A new scoring system for the Rapid Entire Body Assessment (REBA) based on fuzzy sets and Bayesian networks

Traditional methods for assessing the risk of work-related musculoskeletal disorders (WMSDs) have a low sensitivity to changes in input variables. Using them, it is possible to obtain the same risk score for totally different postures, and in some cases, the effectiveness of ergonomic interventions cannot be demonstrated. This study aimed to develop a new scoring system for REBA, FBnREBA, using fuzzy sets and the Bayesian network (BN) approach to cover the drawbacks of the traditional REBA. First, the risk factors of WMSDs were defined in terms of fuzzy membership sets. Next, a BN model was developed based on REBA. Fourteen different postures were assessed using FBnREBA, and the results were compared with those of the original REBA. Lastly, a case study was performed to demonstrate how the new scoring system can be used to rank various interventions based on their effectiveness. FBnREBA is a BN model with 26 nodes and is based completely on REBA, but its results differ from those of REBA for identical postures. A comparison of the results of FBnREBA with those of REBA indicated that FBnREBA is more sensitive to changes in WMSDs risk factors than REBA. A case study was conducted using FBnREBA, and the effectiveness of modifying each body segment was determined and ranked. FBnREBA is more sensitive to changes in input variables so that it is unlikely to obtain the same risk score for different body postures. The introduced methodology can be used to modify the scoring systems of other similar methods.     

Investigative study and sensitivity analysis of Rapid Entire Body Assessment (REBA)

The paper aims primarily to study the sensitivity of Rapid entire body assessment (REBA) and identification of insensitive and sensitive posture zones. The investigative study, and sensitivity analysis of REBA offer deeper insights into the methodology used for the assessment of posture. Full factorial design is divided into parts using a forward approach to access the sensitivity. One parameter is varied keeping other parameters constant to understand its effect on the output score. Combinations of posture where no change was observed were identified. Posture scores were also noted involving sudden jumps. Regression analysis was performed to identify relative importance or weightage of the body and other variables in estimating the final REBA score. The justification of the REBA methodology available in the existing literature is very limited. This paper also demonstrates the need for understanding of REBA method among the researchers. With this paper, ergonomic practitioners can be made aware of insensitive and sensitive zones in posture assessment.OriginalityThis is the first paper that primarily aims to establish the sensitivity of REBA and identifying insensitive postures or problems in REBA assessment. Few research gaps are identified.     

Ergonomics study and analysis of workstations in Tunisian mechanical manufacturing

The workers’ performance in the mechanical manufacturing sector is the main factor for the improvement of productivity and quality. At present, it seems that the available information on the ergonomics and the working environment of the mechanical manufacturing actors is scarce. This study deals with the relationship between the working method and the workstation in injection mold manufacturing. An original methodology, based on the survey of operators using participatory ergonomic tools, is proposed in order to evaluate the ergonomic performance of 3 workstations: milling, turning, and drilling. The surveys concerned 3 operators. Obtained results showed that ergonomics play a key role in improving mechanical manufacturing. The results obtained from the analysis showed that ergonomics has a key role in the quality of the various tasks performed by operators. Using the Rapid Entire Body Assessment (RULA) and Rapid Entire Body Assessment (REBA) investigation tools, the examination of the workstations revealed 4 machining operations and 12 operator postures that have a direct influence on the performance of all machining stations. In addition, data from the analysis conducted on injection mold manufacturing revealed that neither the workstations were ergonomic nor the operators complied with the ergonomic rules. Based on the results obtained, a new standardized score is proposed for the RULA and REBA calculations. This score was applied and validated through another study conducted in a leaf spring manufacturing plant. The results of these studies were concretized by proposing the digital factory where CATIA software was used for the virtual design of the ergonomic workstations and their environments.     

Intra-rater and inter-rater reliability of the rapid entire body assessment (REBA) tool

BackgroundErgonomics researchers and practitioners use many techniques to assess risk. The Rapid Entire Body Assessment (REBA) is a common tool used to facilitate the measurement and evaluation of the risks associated with working postures as a part of ergonomic workload. However, little work has been reported regarding the reliability of REBA reporting.ObjectiveThis study assesses the reliability of this commonly used tool for research and practice.MethodsThe study was conducted as part of the larger Safe Workload Ergonomic Exposure Project (SWEEP), which is a University of Minnesota research initiative for custodians. For this effort, a secondary data analysis was conducted on data collected during a study of custodians’ exposures to risks of musculoskeletal disorders. Eight observers used the REBA tool to sequentially evaluate tasks performed two times in succession by the same individual.ResultsThis study reports high intra-rater reliability (ICC = 0.925) for REBA raw scores and moderate inter-rater reliability (IRR) (Fleiss kappa = 0.54) for a categorical scoring of REBA.ConclusionA moderate amount of IRR was found, and a standardized training and calibration protocol is proposed as a potential means to improve intra- and inter-rater reliability.     

A hybrid of Nested Partition, Binary Ant System, and Linear Programming for the multidimensional knapsack problem

This work presents a hybrid algorithm of Nested Partition (NP), Binary Ant System (BAS), and Linear Programming (LP) to solve the multidimensional knapsack problem (MKP). The hybrid NP+BAS+LP algorithm takes advantage of the global search strategies of the NP algorithm; the ability of BAS to quickly generate good solutions and incorporates information obtained from solving a LP relaxation of the MKP to help guide the search. It thus incorporates both the lower bounds (LB), found by the BAS, and the upper bounds (UB), found by solving the relaxed LP, into the search by embedding both in the NP framework. An adjustable computation budget is implemented where the number of samples increases if the LB and the UB point to different promising subregions. The proposed hybrid is compared to state-of-the-art solution techniques and is found to be one of the best algorithms in terms of the quality of solutions obtained and CPU time requirements.     

Management of scoring sessions in alternative assessment: the computer-assisted scoring approach

We describe a computer-assisted scoring approach in educational assessment. In this approach, scores are captured and analyzed as scoring takes place; information on scoring quality is used to provide immediate feedback to raters and make timely re-calibration and dismissal decisions. We present a conceptual model for computer-assisted scoring and describe how we used this approach to manage the scoring sessions of an assessment for teacher certification. We found that computer-assisted scoring: (a) allowed us to provide immediate feedback to raters about their scoring quality and make accurate re-calibration and dismissal decisions; and (b) did not affect the dependability of the scores or the flow of the scoring sessions. We also confirmed that, with appropriate software, raters can be trained readily to score complex performance with the aid of computers even when they have no prior experience with computers. The conceptual model allowed us to identify how close our scoring sessions were to optimal efficiency.     

SEE: A proactive strategy-centric and deep learning-based ergonomic risk assessment system for risky posture recognition

Work-related musculoskeletal disorders (WMSDs) are serious workplace injuries that put workers' safety at risk. However, traditional WMSD assessments are based on the human-evaluation strategy (HES), requiring human intervention. Proactive strategy (PAS)-oriented WMSDs assessments collect data using posture data tags and special semi-human–machine equipment to improve efficiency and reduce human efforts to capture specific postures in a real-world setting. Meanwhile, more research on applying artificial intelligence-based pose machines for musculoskeletal risk assessment in various workplaces is needed. Hence, this study proposed a holistic posture acquisition and ergonomic risk analysis model with the PAS-oriented philosophy for developing a smartphone-based and workplace-based risk assessment system for WMSDs. The Convolutional Pose Machines (CPM) method was combined with a rapid entire body assessment method for the system's design. Finally, the smart ergonomic explorer (SEE) system includes three subsystems: an automotive scene capturer, an ergonomic risk level calculator, and a risk assessment reporter. A musculoskeletal risk assessment experiment with 13 poses was also carried out to validate the SEE system and compare its accuracy with manual evaluation. The result shows good agreement with the REBA score, with an average proportion agreement index (P0) of 0.962 and kappa of 0.82. It indicates that the proposed system can not only accurately analyze the working posture, but also accurately evaluate the total REBA scores. This study is hoped to provide practical advice and implications for achieving a more effective empirical response for WMSD assessment.     

Using feedforward neural networks and forward selection of input variables for an ergonomics data classification problem

A method was developed to accurately predict the risk of injuries in industrial jobs based on datasets not meeting the assumptions of parametric statistical tools, or being incomplete. Previous research used a backward‐elimination process for feedforward neural network (FNN) input variable selection. Simulated annealing (SA) was used as a local search method in conjunction with a conjugate‐gradient algorithm to develop an FNN. This article presents an incremental step in the use of FNNs for ergonomics analyses, specifically the use of forward selection of input variables. Advantages to this approach include enhancing the effectiveness of the use of neural networks when observations are missing from ergonomics datasets, and preventing overspecification or overfitting of an FNN to training data. Classification performance across two methods involving the use of SA combined with either forward selection or backward elimination of input variables was comparable for complete datasets, and the forward‐selection approach produced results superior to previously used methods of FNN development, including the error back‐propagation algorithm, when dealing with incomplete data. © 2004 Wiley Periodicals, Inc. Hum Factors Man 14: 31–49, 2004.     

用余弦相似度修正评分的协同过滤推荐算法

在用户对项目进行评分的时候,有时会出现不合理因素导致用户对项目做出不合理评分,使得推荐过程出现偏差。为修正这一偏差,采用评分矩阵的多种维度进行相似度比较以修正不合理评分,再用修正后的评分进行协同过滤推荐。而在采用变维度评分矩阵进行相似度对比时,主要利用同一用户对相似项目评分的相近性,对比2个用户对多个相似项目评分数组在不同维度下的余弦相似度。首先将多个评分构建成等维度的几个数组,对比2个用户的各个评分数组相似度,当某个相似度与其它相似度差别较大时,认为该相似度对应的2个用户的数组中至少有1个包含不合理评分;然后将2个数组按同样的方式均分为维度更低的数组,以此类推,最终确定不合理评分;最后以所有合理评分数组对应的相似度均值作为不合理评分数组对应的相似度,从而修正不合理评分。利用MovieLens和Bookcrossing数据库进行实验,结果表明:带修正评分的协同过滤算法相比未修正前的评分具有更高的推荐精度,其推荐评分MAE明显下降,本文算法相比对照算法获得了更优的MAE,Precision和Coverage。     

Technical note: Objective and subjective rankings of scientific journals in the field of ergonomics: 2004–2005

Ergonomics journals and journals related to the field of ergonomics were ranked according to a method developed by Dul and Karwowski (2004) to create the Ergonomics Journal List 2005 (EJL2005). The EJL2005 was compared with the EJL2004. The rankings of the best ergonomics journals in EJL2005 were compared with the rankings based on perceived journal quality from a survey among 130 certified European ergonomists. The results show that in the EJL2005, the six primary ergonomics journals are the same as in the EJL2004, although some journals changed position. Eleven new journals showed up in the list of 61 related journals (non‐ergonomics journals that regularly publish ergonomics articles). The total number of ergonomics articles in these journals increased from 605 in the EJL2004 to 623 in the EJL2005. There was a high congruence between the ranking of ergonomics journals in the EJL2005 and rankings based on perceived journal quality (Pearson r = 0.90). © 2005 Wiley Periodicals, Inc. Hum Factors Man 15: 327–332, 2005.     

The disability index analysis system via an ergonomics, expert systems, and multiple attribute decision-making process

Through rehabilitation and training, visually impaired people can be placed in types of jobs that are compatible with their abilities. A functional assessment approach should be established to measure the physical ability of handicapped people in response to specific tasks and environmental demands. The objective of this study is to develop an integrated computerized system, entitled VITAL (Vision Impaired Task and Assignment Lexicon), to measure the vision impaired worker's residual capabilities and to provide the necessary recommendations for job accommodations. VITAL includes two major modules: the disability index, and the ergonomics consultation module. A single measure, the Disability Index (DI), which represents capacities of vision impaired individuals through a range of skill tests is developed via Multiple Attribute Decision Making (MADM) procedures. The resulting DI can be used in identifying the functional deficits and limitations of the visually impaired worker, and matching the visually impaired people to appropriate employment. This information is also used in the ergonomic consultation module to provide recommendations regarding job and workplace design for the vision impaired worker.     

Comparison of OWAS,RULA and REBA for assessing potential work-related musculoskeletal disorders

This study compared three representative observational methods for assessing musculoskeletal loadings: Ovako Working Posture Analysis System (OWAS), Rapid Upper Limb Assessment (RULA), and Rapid Entire Body Assessment (REBA). The comparison was based on 209 cases of upper-body musculoskeletal disorders (MSDs) diagnosed by medical doctors. The most awkward/stressful posture in each participant's tasks was assessed using these techniques. Postural loadings were rated more highly by the RULA than by the OWAS and REBA (p < 0.01). The chi-square test and logistic regression analysis showed that only RULA grand score and action level, and REBA action level were associated with MSD work-relatedness (p < 0.01, p < 0.05, and p < 0.05, respectively). The percentage concordant values of the logistic model for the RULA grand score and action level were 52.4% and 44.8%, respectively, while the percentage concordant value for the REBA action level was 22.1%. Therefore, the RULA may be the best system for estimating the postural loads and work-relatedness of MSDs.Relevance to industryWork-related musculoskeletal disorders are the leading cause of workplace disability in the developed countries. For preventing the disorders, quantification of musculoskeletal loads is required.     

A checklist for evaluating ergonomic risk factors resulting from awkward postures of the legs, trunk and neck

A one-page checklist for determining the presence of ergonomic risk factors associateed with awkward postures of the lower extremities, trunk and neck was developed and evaluated as part of a joint labor-management ergonomics intervention program. This checklist was used by plant personnel at four work sites to assess the postural requirements on 335 cyclical (i.e., work-cycle duration less than five minutes) manufacturing and warehouse jobs. In addition, results generated by the checklist were compared to the results of ergonomic analyses performed by persons with advanced training in occupational ergonomics.

Workers were observed using awkward postures for most of the jobs in the survey. Awkward postures of the lower extrimities were relatively uncommon, occuring in 25 percent or less of the jobs. Awkward postures of the trunk and neck were common, occuring in more than 70 percent of the jobs. Results generated by the checklist were generally in agreement with results generated by the experienced ergonomists; however, the checklist was found to be more sensitive in identifying the presence of awkward postures.

The checklist was found to be an effective rapid-screening instrument for identifying cyclical jobs that expose workers to potentially harmful postures. However, the checklist methodology did not include sufficient documentation of work methods to identify the specific job attributes associated with these exposures. Furthermore, the checklist was not used to evaluate non-cyclical jobs (e.g., maintenance and skilled trades).     

Physical and mental workload interactions in a sterile processing department

Work in healthcare facilities has been categorized as a high-risk job for developing Work-Related Musculoskeletal Disorders (WMSDs). Little attention has been given to the Sterile Processing Department (SPD) employees who are exposed to both mentally and physically demanding conditions, factors that may impose an elevated risk in the development of WMSDs. Previous studies have shown that WMSDs can be a result of complex interactions between physical, psychosocial, biological, and individual characteristics. However, the evidence of specific associations is still inconclusive. The objective of this study was to determine if the perception of mental workload causes workers to adopt more risky body postures. The study was carried out in four phases: 1) identification of musculoskeletal disorders using customized Nordic questionnaires, 2) ergonomic assessment of SPD using REBA method, 3) mental workload assessment of SPD using NASA-TLX, and 4) interaction between physical (postural risk) and mental workload through the performance of a task at two different levels of workload conducted through a controlled experiment. The findings indicate that increases in REBA scores and NASA-TLX indices were associated with days and conditions with higher workloads. Results showed evidence that increments on mental workload are related to worsening postures, increasing the risk of developing musculoskeletal disorders. These results serve to raise awareness and warn employees about the need to pause and analyze the way they perform their duties under high levels of workload in an attempt to reduce WMSDs risk in healthcare sector employees.     

Large-scale regional economic development: Macroergonomics in theory and practice

Ergonomics has traditionally focused on improving such indices as productivity, health and safety, and quality of work life. Such improvements are necessary to individuals and organizations, but may not be sufficient, as emphasized by the recent focus on community ergonomics and other “macrosystem” concerns. Ergonomists have begun to apply their technologies to go beyond traditional measures to impact regional economic development. A model for ergonomics in regional economic development was developed from a successful 10-year intervention in New York State. After presenting this model in terms of organizational design and core processes, two industrial cases are summarized to help validate the approach. Two large plants and industrial employers were threatened with closure. Macroergonomic assessment, research, and intervention led to significant job retention, facilities expansion, and job creation. Within 5 years, the approach was credited with several turnarounds, retaining and expanding thousands of jobs and transforming the regional economy. © 1999 John Wiley & Sons, Inc.     

Evaluation of the effects of two alternative participatory ergonomics intervention strategies for construction companies

To improve the use of ergonomics tools by construction workers, the effect of two guidance strategies – a face-to-face strategy (F2F) and an e-guidance strategy (EG) – of a participatory ergonomics intervention was studied. Twelve construction companies were randomly assigned to the F2F group or the EG group. The primary outcome measure, the percentage of workers using ergonomics tools, and secondary outcome measures – work ability, physical functioning and limitations due to physical problems – were assessed using surveys at baseline and after 6 months. Additionally, a cost-benefit analysis was performed on company level. No differences in primary and secondary outcomes were found with the exception of the use of ergonomics tools to adjust working height (F2F +1%; EG +10%; p?=?.001). Newly-implemented tools were used by 23% (F2F) and 42% (EG) of the workers (p?=?.271). Costs were mainly determined by guidance costs (F2F group) or purchase costs (EG group).

Practitioner Summary: Participatory strategies aim to stimulate behavioural change of stakeholders to increase the use of ergonomics tools. Two guidance strategies – face-to-face or e-mail interventions – among construction companies were studied. Both guidance strategies led to an increase in the use of new ergonomics tools.     

A job-shop problem with one additional resource type

We consider a job-shop scheduling problem with n jobs and the constraint that at most p<n jobs can be processed simultaneously. This model arises in several manufacturing processes, where each operation has to be assisted by one human operator and there are p (versatile) operators. The problem is binary NP-hard even with n=3 and p=2. When the number of jobs is fixed, we give a pseudopolynomial dynamic programming algorithm and a fully polynomial time approximation scheme (FPTAS). We also propose an enumeration scheme based on a generalized disjunctive graph, and a dynamic programming-based heuristic algorithm. The results of an extensive computational study for the case with n=3 and p=2 are presented.     

Green ergonomics: definition and scope

This paper demonstrates that the goals of ergonomics (i.e. effectiveness, efficiency, health, safety and usability) are closely aligned with the goals of design for environmental sustainability. In this paper, the term ‘green ergonomics’ is conceptualised to specifically describe ergonomics interventions with a pro-nature emphasis. Green ergonomics is focused on the bi-directional connections between human systems and nature. This involves looking at (1) how ergonomics design and evaluation might be used to conserve, preserve, and restore nature and (2) how ecosystem services might be harnessed to facilitate the improved wellbeing and effectiveness of human systems. The paper proposes the scope of green ergonomics based on these bi-directional relationships in the areas of the design of low resource systems and products, the design of green jobs, and the design for behaviour change. Suggestions for further work in the green ergonomics domain are also made.

Practitioner Summary: Given the enormous environmental challenges facing modern industrial society, this paper encourages ergonomics science to embrace a pro-nature understanding of work design and research. This paper sets out the role for green ergonomics based on an appreciation of the human–nature connections that have been integrated with our understanding of ergonomics science and practice.     

基于边界矩阵低阶近似和近邻模型的协同过滤算法

为解决矩阵分解应用到协同过滤算法的局限性和准确率等问题,提出基于边界矩阵低阶近似（BMA）和近邻模型的协同过滤算法（BMAN-CF）来提高物品评分预测的准确率。首先,引入BMA的矩阵分解算法,挖掘子矩阵的隐含特征信息,提高近邻集合查找的准确率;然后,根据传统基于用户和基于物品的协同过滤算法分别预测出目标用户对目标物品的评分,利用平衡因子和控制因子动态平衡两个预测结果,得到目标用户对物品的评分;最后,利用MapReduce计算框架的特点,对数据进行分块,将该算法在Hadoop环境下并行化。实验结果表明,BMAN-CF比其他矩阵分解算法有更高的评分预测准确率,且加速比实验验证了该算法具有较好的可扩展性。