Search results

Construction workers are frequently exposed to safety hazards on sites. Wearable sensing systems (e.g. wearable inertial measurement units (WIMUs), wearable insole pressure system (WIPS)) have been used to collect workers' gait patterns for distinguishing safety hazards. However, the performance of measuring WIPS-based gait parameters for identifying safety hazards as compared to a reference system (i.e. WIMUs) has not been studied. Therefore, this study examined the validity and reliability of measuring WIPS-based gait parameters as compared to WIMU-based gait parameters for distinguishing safety hazards in construction.

Five fall-risk events were conducted in a laboratory setting, and the performance of the proposed approach was assessed by calculating the mean difference (MD), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE) and intraclass correlation coefficient (ICC) of five gait parameters.

Comparable results of MD, MAE, MAPE and RMSE were found between WIPS-based gait parameters and the reference system. Furthermore, all measured gait parameters had validity (ICC = 0.751) and test-retest reliability (ICC = 0.910) closer to 1, indicating a good performance of measuring WIPS-based gait parameters for distinguishing safety hazards.

Overall, this study supports the relevance of developing a WIPS as a noninvasive wearable sensing system for identifying safety hazards on construction sites, thus highlighting the usefulness of its applications for construction safety research.

This is the first study to examine the performance of a wearable insole pressure system for identifying safety hazards in construction.

Since construction workers often need to carry various types of loads in their daily routine, they are at risk of sustaining musculoskeletal injuries. Additionally, carrying a load during walking may disturb their walking balance and lead to fall injuries among construction workers. Different load carrying techniques may also cause different extents of physical exertion. Therefore, the purpose of this paper is to examine the effects of different load-carrying techniques on gait parameters, dynamic balance, and physiological parameters in asymptomatic individuals on both stable and unstable surfaces.

Fifteen asymptomatic male participants (mean age: 31.5 ± 2.6 years) walked along an 8-m walkway on flat and foam surfaces with and without a load thrice using three different techniques (e.g. load carriage on the head, on the dominant shoulder, and in both hands). Temporal gait parameters (e.g. gait speed, cadence, and double support time), gait symmetry (e.g. step time, stance time, and swing time symmetry), and dynamic balance parameters [e.g. anteroposterior and mediolateral center of pressure (CoP) displacement, and CoP velocity] were evaluated. Additionally, the heart rate (HR) and electrodermal activity (EDA) was assessed to estimate physiological parameters.

The gait speed was significantly higher when the load was carried in both hands compared to other techniques (Hand load, 1.02 ms vs Head load, 0.82 ms vs Shoulder load, 0.78 ms). Stride frequency was significantly decreased during load carrying on the head than the load in both hands (46.5 vs 51.7 strides/m). Step, stance, and swing time symmetry were significantly poorer during load carrying on the shoulder than the load in both hands (Step time symmetry ration, 1.10 vs 1.04; Stance time symmetry ratio, 1.11 vs 1.05; Swing time symmetry ratio, 1.11 vs 1.04). The anteroposterior (Shoulder load, 17.47 mm vs Head load, 21.10 mm vs Hand load, −5.10 mm) and mediolateral CoP displacements (Shoulder load, −0.57 mm vs Head load, −1.53 mm vs Hand load, −3.37 ms) significantly increased during load carrying on the shoulder or head compared to a load in both hands. The HR (Head load, 85.2 beats/m vs Shoulder load, 77.5 beats/m vs No load, 69.5 beats/m) and EDA (Hand load, 14.0 µS vs Head load, 14.3 µS vs Shoulder load, 14.1 µS vs No load, 9.0 µS) were significantly larger during load carrying than no load.

The findings suggest that carrying loads in both hands yields better gait symmetry and dynamic balance than carrying loads on the dominant shoulder or head. Construction managers/instructors should recommend construction workers to carry loads in both hands to improve their gait symmetry and dynamic balance and to lower their risk of falls.

The potential changes in gait and balance parameters during various load carrying methods will aid the assessment of fall risk in construction workers during loaded walking. Wearable insole sensors that monitor gait and balance in real-time would enable safety managers to identify workers who are at risk of falling during load carriage due to various reasons (e.g. physical exertion, improper carrying techniques, fatigue). Such technology can also empower them to take the necessary steps to prevent falls.

This is the first study to use wearable insole sensors and a photoplethysmography device to assess the impacts of various load carrying approaches on gait parameters, dynamic balance, and physiological measures (i.e. HR and EDA) while walking on stable and unstable terrains.

High rate of accidents continue to plague the construction industry. The advancements in safety technologies can ameliorate construction health and safety (H&S). This paper aims to explore the use of emerging technologies as an effective solution for improving safety in construction projects.

Following a detailed literature review, a questionnaire survey was developed encompassing ten technologies for safety management and ten safety enablers using technologies in construction. A total of 133 responses were gathered from Malaysian construction practitioners. The collected quantitative data were subjected to descriptive and inferential statistical analyses to determine the meaningful relationships between the variables.

Findings revealed that the most effective emerging technologies for safety management are: building information modelling (BIM), wearable safety technologies and robotics and automation (R&A). The leading safety enablers are related to improve hazard identification, reinforce safety planning, enhance safety inspection, enhance safety monitoring and supervision and raise safety awareness.

Safety is immensely essential in transforming the construction industry into a robustly developed industry with high safety and quality standards. The adoption of safety technologies in construction projects can drive the industry towards the path of Construction 4.0.

The construction industry has historically been slow to adopt new technology. This study contributes to advancing the body of knowledge in the area of incorporating emerging technologies to further construction safety science and management in the context of the developing world. By taking cognisance of the pertinent emerging technologies for safety management and the safety enablers involved, construction safety can be enhanced using integrated technological solutions.

This pragmatic research paper aims to unravel the smart vision-based method (SVBM), an AI program to correlate the computer vision (recorded and live videos using mobile and embedded cameras) that aids in manual lifting human pose deduction, analysis and training in the construction sector.

Using a pragmatic approach combined with the literature review, this study discusses the SVBM. The research method includes a literature review followed by a pragmatic approach and lab validation of the acquired data. Adopting the practical approach, the authors of this article developed an SVBM, an AI program to correlate computer vision (recorded and live videos using mobile and embedded cameras).

Results show that SVBM observes the relevant events without additional attachments to the human body and compares them with the standard axis to identify abnormal postures using mobile and other cameras. Angles of critical nodal points are projected through human pose detection and calculating body part movement angles using a novel software program and mobile application. The SVBM demonstrates its ability to data capture and analysis in real-time and offline using videos recorded earlier and is validated for program coding and results repeatability.

Literature review methodology limitations include not keeping in phase with the most updated field knowledge. This limitation is offset by choosing the range for literature review within the last two decades. This literature review may not have captured all published articles because the restriction of database access and search was based only on English. Also, the authors may have omitted fruitful articles hiding in a less popular journal. These limitations are acknowledged. The critical limitation is that the trust, privacy and psychological issues are not addressed in SVBM, which is recognised. However, the benefits of SVBM naturally offset this limitation to being adopted practically.

The theoretical and practical implications include customised and individualistic prediction and preventing most posture-related hazardous behaviours before a critical injury happens. The theoretical implications include mimicking the human pose and lab-based analysis without attaching sensors that naturally alter the working poses. SVBM would help researchers develop more accurate data and theoretical models close to actuals.

By using SVBM, the possibility of early deduction and prevention of musculoskeletal disorders is high; the social implications include the benefits of being a healthier society and health concerned construction sector.

Human pose detection, especially joint angle calculation in a work environment, is crucial to early deduction of muscoloskeletal disorders. Conventional digital technology-based methods to detect pose flaws focus on location information from wearables and laboratory-controlled motion sensors. For the first time, this paper presents novel computer vision (recorded and live videos using mobile and embedded cameras) and digital image-related deep learning methods without attachment to the human body for manual handling pose deduction and analysis of angles, neckline and torso line in an actual construction work environment.

Fall accidents can cause casualties and economic losses in the construction industry. Fall portents, such as loss of balance (LOB) and sudden sways, can result in fatal, nonfatal or attempted fall accidents. All of them are worthy of studying to take measures to prevent future accidents. Detecting fall portents can proactively and comprehensively help managers assess the risk to workers as well as in the construction environment and further prevent fall accidents.

This study focused on the postures of workers and aimed to directly detect fall portents using a computer vision (CV)-based noncontact approach. Firstly, a joint coordinate matrix generated from a three-dimensional pose estimation model is employed, and then the matrix is preprocessed by principal component analysis, K-means and pre-experiments. Finally, a modified fusion K-nearest neighbor-based machine learning model is built to fuse information from the x, y and z axes and output the worker's pose status into three stages.

The proposed model can output the worker's pose status into three stages (steady–unsteady–fallen) and provide corresponding confidence probabilities for each category. Experiments conducted to evaluate the approach show that the model accuracy reaches 85.02% with threshold-based postprocessing. The proposed fall-portent detection approach can extract the fall risk of workers in the both pre- and post-event phases based on noncontact approach.

First, three-dimensional (3D) pose estimation needs sufficient information, which means it may not perform well when applied in complicated environments or when the shooting distance is extremely large. Second, solely focusing on fall-related factors may not be comprehensive enough. Future studies can incorporate the results of this research as an indicator into the risk assessment system to achieve a more comprehensive and accurate evaluation of worker and site risk.

The proposed machine learning model determines whether the worker is in a status of steady, unsteady or fallen using a CV-based approach. From the perspective of construction management, when detecting fall-related actions on construction sites, the noncontact approach based on CV has irreplaceable advantages of no interruption to workers and low cost. It can make use of the surveillance cameras on construction sites to recognize both preceding events and happened accidents. The detection of fall portents can help worker risk assessment and safety management.

Existing studies using sensor-based approaches are high-cost and invasive for construction workers, and others using CV-based approaches either oversimplify by binary classification of the non-entire fall process or indirectly achieve fall-portent detection. Instead, this study aims to detect fall portents directly by worker's posture and divide the entire fall process into three stages using a CV-based noncontact approach. It can help managers carry out more comprehensive risk assessment and develop preventive measures.

Recognizing construction workers' activities is critical for on-site performance and safety management. Thus, this study presents the potential of automatically recognizing construction workers' actions from activations of the erector spinae muscles.

A lab study was conducted wherein the participants (n = 10) performed rebar task, which involved placing and tying subtasks, with and without a wearable robot (exoskeleton). Trunk muscle activations for both conditions were trained with nine well-established supervised machine learning algorithms. Hold-out validation was carried out, and the performance of the models was evaluated using accuracy, precision, recall and F1 score.

Results indicate that classification models performed well for both experimental conditions with support vector machine, achieving the highest accuracy of 83.8% for the “exoskeleton” condition and 74.1% for the “without exoskeleton” condition.

The study paves the way for the development of smart wearable robotic technology which can augment itself based on the tasks performed by the construction workers.

This study contributes to the research on construction workers' action recognition using trunk muscle activity. Most of the human actions are largely performed with hands, and the advancements in ergonomic research have provided evidence for relationship between trunk muscles and the movements of hands. This relationship has not been explored for action recognition of construction workers, which is a gap in literature that this study attempts to address.

Construction safety management (CSM) has been intensively researched in the last four decades but hitherto mostly aimed at understanding root causes of accidents, recommending preventive measures and evaluating their implications. However, a systematic effort to present a comprehensive picture of construction safety research is hardly witnessed. Therefore, the study aims to investigate construction safety research contributors, ontologies, themes, evolution, emerging trends and future directions using quantitative and qualitative content analysis.

A total of 877 journal articles were extracted using preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines and Scopus literature database and were analyzed using VOSviewer and Nvivo tools to present a comprehensive picture of the CSM body of knowledge.

The study observed rapid growth in construction safety research with contributions from various countries, organizations and researchers. This study identified 3 research levels, 8 project phases, 10 project types, 6 research instruments and 19 research data sources along with their usage in the research domain. Further, the study identified 13 emerging research themes, 4 emerging research trends and an observed paradigm shift from reactive to proactive CSM approach.

The comprehensive study on the emerging themes and findings on proactive CSM has strategic implications to practice to incorporate safety. The identified future directions can assist researchers in bridging the existing gaps and strengthening emerging research trends.

The study presents a comprehensive picture of the CSM body of knowledge using the content analysis approach that was absent in past literature and opened future research avenues.

Work-related musculoskeletal disorders constitute a severe problem in the construction industry. Workers' lower backs are often affected by heavy or repetitive lifting and prolonged awkward postures. Exoskeletal interventions are effective for tasks involving manual lifting and repetitive movements. This study aims to examine the potential of a postural-assist exoskeleton (a passive exoskeleton) for manual material handling tasks.

From an experimental observation of participants, the effects of postural-assist exoskeleton on tasks and workers were measured. Associated benefits of the exoskeleton were assessed through task performance, range of motion and discomfort.

Findings suggest that the exoskeleton influenced discomfort significantly, however range of motion decreased with lifting tasks. The reduced back flexion and increased hip flexion were also indicatives of the participants' responsiveness to the feedback from the exoskeleton. In addition, task completion time increased by 20%, and participants' back pain did not reduce.

The work tasks were performed in a controlled laboratory environment and only wearable inertia measurement units (IMUs) were used to assess the risk exposures of the body parts.

This study opens a practical pathway to human-exoskeleton integration, artificial regeneration or enablement of impaired workforce and a window toward a new order of productivity scaling. Results from this study provide preliminary insights to designers and innovators on the influence of postural assist exoskeleton on construction work. Project stakeholders can be informed of the suitability of the postural assist exoskeletons for manual material handling tasks.

Little has been reported on the benefits and impact of exoskeletons on tasks' physical demands and construction workers' performance. This study adds value to the existing literature, in particular by providing insights into the effectiveness and consequences of the postural-assist exoskeleton for manual material handling tasks.

Carpenters are constantly vulnerable to musculoskeletal disorders. Their work consists of subtasks that promote nonfatal injuries and pains that affect different body segments. The purpose of this study is to examine ergonomic exposures of carpentry subtasks involved in floor framing, how they lead to musculoskeletal injuries, and how preventive and protective interventions around them can be effective.

Using wearable sensors, this study characterizes ergonomic exposures of carpenters by measuring and analyzing body movement data relating to major subtasks in carpentry flooring work. The exposures are assessed using Postural Ergonomic Risk Assessment classification, which is based on tasks involving repetitive subtasks and nonstatic postures.

The findings of this paper suggest severe risk impositions on the trunk, shoulder and elbow as a result of the measuring and marking and cutting out vent locations, as well as in placing and nailing boards into place.

Because of the type and size of wearable sensor used, only results of risk exposures of four body-parts are presented.

This study draws insights on how to benchmark trade-specific measurement of work-related musculoskeletal disorders. Safety efforts can be targeted toward these risk areas and subtasks. Specifically, results from these will assist designers and innovators in designing effective and adaptable protective interventions and safety trainings.

Extant studies have failed to provide adequate evidence regarding the relationships between subtasks and musculoskeletal disorders; they have only mimicked construction tasks through laboratory experimental scenarios. This study adds value to the existing literature, in particular by providing insights into hazards associated with floor carpentry subtasks.

The outbreak of the pandemic makes it more difficult to manage the safety or health of construction workers in infrastructure construction. Risk events in construction workers' material handling tasks are highly relevant to workers' work-related musculoskeletal disorders. However, there are still many problems to be resolved in recognizing risk events accurately. The purpose of this research is to propose an automatic and non-invasive recognition method for construction workers in material handling tasks during the pandemic based on smartphone and machine learning.

This research proposes a method to recognize and classify four different risk events by collecting specific acceleration and angular velocity patterns through built-in sensors of smartphones. The events were simulated with anterior handling and shoulder handling methods in the laboratory. After data segmentation and feature extraction, five different machine learning methods are used to recognize risk events and the classification performances are compared.

The classification result of the shoulder handling method was slightly better than the anterior handling method. By comparing the accuracy of five different classifiers, cross-validation results showed that the classification accuracy of the random forest algorithm was the highest (76.71% in anterior handling method and 80.13% in shoulder handling method) when the window size was 0.64 s.

Less attention has been paid to the risk events in workers' material handling tasks in previous studies, and most events are recorded by manual observation methods. This study provided a simple and objective way to judge the risk events in manual material handling tasks of construction workers based on smartphones, which can be used as a non-invasive way for managers to improve health and labor productivity during the pandemic.