Inferring workplace safety hazards from the spatial patterns of workers’ wearable data

Hazard identification in construction typically requires safety managers to manually inspect an area. However, current approach is very limited due to the dynamic nature of construction sites and the subjective nature of human perception. Using wearable inertial measurement units (WIMU), previous literatures revealed the relationship between a worker’s abnormal gait patterns and the existence of slip, trip and fall (STF) hazards. Though the prior work demonstrated the strong correlation between STF hazards and abnormal gait patterns, automated hazard identification is a challenging issue due to the lack of knowledge on decision threshold on identifying hazards under different construction environments. To fill the research gap, this study developed an approach that can automatically identify the STF hazards without knowledge about thresholds by investigating the spatial associations of workers’ abnormal gait occurrences. An experiment simulating a brick installation was performed with different types of STF hazards (e.g., poor housekeeping), and results demonstrate the feasibility of STF hazards identification with the developed approach. The results highlight the opportunities of revealing potential accident hotspots via an efficient and semi-automated methodology, which overcomes many of the limitations in current practice.     

Biomechanical model for energy consumption in manual load carrying on Indian farms

This study pertains to manually carrying load in Indian farms. Different modes are adopted for carrying farm inputs and farm produce; head, shoulder and back. A biomechanical model was developed and validated to predict metabolic energy consumption for carrying load manually by varying modes, loads and ground inclinations. The model developed incorporated operator, ground inclination and load parameters. Operator parameters included human efficiency, body weight and height of the worker. Load parameters considered were weight of load and mode of load carrying. Experiments on three modes (head, back and shoulder) and three loads (10, 15, 20 kg load) at three slopes (0, 5, 10%) were conducted in a laboratory set up. Twelve farm workers (six males and six females) working in local farms participated in the study. The model closely predicted energy and rest requirement for load carrying in different modes.     

Analysis of worker strategies: A comprehensive understanding for the prevention of work related musculoskeletal disorders

By documenting the strategies developed by food processing workers to manage their musculoskeletal pain and discomfort in order to remain on the job, the present article seeks to increase awareness of a different “way of approaching” WMSDs inspired by the ergonomic approach centred on work activity analysis. Based on a mixed methods approach, an ergonomic work activity study combined with a multiple case study was conducted. Sixteen female seafood-processing workers were followed up during two consecutive work seasons using a range of interviews as well as observations of work activity throughout the entire study. A large variety of musculoskeletal pain management strategies developed by those workers to remain on the job were identified. This identification and the process of categorizing the strategies led to the development of a framework for studying worker strategies. The mixed methods approach made it possible to better pinpoint and understand obstacles to the development of workplace strategies and then identify avenues for change to improve working conditions.Relevance to industryThe framework constitutes a valuable contribution for the prevention of WMSDs by representing a methodological tool for documenting worker strategies. Very few tools of this kind are currently available for practitioners and researchers. In becoming aware of the existence of such coping strategies, companies can gain a better understanding of the difficulties workers have to cope with.     

Criteria for the reintegration in the workforce of workers with musculoskeletal disorders of the upper limbs,based on preliminary practical experience

This paper presents a preliminary study on the return to the workforce of employees with WMSDs of the upper limbs, and their reallocation to jobs with ‘low exposure’. The study, which is still underway, involves a large engineering firm and includes some 100 workers affected by WMSDs. The trial involved: providing a definition of the criteria for characterizing ‘accommodating’ jobs (i.e. frequency of action < 20 actions/min; virtual absence of other risk factors such as force, awkward posture, inadequate pauses, etc.); effectively identifying jobs meeting such criteria (or jobs which, with minimal modifications, could be made suitable); classifying WMSD workers according to the type and severity of the disorder; matching WMSD workers with the jobs best suited to them; specific training for the workers and their supervisors; carrying out a follow-up of the return of WMSD workers to the workforce in organizational terms (i.e. the need for further modifications to equipment or procedures) and clinical terms (i.e. symptom patterns, acceptability of the condition). The preliminary results, 6–12 months after the start of the trial, are extremely encouraging, and show that when workers return to the workforce in jobs that fully meet defined criteria, a significant prevalence of ‘improvements’ are reported among the workers involved. The investigation will need to be extended but it already shows quite convincingly that it is possible for workers with what can be described as a ‘reduced working capacity’ to remain ‘productive’ (albeit in jobs featuring a lower exposure potential than the acceptable threshold for ‘healthy’ workers).     

Ergonomic assessment of office worker postures using 3D automated joint angle assessment

Sedentary activity and static postures are associated with work-related musculoskeletal disorders (WMSDs) and worker discomfort. Ergonomic evaluation for office workers is commonly performed by experts using tools such as the Rapid Upper Limb Assessment (RULA), but there is limited evidence suggesting sustained compliance with expert’s recommendations. Assessing postural shifts across a day and identifying poor postures would benefit from automation by means of real-time, continuous feedback. Automated postural assessment methods exist; however, they are usually based on ideal conditions that may restrict users’ postures, clothing, and hair styles, or may require unobstructed views of the participants. Using a Microsoft Kinect camera and open-source computer vision algorithms, we propose an automated ergonomic assessment algorithm to monitor office worker postures, the 3D Automated Joint Angle Assessment, 3D-AJA. The validity of the 3D-AJA was tested by comparing algorithm-calculated joint angles to the angles obtained from manual goniometry and the Kinect Software Development Kit (SDK) for 20 participants in an office space. The results of the assessment show that the 3D-AJA has mean absolute errors ranging from 5.6° ± 5.1° to 8.5° ± 8.1° for shoulder flexion, shoulder abduction, and elbow flexion relative to joint angle measurements from goniometry. Additionally, the 3D-AJA showed relatively good performance on the classification of RULA score A using a Random Forest model (micro averages F1-score = 0.759, G-mean = 0.811), even at high levels of occlusion on the subjects’ lower limbs. The results of the study provide a basis for the development of a full-body ergonomic assessment for office workers, which can support personalized behavior change and help office workers to adjust their postures, thus reducing their risks of WMSDs.     

Forest harvesting in rural properties: Risks and worsening to the worker’s health under the ergonomics approach

Through an ergonomic approach, this study aimed to evaluate whether workers involved in forest harvesting activities in rural properties are subject to the development of work-related diseases, as well as their consequences. A cross-sectional study with 267 forest workers in rural properties in the Brazilian Central region was used. The following evaluations were performed for each of the activities (felling, delimbing, tracing, manual extraction and manual loading): physical workload evaluation; biomechanical evaluation; risk of repetitive strain injuries/work-related musculoskeletal disorders; environmental noise and vibration factors, where relevant, and thermal overload through the Wetbulb Globe Temperature index. The results showed that in general the physical workload was very high, exceeding the cardiovascular load limits and adding to the need for work reorganization. All activities exposed workers to serious and imminent risks of developing injuries to the spine and lower limbs. Likewise, in general the risk of the appearance of RSI/WMSDs was very high for all activities evaluated. Such results are due to the combination of organizational work factors and factors of the work environment such as exposure to bad weather, uneven terrain, lifting and handling loads above tolerable limits, excessive noise and thermal overload. All of this allows to conclude that ergonomic risks and workers’ health hazards in forest harvesting in rural properties are latent and very worrying, and that these workers are exposed to a form of labor exploitation that invariably leads to physical and emotional exhaustion and therefore to their decreased labor capacity and useful working life.     

Real-time construction worker posture analysis for ergonomics training

Construction activities performed by workers are usually repetitive and physically demanding. Execution of such tasks in awkward postures can strain their body parts and can result in fatigue, injuries or in severe cases permanent disabilities. In view of this, it is essential to train workers, before the commencement of any construction activity. Furthermore, traditional worker monitoring methods are tedious, inefficient and are carried out manually whereas, an automated approach, apart from monitoring, can yield valuable information concerning work-related behavior of worker that can be beneficial for worker training in a virtual reality world. Our research work focuses on developing an automated approach for posture estimation and classification using a range camera for posture analysis and categorizing it as ergonomic or non-ergonomic. Using a range camera, first we classify worker’s pose to determine whether a worker is ‘standing’, ‘bending’, ‘sitting’, or ‘crawling’ and then estimate the posture of the worker using OpenNI middleware to get the body joint angles and spatial locations. A predefined set of rules is then formulated to use this body posture information to categorize tasks as ergonomic or non-ergonomic.     

Heavy load carrying and musculoskeletal health: An exploratory study of biomechanical risk factors among sand miners in Pokhara,Kaski District,Nepal

BackgroundTrends in urbanization contribute to the growing global demand for raw construction materials. The health effects of load carrying among occupational groups that mine and carry sand and stone used for construction of roads and buildings remains poorly understood.MethodsWe conducted an exploratory cross-sectional study among a convenience sample of sand miners working at an excavation site on the Seti River in Pokhara, Nepal. Load carrying weight, duration, and frequency were used to categorize miners as having “low” or “high” load-carrying exposures. Musculoskeletal disorders (MSDs) were identified using self-reported symptoms of moderate to severe musculoskeletal pain, as well as physical examinations.ResultsThe average loads carried by female and male sand miners weighed 66 kg and 87 kg, respectively. Among all participants (N = 42), 45% reported moderate to severe musculoskeletal pain in at least one body region and 16 (38%) had MSDs identified using specified case criteria. The prevalence of MSDs was lower among miners carrying, on average, heavier loads compared to those carrying lighter loads (OR = 0.18; 95% CI: 0.04, 0.7), possibly indicative of the healthy worker survival effect. Miners carrying loads for longer durations had higher odds of MSDs compared with those carrying for shorter durations.ConclusionThis study has provided data on the extraordinary loads carried by sand miners in Nepal and preliminary evidence of health impacts associated with these loads. However, larger epidemiologic studies are needed to justify action to protect the health and safety of these unrecognized and understudied groups.     

Prevalence of work-related musculoskeletal symptoms among grocery workers

Work-related musculoskeletal disorders (WMSDs) affect all sectors of the working population, and grocery workers have especially high rates. Although the incidence of WMSDs among any worker population can be estimated from workers' compensation claims, musculoskeletal symptom surveys can be used as a proxy estimate of WMSDs. The purposes of this cross-sectional study were to describe the prevalence of work-related musculoskeletal symptoms in grocery store employees from many different departments, and to determine the association between exposure to physical risk factors and presence of symptoms. Study participants (N = 254) were grocery store workers from five different stores in a medium sized grocery chain. Participants completed a self-administered survey consisting of demographic information and job history; the modified Nordic Questionnaire (MNQ); and physical component (PCS) and mental component (MCS) summary measures of the SF-36v2^®. Rodgers Muscle Fatigue Analysis (Rodgers) was used to assess exposure to physical risk factors in the most difficult tasks in certain store departments. Prevalence of musculoskeletal symptoms was estimated for each body region and for various subgroups, and multivariable logistic regression analysis was used to identify independent predictors of presence of musculoskeletal symptoms. Approximately 78% of grocery store workers reported work-related musculoskeletal symptoms in at least one body region, with most workers complaining of low back and feet symptoms. The high prevalence of foot symptoms has not been previously reported for this population. Approximately 11% of employees missed work because of symptoms and 25% sought medical care for symptoms. There were no differences among Rodgers rating groups for proportions reporting symptoms. SF-36v2^® scores were inconsequential predictors for musculoskeletal symptoms. Gender and age were both significant predictors of symptoms, and age predicted healthcare utilization. These findings are relevant to the grocery industry in order to target WMSD preventive interventions to specific body regions for high-risk activities within a grocery store position.     

Low back injury risks during construction with prefabricated (panelised) walls: effects of task and design factors

New technology designed to increase productivity in residential construction may exacerbate the risk of work-related musculoskeletal disorders (WMSDs) among residential construction workers. Of interest here are panelised (prefabricated) wall systems (or panels) and facilitating an ongoing effort to provide proactive control of ergonomic exposures and risks among workers using panels. This study, which included 24 participants, estimated WMSD risks using five methods during common panel erection tasks and the influences of panel mass (sheathed vs. unsheathed) and size (wall length). WMSD risks were fairly high overall; e.g. 34% and 77% of trials exceeded the ‘action limits’ for spinal compressive and shear forces, respectively. Heavier (sheathed) panels significantly increased risks, although the magnitude of this effect differed with panel size and between tasks. Higher levels of risk were found in tasks originating from ground vs. knuckle height. Several practical recommendations based on the results are discussed.

Statement of Relevance:Panelised wall systems have the potential to increase productivity in residential construction, but may result in increased worker injury risks. Results from this study can be used to generate future panel design and construction processes that can proactively address WMSD risks.     

Machine learning-based identification and classification of physical fatigue levels: A novel method based on a wearable insole device

Construction is known for being a labor-intensive and risky industry. Within various occupational settings such as construction, physical fatigue is an underlying health condition that may lead to musculoskeletal disorders and fall-related injuries. Identifying a worker's physical fatigue could enable safety managers to mitigate fatigue-related injuries and improve workplace operations. However, current physical fatigue assessment and identification methods include subjective, physiological, biomechanical, and computer vision approaches, which may be unreliable, intrusive, and require extensive post-processing, thus, rendering them impractical for continuous monitoring of workers' movements and automated identification of physical fatigue. Given the above, this study aims to utilize a wearable insole device to identify and classify physical fatigue levels in construction workers. Ten asymptomatic subjects were recruited to perform a fatiguing manual rebar tying activity in a laboratory setting. Borg's rating of perceived exertion (RPE) was applied as a subjective measure for collecting the levels of physical fatigue of each subject. Three sub-classification problems for identifying physical fatigue levels (i.e., PFL1, PFL2, and PFL3) were assessed. Numerous features were evaluated from the collected data samples after data segmentation. The classification performance of supervised machine learning algorithms was evaluated at a sliding window of 2.56 s. Our results from 10-fold cross-validation show an accuracy of 86% for the Random Forest (RF) algorithm, indicating the best performance among other algorithms. In addition, precision, recall, specificity, and F1-score metrics of the RF algorithm were between 52.63% and 82.62%, 52.63%–84.32%, 89.60%–92.33%, and 52.63%–83.46%, respectively. These results indicate that data samples such as acceleration and plantar pressure acquired from a wearable insole device are reliable for identifying and classifying physical fatigue levels in construction workers. In summary, this study would contribute to providing a proactive physical fatigue assessment method and guidelines for early identification of physical fatigue in construction.     

Legal system and its effect for prevention of work-related musculoskeletal disorders in Korea

This study aims to introduce the legislation of occupational safety and health regulations for prevention of WMSDs in Korea and investigate its effect by showing an ergonomic intervention effort in a major motor company. In Korea, WMSDs incidence rates had increased from 1999 to 2003, and it is noted that its increment jumped rapidly in 2002 and 2003. The Korean government established a law prescribing employers’ duty of preventing WMSDs in 2002, which began effective in July, 2003. Following the legislation, all employers should execute the examination of WMSDs risk factors for the eleven designated tasks every three years. In addition to this legal obligation, some large companies voluntarily established an ergonomic intervention program by carrying out in-depth assessments for stressful tasks using OWAS, RULA, NLE, etc. We introduce a major motor company case to illustrate the industry’s activities of fulfilling the legislative requirement and of performing ergonomic assessments. Thanks to Korean government and industry’s effort for prevention of WMSDs, the incidence rates of WMSDs have continually decreased from the year of 2004, right after the year when the WMSDs-related regulation was enforced.

Relevance to industry

In spite of booming of information technology industries and automation of manufacturing processes in Korea, many workers are still exposed to the risk of WMSDs including awkward postures, stressful force exertions, repetitive motions in manufacturing and agriculture industries. WMSDs cases alone constitute 43.1% of occupational diseases in Korea and the industry’s effort of ergonomic intervention of WMSDs becomes a major issue to both the management and the labor union.     

Low back injury risks during construction with prefabricated (panelised) walls: effects of task and design factors

New technology designed to increase productivity in residential construction may exacerbate the risk of work-related musculoskeletal disorders (WMSDs) among residential construction workers. Of interest here are panelised (prefabricated) wall systems (or panels) and facilitating an ongoing effort to provide proactive control of ergonomic exposures and risks among workers using panels. This study, which included 24 participants, estimated WMSD risks using five methods during common panel erection tasks and the influences of panel mass (sheathed vs. unsheathed) and size (wall length). WMSD risks were fairly high overall; e.g. 34% and 77% of trials exceeded the 'action limits' for spinal compressive and shear forces, respectively. Heavier (sheathed) panels significantly increased risks, although the magnitude of this effect differed with panel size and between tasks. Higher levels of risk were found in tasks originating from ground vs. knuckle height. Several practical recommendations based on the results are discussed. STATEMENT OF RELEVANCE: Panelised wall systems have the potential to increase productivity in residential construction, but may result in increased worker injury risks. Results from this study can be used to generate future panel design and construction processes that can proactively address WMSD risks.     

Vibration of portable orbital sanders and its impact on the development of work-related musculoskeletal disorders in the furniture industry

The wood furniture industry has a strong presence in Canada, where it employs over 100,000 workers. Because of the extensive number of manual tasks required in this industry, several studies have been undertaken to characterize the health and safety risk factors to which these workers are exposed, such as awkward postures, repetitive movements and the application of undue force. However, very little research has been done on workers’ exposure to vibration from portable orbital sanders, one of the most common tools used in this industry. Vibration is responsible for a specific occupational disease called vibration syndrome, but is also recognized as a risk factor that increases the prevalence of more common work-related musculoskeletal disorders (WMSDs). This study proposed to determine the level of vibration to which sanders of furniture parts are exposed, and to analyze its impact on the risk of WMSDs. The results show that the level of vibration to which the workers are exposed is well above acceptable levels defined by recognized standards and directives and that this vibration is combined with many other risk factors, thus representing a risk for the development of WMSDs.     

Dutch Musculoskeletal Questionnaire: description and basic qualities

A questionnaire (‘Dutch Musculoskeletal Questionnaire’, DMQ) for the analysis of musculoskeletal workload and associated potential hazardous working conditions as well as musculoskeletal symptoms in worker populations is described and its qualities are explored using a database of 1575 workers in various occupations who completed the questionnaire. The 63 questions on musculoskeletal workload and associated potentially hazardous working conditions can be categorized into seven indices (force, dynamic and static load, repetitive load, climatic factors, vibration and ergonomic environmental factors). Together with four separate questions on standing, sitting, walking and uncomfortable postures, the indices constitute a brief overview of the main findings on musculoskeletal workload and associated potentially hazardous working conditions. Homogeneity of the indices is satisfactory. The divergent validity of the indices is fair when compared with an index of psychosocial working conditions and discomfort during exposure to physical loads. Worker groups with contrasting musculoskeletal loads can be differentiated on the basis of the indices and other factors. With respect to the concurrent validity, it appears that most indices and factors show significant associations with low back and/or neck shoulder symptoms. This questionnaire can be used as a simple and quick inventory for occupational health services to identify worker groups in which a more thorough ergonomic analysis is indicated.     

What is 'heavy'?

One of the work practices frequently taught to employees is to estimate the heaviness of load before it is actually handled. If it is ‘heavy’, then one should ask for help. However, limited information can be found in the ergonomics literature about what a person perceives as a ‘heavy load’. This study was conducted on 20 male and 20 female workers in the package delivery industry to estimate the amounts of load that correspond to various levels of load heaviness (e.g. ‘somewhat heavy’). Experienced employees were used for this purpose. The distribution of loads within each heaviness level was developed using fuzzy sets theory. The maximum load (i.e. 23 kg) defined by the US National Institute for Occupational Safety and Health represents a ‘somewhat heavy’ load based on the analysis of load distribution (corresponding to a 1.0 certainty factor). Also, the 40 kg considered in the 1981 NIOSH guidelines may be classified as a ‘very heavy’ load. A comparative analysis of the results of this study with norms established in prior research indicates that one should be more careful in the interpretation of statistical norms for human perception of load handling. A ‘moderate’ level of load heaviness (i.e. 14 kg) can be handled by 85% of the worker population.     

Assessing exposure to risk factors for work-related musculoskeletal disorders using Quick Exposure Check (QEC) in taxi drivers

Work-related musculoskeletal disorders (WMSDs) are a common health problem throughout the world. This study aimed to examine the risk factors that are involved in the development of WMSDs in taxi drivers. In total 382 taxi drivers were observed using Quick Exposure Check (QEC) observational tool, which allows practitioners and workers to assess four key areas of the body. Results of the QEC scores were found to be very high for the shoulder/arm, wrist/hand and neck, whereas the scores for the back were found to be high for static use and moderate for moving. The results also showed that the occupational risk factors for WMSDs were associated with restricted postures, repetitive movements, vibration, work related stress. Essential ergonomic interventions are needed to eliminate risk of exposures to WMSDs in taxi drivers.Relevance to industryThe study results have relevance for ergonomists, health and safety practitioners as well as the drivers themselves, and helpful for estimating the main physical risk factors for WMDSs before choosing a method prior to an ergonomic intervention in industry.     

Determination of workers' compliance to safety regulations using a spatio-temporal graph convolution network

The safety of workers in construction remains a critical issue despite the automation of several tasks with fewer workers on site. As fatal accidents of workers account for a significant number of construction accidents, considerable effort has been made to monitor workers’ safety behaviors with additional personnel for supervising workers. With the advancement of data analytics, recent research has reported various human activity recognition methods based on image data to perform automated worker monitoring without additional labor. Nevertheless, unlike existing approaches based on a single image, a method that can capture a series of actions from sequential images is required to monitor workers’ compliance with safety behavior. To this end, an approach based on OpenPose and a spatio-temporal graph convolutional network is proposed in this study to evaluate workers’ compliance with safety regulations using sequential videos. The two primary functions of the developed method include 1) classifying each safety behavior among five representative behaviors stipulated in construction, and 2) determining the compliance of workers with each safety regulation. The results indicate that the developed approach can capture momentary safety behaviors and workers’ compliance with feasible accuracy of an average F1 score greater than 0.8. Furthermore, the proposed method can be extended to safety intervention policies with behavior-based feedback to inform workers of their non-compliance with safety behaviors. Therefore, this study contributes to proactive safety management by focusing on workers’ behavioral levels rather than on accident rate-based management.     

Automated ergonomic risk monitoring using body-mounted sensors and machine learning

Workers in various industries are often subject to challenging physical motions that may lead to work-related musculoskeletal disorders (WMSDs). To prevent WMSDs, health and safety organizations have established rules and guidelines that regulate duration and frequency of labor-intensive activities. In this paper, a methodology is introduced to unobtrusively evaluate the ergonomic risk levels caused by overexertion. This is achieved by collecting time-stamped motion data from body-mounted smartphones (i.e., accelerometer, linear accelerometer, and gyroscope signals), automatically detecting workers’ activities through a classification framework, and estimating activity duration and frequency information. This study also investigates various data acquisition and processing settings (e.g., smartphone’s position, calibration, window size, and feature types) through a leave-one-subject-out cross-validation framework. Results indicate that signals collected from arm-mounted smartphone device, when calibrated, can yield accuracy up to 90.2% in the considered 3-class classification task. Further post-processing the output of activity classification yields very accurate estimation of the corresponding ergonomic risk levels. This work contributes to the body of knowledge by expanding the current state in workplace health assessment by designing and testing ubiquitous wearable technology to improve the timeliness and quality of ergonomic-related data collection and analysis.