This paper presents a framework for heat risk monitoring, enabled by a construction site digital twin. This framework leverages geometric modeling, incorporates real-time weather data from a weather station, and utilizes computational simulations for assessing spatio-temporal heat risks. Its effectiveness was validated through a case study in Stephenville, Texas, USA, where it demonstrated superior fidelity when compared to using the conventional black-globe thermometer. Moreover, the results substantiated that incorporating the spatio-temporal variability of heat risks enhances heat risk surveillance in construction workplaces. This approach offers practical insights into imminent heat-related threats, aiming to prevent potential heat-related accidents in construction. • A digital twin-enabled heat risk monitoring that facilitates the spatio-temporal heat risk analysis. • Geometric modeling and real-time climatic data analysis for computational simulations of the spatio-temporal heat risk. • The case study on a construction site located in Stephenville, Texas, USA, to evaluate the proposed method. • Providing empirical evidence highlighting the importance of monitoring the spatio-temporal heat risk in jobsites. [ABSTRACT FROM AUTHOR]

Computer vision techniques can be used to detect site objects for identifying noncompliances that could lead to safety incidents. However, existing methods are limited in covering diverse hazard scenarios, detecting site objects with imbalanced distributions, and recognizing their intricate attributes to describe their conditions and functionality. To address these gaps, this paper proposes a deep learning-based method for identifying multiple fall-related objects and their associated attributes. The proposed method consists of three submethods: (1) a method for developing relevant datasets by retrieving images from open resources; (2) a method for few-shot object detection, which deals with imbalanced distributions; and (3) a method for attribute recognition to add semantic descriptions to the detected objects. The proposed method achieved an average precision and recall of 88.2% and 79.5% for few-shot object detection and 94.8% and 95.7% for attribute recognition, respectively, which indicates good performance. • Deep learning-based method to detect information for field compliance checking. • Conducts few-shot object detection for objects with imbalanced distribution. • Conducts attribute recognition to add descriptive condition information to objects. • Achieved good performance in extracting site visual information. [ABSTRACT FROM AUTHOR]

There has been a persistent challenge in acquiring sufficient training image data for deep neural networks (DNNs) to enhance safety monitoring on construction sites. Given the prevalence of textual data in the construction sector and the capabilities of multi-modal AI systems, this paper presents the use of text-to-image models to generate training images that capture the relationships between objects involved in construction accidents. Through a systematic prompt design process, a synthetic dataset of 3585 images across 27 hazardous scenarios was generated. The efficacy of this method is demonstrated by the performance of DNN models trained on these virtual images, which achieved a mean Average Precision (mAP) of approximately 64% in object detection and 60% in segmentation tasks. This paper demonstrates the potential of text-to-image models in mitigating the scarcity of training data and enhancing the capability of DNNs to identify potential hazards. • Mitigating the image data scarcity in a construction safety field using synthetic data. • Training DNN models with images synthesized by text-to-image generative models. • DNN models trained with only synthetic data achieved high mAP(%) when tested with real-world images. [ABSTRACT FROM AUTHOR]

Construction is one of the most hazardous industries with high fatal and nonfatal accidents rates. However, many accidents could be prevented by improving workers' safety performance. Numerous factors impact their performance, such as safety culture and attitude, distraction, and personal characteristics. Among these factors, age has been widely cited in past research, but there is no unanimity among researchers regarding its impact on workers' safety performance. Both positive and negative impacts of age on safety performance have been reported in studies, along with several researchers who found no significant difference in safety performance among workers of different ages. To demystify the impact of age on construction workers' safety performance, this research hypothesizes that the relationship between age and safety performance is mediated by other factors such as experience and fatigue. A survey was conducted among 135 randomly selected participants from 38 construction sites in Iran. The survey consisted of three sections, namely demographic information, subjective fatigue assessment, and safety performance measurement. Statistical analysis revealed that the relationship between age and safety performance is mediated by experience and fatigue, explaining the disparity among past research findings. The findings of this study highlight that age does not have a direct impact, but an indirect impact mediated by multiple factors, on workers' safety performance. Future research must consider mediating factors when studying the role of age in workers' safety performance. The results suggest that researchers and practitioners should focus on other factors such as fatigue and safety training, which employers can positively influence. [ABSTRACT FROM AUTHOR]

Because workers' abnormal psychophysiological responses (e.g., high levels of stress and fatigue) are directly or indirectly linked to disorders and accidents at construction sites, monitoring workers' abnormal psychophysiological responses during ongoing work enables preventive interventions, thereby improving their health and safety. As such, wearable biosensors (e.g., wristbands) have been extensively applied with machine-learning models in construction fields as a means of continuous and less-invasive psychophysiological monitoring. However, there is a significant knowledge gap in how to validate machine-learning models that monitor human responses from biosignals. Specifically, despite the importance of generalizability across different people and contexts for psychophysiological monitoring tasks, current validation methods do not ensure different subjects and contexts between training and testing data sets, and thus overestimate the generalization performance of models. To address this issue, the authors propose a new independent subject and context testing method, leave-one-subject-and-context-out cross validation (LOSCOCV), which ensures that training and testing data sets are collected from different subjects and contexts. The proposed LOSCOCV method's generalizability estimation performance was compared with current validation methods through conducting a test wherein machine-learning models were developed to detect construction workers' stress levels from biosignals collected during their ongoing work. The proposed LOSCOCV method showed statistically lower errors in estimating machine-learning models' generalizability than other benchmarks. The results indicate that LOSCOCV is more valid than current validation methods in assessing models' generalizability for tasks that monitor human responses from biosignals. Accurately tracking generalization performance is fundamental to efforts toward advancing the generalizability of models. This study therefore significantly contributes to the field's use of biosensors and machine learning to monitor construction workers' psychophysiological responses—ultimately advancing their health and safety. [ABSTRACT FROM AUTHOR]

Unsafe behaviors of construction workers often lead to construction accidents, while traditional safety monitoring methods have low efficiency and timeliness. Although deep learning has been widely applied in detecting construction site unsafe behaviors, most studies still focus on supervised learning for detecting personal protective equipment use, with less emphasis on worker behaviors. This study developed an unsupervised learning model, Multi-Anomaly GAN, based on GAN with five pseudo anomaly synthesizers to detect unsafe behaviors of construction workers. First, the WeTeam22 dataset was built with tower crane edge scenarios to compensate for the lack of construction worker behavior datasets. After training on WeTeam22, Multi-Anomaly GAN achieved better results in AUC, EER, and F1 score compared to baseline methods. The model effectively identified unsafe behaviors during testing. The study proves the effectiveness of Multi-Anomaly GAN in detecting unsafe construction site behaviors, providing a novel and valid detection scheme for this problem. • An unsupervised Multi-Anomaly GAN is proposed for construction worker unsafe behavior detection. • The WeTeam22 dataset with 394 video samples covering normal and unsafe behaviors is constructed. • Multi-Anomaly GAN combines temporal information and multiple pseudo anomaly synthesizers to improve model performance. • Multi-Anomaly GAN outperforms the baseline model in AUC, EER, and F1 score metrics on both single and multi-person datasets. • Ablation studies demonstrate combining diverse modules enhances model generalization ability. [ABSTRACT FROM AUTHOR]

High occupational injury and fatality rate in the construction industry is a serious global concern. Recognizing AI as a solution to enhance safety performance, this study reviews 153 papers to assess and categorize current AI applications in construction, focusing on text, visual, and audio data, while also identifying challenges and future research opportunities. Real-time monitoring, hazard detection, and information extraction are identified as key areas where AI is applied, with a notable reliance on deep neural networks, object recognition, and Natural Language Processing. The review highlights major challenges, including the need for high-quality data management, semantic feature representation, and occluded object detection. Additionally, it underscores the untapped potential of audio-based AI and the advancements possible with Large Language Models for text interpretation. The findings emphasize the need for integrated, multi-faceted AI systems and advocate for responsible AI deployment to mitigate safety risks on construction sites. [Display omitted] • Poor Safety remains a global challenge for construction. • AI emerges as an effective approach for enhancing safety. • Study reviews and categorizes AI applications in construction safety. • The key insights, opportunities, and challenges for AI integration are identified. [ABSTRACT FROM AUTHOR]

Tower cranes (TCs) are vital equipment highly sought after on construction sites due to their efficiency in handling and lifting heavy loads. Nevertheless, the use of TCs on construction sites is riddled with significant safety issues, resulting in numerous accidents across the globe. This study uniquely focuses on the emerging tower crane safety technologies (TCST) field and makes vital contributions by investigating and analyzing TCST research. It aims to explore knowledge gaps and propose future research directions through a systematic review. The uniqueness of this study is its comprehensive examination of TCST, which encompasses not only academic research but also industrial technologies and products. TCST has been categorized based on their purposes and specific aspects of crane management, leading to four key categories: (1) proactive preconstruction crane management technologies; (2) monitoring technologies during construction; (3) anti-collision technologies during construction; and (4) stability control technologies during construction. This study makes a threefold contribution. First, it identifies six crucial knowledge gaps, three in academia and three in the industrial sector. These gaps relate to data completeness, data scope, real-world application, post-construction dismantling, accuracy and data reliability, and data security. Second, it outlines future research opportunities in both academic and industrial contexts, providing a clear path to address these gaps and improve tower crane (TC) operation safety and efficiency. Lastly, it delivers valuable insights to industry practitioners by presenting the latest TCST applications in real-world scenarios, thereby promoting safer and more effective construction practices. • Tower cranes enhance construction efficiency but pose safety challenges. • Comprehensive systematic review of TCST conducted in academia and industry. • Four TCST categories identified: preconstruction, monitoring, anti-collision, stability. • A total of six critical knowledge gaps found in academia and industry. • Offers insights and future research directions for safer construction practices. [ABSTRACT FROM AUTHOR]