International Journal of Industrial Ergonomics最新文献_第9页

Developing workload-informed crew configuration recommendations for emergency medical services 为紧急医疗服务制定工作负荷知情的机组配置建议

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-07-01 DOI: 10.1016/j.ergon.2025.103777

Setareh Darvishi , Paul Misasi , Laila Cure

While crew configuration in primary care settings has been studied in terms of its impact on patient outcomes, less is known about how it influences the members' workload experience. This study investigates the workload implications of crew configuration based on members' certification in emergency medical services (EMS). Advanced life support (ALS) ambulance crews are commonly comprised of two paramedics (homogeneous crew) or an emergency medical technician (EMT) and a paramedic (heterogeneous crew). The goals of this study were the following: (1) to investigate differences in workload among members of the same crew, and (2) to use workload assessments to inform crew configuration strategies. We mapped one year of an EMS system's dispatch data to members' workload estimates using the visual, auditory, cognitive, and psychomotor (VACP) approach. We found that lead members (lead paramedics) experience higher workload levels compared to support members (support paramedics or EMTs) in both types of crews. Neither configuration had a consistently lower workload than the other, but differences varied for different shifts and stations. These results informed crew configuration recommendations for stations and shifts in the collaborating system, and in terms of more generalizable variables. A minimum number of staffed crews, half-half shift type (covering both day and night hours), and 30-day frequency of calls with priority P7 most significantly impacted the recommended crew configurations.

虽然已经研究了初级保健机构的工作人员配置对患者结果的影响，但对其如何影响成员的工作量体验知之甚少。本研究旨在探讨紧急医疗服务中，基于成员资格认证的机组配置对工作量的影响。高级生命支持（ALS）救护人员通常由两名护理人员（同质人员）或一名紧急医疗技术人员（EMT）和一名护理人员（异质人员）组成。本研究的目的如下：(1)调查同一机组成员之间的工作量差异；(2)使用工作量评估来告知机组配置策略。我们使用视觉、听觉、认知和精神运动（VACP）方法将EMS系统一年的调度数据映射到成员的工作量估计。我们发现，在这两种类型的工作人员中，领导成员（领导护理人员）比支持成员（支持护理人员或emt）的工作量更高。两种配置都没有始终比另一种更低的工作量，但不同班次和站点的差异有所不同。这些结果为协作系统中站位和班次的机组人员配置建议提供了依据，并提供了更多可推广的变量。最小工作人员数量、半轮班类型（包括白天和夜间）以及优先级为P7的30天呼叫频率对建议的工作人员配置影响最大。

{"title":"Developing workload-informed crew configuration recommendations for emergency medical services","authors":"Setareh Darvishi , Paul Misasi , Laila Cure","doi":"10.1016/j.ergon.2025.103777","DOIUrl":"10.1016/j.ergon.2025.103777","url":null,"abstract":"<div><div>While crew configuration in primary care settings has been studied in terms of its impact on patient outcomes, less is known about how it influences the members' workload experience. This study investigates the workload implications of crew configuration based on members' certification in emergency medical services (EMS). Advanced life support (ALS) ambulance crews are commonly comprised of two paramedics (homogeneous crew) or an emergency medical technician (EMT) and a paramedic (heterogeneous crew). The goals of this study were the following: (1) to investigate differences in workload among members of the same crew, and (2) to use workload assessments to inform crew configuration strategies. We mapped one year of an EMS system's dispatch data to members' workload estimates using the visual, auditory, cognitive, and psychomotor (VACP) approach. We found that lead members (lead paramedics) experience higher workload levels compared to support members (support paramedics or EMTs) in both types of crews. Neither configuration had a consistently lower workload than the other, but differences varied for different shifts and stations. These results informed crew configuration recommendations for stations and shifts in the collaborating system, and in terms of more generalizable variables. A minimum number of staffed crews, half-half shift type (covering both day and night hours), and 30-day frequency of calls with priority P7 most significantly impacted the recommended crew configurations.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103777"},"PeriodicalIF":2.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The influence of interface attributes and interaction elements on user performance and cognitive load in task interruption scenarios 任务中断场景下界面属性和交互元素对用户性能和认知负荷的影响

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-25 DOI: 10.1016/j.ergon.2025.103761

Chi Zhang , Da Peng Wei , Yue Ji , Ding Chen , Xin Yan Li , Xiao Dong Gong

This study aims to investigate the mechanisms by which digital interface attributes (interface complexity and similarity) and interaction elements (contextual guidance during the task resumption phase) influence user task performance and cognitive load in task interruption scenarios. A within-subject experimental design was employed, where participants were required to switch between primary and interrupting tasks while completing designated arithmetic tasks, thereby simulating real-world task interruptions. The results indicate that interface complexity is a key factor affecting task performance and cognitive load. High-complexity interfaces significantly prolonged task resumption lag times, increased error rates, and led to higher levels of cognitive load. The effect of interface similarity on performance showed a significant interaction with complexity. Under high complexity conditions, high-similarity interfaces increased resumption lag times; conversely, under low complexity conditions, high-similarity interfaces reduced resumption lag times. Furthermore, providing clear contextual guidance significantly shortened resumption lag times during the task resumption phase and reduced the number of selection errors, although it did not have a sufficiently significant impact on cognitive load. Despite the varying influence of each variable on resumption performance, the overall performance can be explained by the Memory for Goals Theory (MFG). The findings offer valuable theoretical and practical guidance for optimizing interface design in complex task environments, underscoring the importance of considering interface complexity, similarity, and resumption guidance when designing multitasking interfaces.

本研究旨在探讨任务中断情境下，数字界面属性（界面复杂性和相似性）和交互元素（任务恢复阶段的语境引导）对用户任务绩效和认知负荷的影响机制。采用受试者内实验设计，要求参与者在完成指定的算术任务时在主要任务和中断任务之间切换，从而模拟现实世界的任务中断。结果表明，界面复杂性是影响任务绩效和认知负荷的关键因素。高复杂性的界面显著延长了任务恢复延迟时间，增加了错误率，并导致更高水平的认知负荷。界面相似度对性能的影响与复杂性有显著的交互作用。在高复杂性条件下，高相似度接口增加了恢复延迟时间；相反，在低复杂度条件下，高相似度的接口减少了恢复延迟时间。此外，提供清晰的上下文指导显著缩短了任务恢复阶段的恢复滞后时间，减少了选择错误的数量，尽管它对认知负荷没有足够显著的影响。尽管每个变量对恢复表现的影响不同，但总体表现可以用目标记忆理论（MFG）来解释。研究结果为在复杂任务环境下优化界面设计提供了有价值的理论和实践指导，强调了在设计多任务界面时考虑界面复杂性、相似性和恢复指导的重要性。

{"title":"The influence of interface attributes and interaction elements on user performance and cognitive load in task interruption scenarios","authors":"Chi Zhang , Da Peng Wei , Yue Ji , Ding Chen , Xin Yan Li , Xiao Dong Gong","doi":"10.1016/j.ergon.2025.103761","DOIUrl":"10.1016/j.ergon.2025.103761","url":null,"abstract":"<div><div>This study aims to investigate the mechanisms by which digital interface attributes (interface complexity and similarity) and interaction elements (contextual guidance during the task resumption phase) influence user task performance and cognitive load in task interruption scenarios. A within-subject experimental design was employed, where participants were required to switch between primary and interrupting tasks while completing designated arithmetic tasks, thereby simulating real-world task interruptions. The results indicate that interface complexity is a key factor affecting task performance and cognitive load. High-complexity interfaces significantly prolonged task resumption lag times, increased error rates, and led to higher levels of cognitive load. The effect of interface similarity on performance showed a significant interaction with complexity. Under high complexity conditions, high-similarity interfaces increased resumption lag times; conversely, under low complexity conditions, high-similarity interfaces reduced resumption lag times. Furthermore, providing clear contextual guidance significantly shortened resumption lag times during the task resumption phase and reduced the number of selection errors, although it did not have a sufficiently significant impact on cognitive load. Despite the varying influence of each variable on resumption performance, the overall performance can be explained by the Memory for Goals Theory (MFG). The findings offer valuable theoretical and practical guidance for optimizing interface design in complex task environments, underscoring the importance of considering interface complexity, similarity, and resumption guidance when designing multitasking interfaces.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103761"},"PeriodicalIF":2.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gender-specific effects of passive wearable exoskeletons (pwExo) on gait stability and fall risk in simulated construction tasks 被动可穿戴外骨骼（pwExo）对模拟施工任务中步态稳定性和跌倒风险的性别影响

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-24 DOI: 10.1016/j.ergon.2025.103776

Muhammad Khan, Chukwuma Nnaji

Exoskeletons (Exos) offer significant benefits, but they may also introduce balance-related challenges, which could vary across genders or be exacerbated by gender-specific factors. This study investigates their biomechanical impact on gait stability and fall risk, considering gender-specific differences and task-specific outcomes. Key metrics, including Peak Pressure (PP), Mean Pressure (MP), Pressure-Time Integral (PTI), and Full Width at Half Maximum (FWHM), were analyzed across dynamic and static tasks. Results revealed that pwExos significantly influenced plantar pressure distribution, particularly in dynamic tasks such as lifting and carrying. Female participants experienced substantial reductions in peak heel pressure (up to 17.7%, p = 0.021), metatarsal pressures (14.2%, p = 0.034), and arch PTI (up to 52.8%), suggesting enhanced load redistribution and stability, whereas males exhibited increased forefoot loading, including a 15.5% increase in metatarsal PP and a 90.8% rise in toe PTI, indicating potential compensatory adaptations. Mean Pressure in females decreased by 73.5% at the heel during placing tasks, while males showed increased anterior pressure in static tasks. The pwExos were most effective during high-load tasks such as lifting and walking with sandbags (10lb), where pressure redistribution was greatest. While static tasks showed limited benefits, improvements in the arch and metatarsal regions suggest partial stabilization. These findings emphasize the potential of pwExos to enhance stability and reduce biomechanical fatigue, highlighting the need for task-specific and gender-sensitive designs. Future research should assess long-term effects, real-world applicability, and the role of individual factors such as Body Mass Index to optimize Exo integration in construction safety and health management.

外骨骼（Exos）提供了显著的好处，但它们也可能带来与平衡相关的挑战，这些挑战可能因性别而异，或因性别特定因素而加剧。考虑到性别差异和特定任务的结果，本研究调查了他们对步态稳定性和跌倒风险的生物力学影响。关键指标包括峰值压力（PP）、平均压力（MP）、压力-时间积分（PTI）和半最大全宽度（FWHM），在动态和静态任务中进行了分析。结果显示，pwExos显著影响足底压力分布，特别是在动态任务中，如举起和搬运。女性受试者的峰值足跟压力（高达17.7%,p = 0.021）、跖骨压力（14.2%,p = 0.034）和足弓PTI（高达52.8%）显著降低，表明负荷再分配和稳定性增强，而男性受试者的前脚负荷增加，包括跖骨PP增加15.5%，趾部PTI增加90.8%，表明潜在的代偿性适应。在放置任务中，女性脚后跟的平均压力下降了73.5%，而男性在静态任务中表现出增加的前压。pwexo在搬运沙袋（10磅）等高负荷任务中最为有效，因为这些任务的压力再分配效果最好。虽然静态任务的益处有限，但足弓和跖骨区域的改善表明部分稳定。这些发现强调了pwExos在增强稳定性和减少生物力学疲劳方面的潜力，强调了针对特定任务和性别敏感设计的必要性。未来的研究应评估长期效果、现实适用性以及个体因素（如身体质量指数）的作用，以优化Exo集成在建筑安全与健康管理中的作用。

{"title":"Gender-specific effects of passive wearable exoskeletons (pwExo) on gait stability and fall risk in simulated construction tasks","authors":"Muhammad Khan, Chukwuma Nnaji","doi":"10.1016/j.ergon.2025.103776","DOIUrl":"10.1016/j.ergon.2025.103776","url":null,"abstract":"<div><div>Exoskeletons (Exos) offer significant benefits, but they may also introduce balance-related challenges, which could vary across genders or be exacerbated by gender-specific factors. This study investigates their biomechanical impact on gait stability and fall risk, considering gender-specific differences and task-specific outcomes. Key metrics, including Peak Pressure (PP), Mean Pressure (MP), Pressure-Time Integral (PTI), and Full Width at Half Maximum (FWHM), were analyzed across dynamic and static tasks. Results revealed that pwExos significantly influenced plantar pressure distribution, particularly in dynamic tasks such as lifting and carrying. Female participants experienced substantial reductions in peak heel pressure (up to 17.7%, p = 0.021), metatarsal pressures (14.2%, p = 0.034), and arch PTI (up to 52.8%), suggesting enhanced load redistribution and stability, whereas males exhibited increased forefoot loading, including a 15.5% increase in metatarsal PP and a 90.8% rise in toe PTI, indicating potential compensatory adaptations. Mean Pressure in females decreased by 73.5% at the heel during placing tasks, while males showed increased anterior pressure in static tasks. The pwExos were most effective during high-load tasks such as lifting and walking with sandbags (10lb), where pressure redistribution was greatest. While static tasks showed limited benefits, improvements in the arch and metatarsal regions suggest partial stabilization. These findings emphasize the potential of pwExos to enhance stability and reduce biomechanical fatigue, highlighting the need for task-specific and gender-sensitive designs. Future research should assess long-term effects, real-world applicability, and the role of individual factors such as Body Mass Index to optimize Exo integration in construction safety and health management.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103776"},"PeriodicalIF":2.5,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144366643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative analysis of classical and ensemble models for predicting whole body vibration induced lumbar spine stress. A case study of agricultural tractor operators 经典模型与集合模型预测腰椎全身振动应力的比较分析。农用拖拉机操作员的案例研究

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-20 DOI: 10.1016/j.ergon.2025.103775

Amandeep Singh , Naser Nawayseh , Philippe Doyon-Poulin , Stephan Milosavljevic , Krishna N. Dewangan , Yash Kumar , Siby Samuel

Accurate prediction of lumbar health is necessary for developing effective ergonomic strategies for tractor operators exposed to whole-body vibration. This study aims to predict static compression dose (S_ed), a key measure of lumbar spine stress as per ISO 2631-5, by comparing classical regression and ensemble models. Three tractor operation parameters (average speed, average depth, and pulling force) are considered to assess S_ed during rotary tillage operation. The performance of two classical models (Linear and Huber regression) is compared with five ensemble models (Random Forest, Gradient Boosting, XGBoost, AdaBoost, and Bagging regressors) in predicting S_ed. The comparison identifies the best models in each category, with linear regression achieving a mean bootstrap R² of 0.91 (95 % CI: 0.87 to 0.94) and Random Forest achieving 0.93 (95 % CI: 0.90 to 0.95). To further enhance performance, meta-models are developed using two meta-learners (Random Forest and Gradient Boosting) to integrate classical and ensemble models. These models are optimized using different ensemble strategies: simple averaging, weighted averaging, stacking, and voting regressors. Among these, the stacking method proves most effective, achieving a mean bootstrap R² of 0.94 (95 % CI: 0.93 to 0.96). Feature importance analysis reveals that the multi-model combination of ensemble models achieves the highest predictive score (0.99) for S_ed. These findings demonstrate that ensemble models outperform classical models in predicting Sed, particularly when combined through stacking methods. This advancement has significant implications for improving occupational health and safety among tractor operators, potentially leading to better ergonomic tractor designs aimed at reducing lumbar spine stress.

准确预测腰椎健康状况对于制定有效的人体工程学策略对于暴露于全身振动的拖拉机操作员是必要的。本研究旨在通过比较经典回归模型和集合模型来预测静态压缩剂量（Sed），这是ISO 2631-5规定的腰椎应力的关键指标。考虑三个拖拉机操作参数（平均速度，平均深度和牵引力）来评估旋转耕作操作中的Sed。将两种经典模型（线性和Huber回归）与五种集成模型（随机森林、梯度增强、XGBoost、AdaBoost和Bagging回归）在预测Sed方面的性能进行了比较。比较确定了每个类别中的最佳模型，线性回归的平均bootstrap R2为0.91 (95% CI: 0.87至0.94)，随机森林的平均bootstrap R2为0.93 （95% CI: 0.90至0.95）。为了进一步提高性能，使用两个元学习器（随机森林和梯度增强）开发元模型来集成经典模型和集成模型。这些模型使用不同的集成策略进行优化：简单平均、加权平均、堆叠和投票回归。其中，叠加法被证明是最有效的，实现了0.94的平均bootstrap R2 （95% CI: 0.93至0.96）。特征重要性分析表明，集成模型的多模型组合对Sed的预测得分最高（0.99）。这些发现表明，集成模型在预测Sed方面优于经典模型，特别是当通过堆叠方法组合时。这一进展对改善牵引车操作人员的职业健康和安全具有重要意义，可能导致更好的符合人体工程学的牵引车设计，旨在减少腰椎压力。

{"title":"Comparative analysis of classical and ensemble models for predicting whole body vibration induced lumbar spine stress. A case study of agricultural tractor operators","authors":"Amandeep Singh , Naser Nawayseh , Philippe Doyon-Poulin , Stephan Milosavljevic , Krishna N. Dewangan , Yash Kumar , Siby Samuel","doi":"10.1016/j.ergon.2025.103775","DOIUrl":"10.1016/j.ergon.2025.103775","url":null,"abstract":"<div><div>Accurate prediction of lumbar health is necessary for developing effective ergonomic strategies for tractor operators exposed to whole-body vibration. This study aims to predict static compression dose (S<sub>ed</sub>), a key measure of lumbar spine stress as per ISO 2631-5, by comparing classical regression and ensemble models. Three tractor operation parameters (average speed, average depth, and pulling force) are considered to assess S<sub>ed</sub> during rotary tillage operation. The performance of two classical models (Linear and Huber regression) is compared with five ensemble models (Random Forest, Gradient Boosting, XGBoost, AdaBoost, and Bagging regressors) in predicting S<sub>ed</sub>. The comparison identifies the best models in each category, with linear regression achieving a mean bootstrap R<sup>2</sup> of 0.91 (95 % CI: 0.87 to 0.94) and Random Forest achieving 0.93 (95 % CI: 0.90 to 0.95). To further enhance performance, meta-models are developed using two meta-learners (Random Forest and Gradient Boosting) to integrate classical and ensemble models. These models are optimized using different ensemble strategies: simple averaging, weighted averaging, stacking, and voting regressors. Among these, the stacking method proves most effective, achieving a mean bootstrap R<sup>2</sup> of 0.94 (95 % CI: 0.93 to 0.96). Feature importance analysis reveals that the multi-model combination of ensemble models achieves the highest predictive score (0.99) for S<sub>ed</sub>. These findings demonstrate that ensemble models outperform classical models in predicting Sed, particularly when combined through stacking methods. This advancement has significant implications for improving occupational health and safety among tractor operators, potentially leading to better ergonomic tractor designs aimed at reducing lumbar spine stress.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103775"},"PeriodicalIF":2.5,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A new measurement for workload assessment in agricultural tasks: EDA-based real-time model 一种新的农业任务工作量评估方法：基于eda的实时模型

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-20 DOI: 10.1016/j.ergon.2025.103771

Sujin Seong , Jaehyun Park , Jeong Ho Kim

Agriculture is vital for the global economy but remains one of the most hazardous industries due to the high prevalence of musculoskeletal disorders (MSDs). This study aimed to develop and validate an electrodermal activity (EDA)-based model for non-invasive, real-time assessment of upper limb task workload, addressing the impact of environmental factors on workers' mental and physical strain. To achieve this, participants engaged in simulated pruning and harvesting tasks, which are known for imposing substantial workload and injury risks on the upper extremities in agriculture. Anthropometric data, EDA signals, and the Borg rating of perceived exertion (RPE) were collected. A multinomial logistic regression (MLR) model was employed to classify workload levels based on EDA wavelet features and key task-related variables. The developed models for pruning and harvesting tasks explained 40–50 % of the variance in RPE, demonstrating the highest accuracy in the middle RPE group (88–89 %). Specificity was notably high (>91 %) across both tasks for low and high RPE groups. Additionally, the middle RPE group exhibited recall and F1 scores above 84.5 %, while the high RPE category demonstrated recall, precision, and F1 scores ranging from 73 % to 92 % for pruning and from 60 % to 75 % for harvesting. These findings underscore the model's potential for precise workload categorization and the development of effective management strategies. Furthermore, the proposed EDA-based framework may hold broader applicability across various occupational domains that require non-invasive and continuous workload monitoring.

农业对全球经济至关重要，但由于肌肉骨骼疾病（MSDs）的高发，农业仍然是最危险的行业之一。本研究旨在开发并验证一种基于皮肤电活动（EDA）的模型，用于无创、实时评估上肢任务工作量，解决环境因素对工人精神和身体压力的影响。为了实现这一目标，参与者参与了模拟修剪和收获任务，这些任务在农业中会对上肢施加大量工作量和伤害风险。收集人体测量数据、EDA信号和感知运动的博格评分（RPE）。基于EDA小波特征和关键任务相关变量，采用多项逻辑回归（MLR）模型对工作负荷进行分类。开发的修剪和收获任务模型解释了RPE中40 - 50%的方差，显示了中间RPE组的最高准确性（88 - 89%）。在低RPE组和高RPE组的两项任务中，特异性都非常高（> 91%）。此外，中等RPE组的召回率和F1得分高于84.5%，而高RPE组的召回率、准确率和F1得分在修剪的73%到92%之间，收割的60%到75%之间。这些发现强调了该模式在精确工作量分类和制定有效管理战略方面的潜力。此外，建议的基于eda的框架可能在需要非侵入性和连续工作负载监控的各种职业领域具有更广泛的适用性。

{"title":"A new measurement for workload assessment in agricultural tasks: EDA-based real-time model","authors":"Sujin Seong , Jaehyun Park , Jeong Ho Kim","doi":"10.1016/j.ergon.2025.103771","DOIUrl":"10.1016/j.ergon.2025.103771","url":null,"abstract":"<div><div>Agriculture is vital for the global economy but remains one of the most hazardous industries due to the high prevalence of musculoskeletal disorders (MSDs). This study aimed to develop and validate an electrodermal activity (EDA)-based model for non-invasive, real-time assessment of upper limb task workload, addressing the impact of environmental factors on workers' mental and physical strain. To achieve this, participants engaged in simulated pruning and harvesting tasks, which are known for imposing substantial workload and injury risks on the upper extremities in agriculture. Anthropometric data, EDA signals, and the Borg rating of perceived exertion (RPE) were collected. A multinomial logistic regression (MLR) model was employed to classify workload levels based on EDA wavelet features and key task-related variables. The developed models for pruning and harvesting tasks explained 40–50 % of the variance in RPE, demonstrating the highest accuracy in the middle RPE group (88–89 %). Specificity was notably high (>91 %) across both tasks for low and high RPE groups. Additionally, the middle RPE group exhibited recall and F1 scores above 84.5 %, while the high RPE category demonstrated recall, precision, and F1 scores ranging from 73 % to 92 % for pruning and from 60 % to 75 % for harvesting. These findings underscore the model's potential for precise workload categorization and the development of effective management strategies. Furthermore, the proposed EDA-based framework may hold broader applicability across various occupational domains that require non-invasive and continuous workload monitoring.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103771"},"PeriodicalIF":2.5,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Metaphorical types of industrial icons: Impact on cognitive performance and the neural pattern in processing 工业标志隐喻类型对认知表现的影响及加工中的神经模式

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-19 DOI: 10.1016/j.ergon.2025.103772

Lan Zhang , Xiaoli Wu , Biao Yan , Linyan Ren , Xiaoyang Mao

The rapid development of intelligent manufacturing poses challenges to the presentation of industrial information, leading to a recent surge of interest in industrial icons. To explore the semantic understanding of industrial icons within the intelligent manufacturing field, this study conducted an event-related potential (ERP) investigation focusing on metaphorical types (object metaphor, structural metaphor) and semantic conditions (match, mismatch). The ERP components observed—N1, P200, N400, and P600—reflect different stages of cognitive processing. N1 represents an initial response to visual perception, P200 indicates early recognition of semantic violations, N400 is associated with semantic processing and integration, and P600 reflects a prolonged reanalysis process for semantic integration. The study found that object metaphor elicited larger amplitudes in P200 and a smaller N400 compared to structural metaphor, suggesting that object metaphor requires more attention resources and is less impacted by semantic violations. However, the amplitude of P600 showed no significant difference between the two metaphorical types. Behavioral results demonstrated that object metaphor had higher accuracy and shorter response times than structural metaphor, indicating superior cognitive performance for object metaphor. These findings propose a novel perspective on using ERP components (N1, P200, N400, P600) to gain a deeper understanding of industrial icons. This contributes to the study of metaphorical design and the semantic understanding of industrial icons in the intelligent manufacturing domain.

智能制造的快速发展对工业信息的呈现提出了挑战，近年来人们对工业图标的兴趣激增。为探索智能制造领域工业图标的语义理解，本研究以隐喻类型（对象隐喻、结构隐喻）和语义条件（匹配、不匹配）为重点，开展了事件相关电位（ERP）调查。观察到的ERP成分n1、P200、N400和p600反映了认知加工的不同阶段。N1表示对视觉感知的初始反应，P200表示对语义违规的早期识别，N400与语义加工和整合相关，P600表示语义整合的再分析过程较长。研究发现，与结构隐喻相比，客体隐喻诱发的P200振幅较大，N400振幅较小，说明客体隐喻需要更多的注意资源，受语义违背的影响较小。而P600的振幅在两种隐喻类型间无显著差异。行为实验结果表明，客体隐喻比结构隐喻具有更高的准确性和更短的反应时间，表明客体隐喻具有更高的认知能力。这些发现提出了使用ERP组件（N1, P200, N400, P600）来更深入地理解工业图标的新视角。这有助于隐喻设计的研究和智能制造领域工业符号的语义理解。

{"title":"Metaphorical types of industrial icons: Impact on cognitive performance and the neural pattern in processing","authors":"Lan Zhang , Xiaoli Wu , Biao Yan , Linyan Ren , Xiaoyang Mao","doi":"10.1016/j.ergon.2025.103772","DOIUrl":"10.1016/j.ergon.2025.103772","url":null,"abstract":"<div><div>The rapid development of intelligent manufacturing poses challenges to the presentation of industrial information, leading to a recent surge of interest in industrial icons. To explore the semantic understanding of industrial icons within the intelligent manufacturing field, this study conducted an event-related potential (ERP) investigation focusing on metaphorical types (object metaphor, structural metaphor) and semantic conditions (match, mismatch). The ERP components observed—N1, P200, N400, and P600—reflect different stages of cognitive processing. N1 represents an initial response to visual perception, P200 indicates early recognition of semantic violations, N400 is associated with semantic processing and integration, and P600 reflects a prolonged reanalysis process for semantic integration. The study found that object metaphor elicited larger amplitudes in P200 and a smaller N400 compared to structural metaphor, suggesting that object metaphor requires more attention resources and is less impacted by semantic violations. However, the amplitude of P600 showed no significant difference between the two metaphorical types. Behavioral results demonstrated that object metaphor had higher accuracy and shorter response times than structural metaphor, indicating superior cognitive performance for object metaphor. These findings propose a novel perspective on using ERP components (N1, P200, N400, P600) to gain a deeper understanding of industrial icons. This contributes to the study of metaphorical design and the semantic understanding of industrial icons in the intelligent manufacturing domain.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103772"},"PeriodicalIF":2.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Experimental study on a novel phase change cooling garment to improve the thermal comfort of live-line workers 提高现场工作人员热舒适性的新型相变冷却服的实验研究

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-13 DOI: 10.1016/j.ergon.2025.103774

Shengwei Wang , Xiaohong Gui , Tian Liu , Yuran Huang , Li Ding

The study investigated the impact of a phase change cooling garment on the thermal comfort of live-line workers in humid and hot environments (38 °C, 75 % RH). A novel phase change cooling garment (C1), weighing 3.21 kg, was developed based on ergonomic design. The cooling effectiveness of C1 was assessed through evaluations conducted in an artificial climate chamber and field experiments. These evaluations measured physiological parameters such as heart rate, blood pressure, blood oxygen saturation, skin temperature, and core temperature, along with subjective questionnaires that covered overall and local thermal sensation, thermal comfort, and moisture sensation. The results demonstrated that C1 effectively reduced both the average and local skin temperatures in the cooled areas. Specifically, the average skin temperature decreased by approximately 2.4 °C, head skin temperature by about 1.2 °C, torso skin temperature by about 5.7 °C, and neck skin temperature by about 5.9 °C. Core temperature showed a reduction of approximately 0.4 °C. The use of C1 had minimal impact on other physiological parameters measured. Additionally, C1 significantly lowered subjective thermal sensation scores, with the overall thermal sensation vote (TSV) decreasing by 2.65 levels and the overall thermal comfort vote (TCV) decreasing by 1.7 levels. The overall heat stress level was reduced from severe to mild. Compared to other cooling garments, C1 exhibited superior performance in terms of thermal comfort. The findings provide valuable guidance for the design of personal phase change cooling garments, contributing to enhanced safety and comfort for live-line workers in humid and hot environments.

该研究调查了相变冷却服对湿热环境（38°C， 75%相对湿度）下现场工作人员热舒适性的影响。基于人体工学设计，研制了一种重3.21 kg的新型相变冷却服（C1）。通过人工气候室和现场实验对C1的降温效果进行了评价。这些评估测量了生理参数，如心率、血压、血氧饱和度、皮肤温度和核心温度，以及涵盖整体和局部热感觉、热舒适和水分感觉的主观问卷。结果表明，C1有效降低了冷区平均皮肤温度和局部皮肤温度。具体而言，平均皮肤温度下降约2.4°C，头部皮肤温度下降约1.2°C，躯干皮肤温度下降约5.7°C，颈部皮肤温度下降约5.9°C。岩心温度降低了约0.4℃。使用C1对测量的其他生理参数影响最小。此外，C1显著降低了主观热感觉评分，总热感觉投票（TSV）降低了2.65个等级，总热舒适投票（TCV）降低了1.7个等级。整体热应激水平由重度降至轻度。与其他制冷服装相比，C1在热舒适性方面表现出优越的性能。研究结果为个人相变冷却服的设计提供了有价值的指导，有助于提高湿热环境下现场工作人员的安全性和舒适性。

{"title":"Experimental study on a novel phase change cooling garment to improve the thermal comfort of live-line workers","authors":"Shengwei Wang , Xiaohong Gui , Tian Liu , Yuran Huang , Li Ding","doi":"10.1016/j.ergon.2025.103774","DOIUrl":"10.1016/j.ergon.2025.103774","url":null,"abstract":"<div><div>The study investigated the impact of a phase change cooling garment on the thermal comfort of live-line workers in humid and hot environments (38 °C, 75 % RH). A novel phase change cooling garment (C1), weighing 3.21 kg, was developed based on ergonomic design. The cooling effectiveness of C1 was assessed through evaluations conducted in an artificial climate chamber and field experiments. These evaluations measured physiological parameters such as heart rate, blood pressure, blood oxygen saturation, skin temperature, and core temperature, along with subjective questionnaires that covered overall and local thermal sensation, thermal comfort, and moisture sensation. The results demonstrated that C1 effectively reduced both the average and local skin temperatures in the cooled areas. Specifically, the average skin temperature decreased by approximately 2.4 °C, head skin temperature by about 1.2 °C, torso skin temperature by about 5.7 °C, and neck skin temperature by about 5.9 °C. Core temperature showed a reduction of approximately 0.4 °C. The use of C1 had minimal impact on other physiological parameters measured. Additionally, C1 significantly lowered subjective thermal sensation scores, with the overall thermal sensation vote (TSV) decreasing by 2.65 levels and the overall thermal comfort vote (TCV) decreasing by 1.7 levels. The overall heat stress level was reduced from severe to mild. Compared to other cooling garments, C1 exhibited superior performance in terms of thermal comfort. The findings provide valuable guidance for the design of personal phase change cooling garments, contributing to enhanced safety and comfort for live-line workers in humid and hot environments.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103774"},"PeriodicalIF":2.5,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Age and sex differences in wrist range of motion: A population-based study of young and elderly Taiwanese adults 腕部活动度的年龄与性别差异：台湾年轻与年老成人的人口研究

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-06-10 DOI: 10.1016/j.ergon.2025.103773

Yi-Lang Chen , Pei-Yun Chiu

Carpal tunnel syndrome is the most prevalent wrist-related condition, impacting both occupational tasks and daily activities. Awkward wrist postures are a major risk factor, with the likelihood of injury increasing as postures approach the wrist's range of motion (ROM). However, reference data for wrist ROM in the Taiwanese population is currently unavailable. This study examined wrist ROM in 250 participants (100 young adults and 150 elderly individuals, equally distributed by sex) using a dual-axis electro-goniometer. Measurements included ulnar deviation, radial deviation, flexion, and extension for both dominant and non-dominant wrists. Analysis of variance identified significant group differences in ulnar deviation (p < 0.001), flexion (p < 0.001), and extension (p < 0.05), with sex and hand dominance significantly influencing ulnar deviation (p < 0.01) and flexion (p < 0.05), respectively. An interaction effect between sex and dominance was observed for flexion (p < 0.05). Compared to the young group, the elderly group exhibited reduced ROM, with decreases of approximately 4° in ulnar deviation, 12° in flexion, and 4° in extension. Females exhibited greater ulnar deviation ROM than males, while the effect of hand dominance on flexion was evident only in males (+4°). Among the elderly cohort, no significant differences in ROM were observed between the 60–69 and 70–90 age subgroups.

腕管综合征是最常见的手腕相关疾病，影响职业任务和日常活动。笨拙的手腕姿势是一个主要的危险因素，随着姿势接近手腕的活动范围（ROM），受伤的可能性增加。然而，台湾人口腕部ROM的参考资料目前尚无。这项研究使用双轴电测角仪检查了250名参与者（100名年轻人和150名老年人，按性别平均分布）的手腕ROM。测量包括主手腕和非主手腕的尺骨偏差、桡骨偏差、屈曲和伸展。方差分析发现尺侧偏差组间差异显著(p <；0.001)，屈曲(p <；0.001)，扩展(p <；0.05)，性别和手优势显著影响尺偏度(p <；0.01)和屈曲(p <；分别为0.05)。在屈曲中观察到性别和优势之间的相互作用效应(p <；0.05)。与年轻组相比，老年组表现出ROM减少，尺骨偏差减少约4°，屈曲减少12°，伸直减少4°。女性表现出比男性更大的尺侧偏差，而手优势对屈曲的影响仅在男性中明显（+4°）。在老年队列中，60-69岁和70-90岁亚组间ROM无显著差异。

{"title":"Age and sex differences in wrist range of motion: A population-based study of young and elderly Taiwanese adults","authors":"Yi-Lang Chen , Pei-Yun Chiu","doi":"10.1016/j.ergon.2025.103773","DOIUrl":"10.1016/j.ergon.2025.103773","url":null,"abstract":"<div><div>Carpal tunnel syndrome is the most prevalent wrist-related condition, impacting both occupational tasks and daily activities. Awkward wrist postures are a major risk factor, with the likelihood of injury increasing as postures approach the wrist's range of motion (ROM). However, reference data for wrist ROM in the Taiwanese population is currently unavailable. This study examined wrist ROM in 250 participants (100 young adults and 150 elderly individuals, equally distributed by sex) using a dual-axis electro-goniometer. Measurements included ulnar deviation, radial deviation, flexion, and extension for both dominant and non-dominant wrists. Analysis of variance identified significant group differences in ulnar deviation (<em>p</em> < 0.001), flexion (<em>p</em> < 0.001), and extension (<em>p</em> < 0.05), with sex and hand dominance significantly influencing ulnar deviation (<em>p</em> < 0.01) and flexion (<em>p</em> < 0.05), respectively. An interaction effect between sex and dominance was observed for flexion (<em>p</em> < 0.05). Compared to the young group, the elderly group exhibited reduced ROM, with decreases of approximately 4° in ulnar deviation, 12° in flexion, and 4° in extension. Females exhibited greater ulnar deviation ROM than males, while the effect of hand dominance on flexion was evident only in males (+4°). Among the elderly cohort, no significant differences in ROM were observed between the 60–69 and 70–90 age subgroups.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"108 ","pages":"Article 103773"},"PeriodicalIF":2.5,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ergonomic design of shoe inserts for reducing lower extremity musculoskeletal discomfort in male Participants: An analysis of shape and size 减少男性参与者下肢肌肉骨骼不适的鞋垫的人体工程学设计：形状和尺寸的分析

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-05-01 DOI: 10.1016/j.ergon.2025.103754

Waseem Ahmad , Md Sarfaraz Alam

Background

The human foot endures substantial forces during daily activities such as walking and standing, often bearing loads 1.5 to 5 times the individual's body weight. These forces propagate through the lower extremity musculoskeletal structures, placing stress on critical joints, which can lead to discomfort, musculoskeletal issues, and reduced productivity. Shoe inserts (SIs) have emerged as effective ergonomic interventions, provided additional support and redistributed pressure to alleviate discomfort and enhance gait stability.

Objective

This study investigates the ergonomic effects of shoe insert placement, shape, and surface area on perceived comfort and plantar pressure distribution during static standing.

Methods

Twenty-six healthy male participants were assessed using flat and contoured inserts of varying surface areas (30 × 30 mm², 40 × 40 mm², and 50 × 50 mm²). Comfort ratings were measured using a Visual Analogue Scale (VAS), while plantar pressures (peak and mean) were evaluated using F-Scan sensors. Data were analysed using paired t-tests and repeated-measures ANOVA, with Bonferroni corrections applied for multiple comparisons.

Results

Inserts placed 2–4 cm anterior to the lateral midfoot region provided the highest comfort ratings. Contoured inserts consistently outperformed flat designs in improving comfort and reducing plantar pressures across all surface areas (p < 0.017). Larger surface area inserts (50 × 50 mm²) were the most effective in enhancing subjective and objective outcomes, demonstrating significant improvements compared to smaller designs (p < 0.001).

Conclusion

This study underscores the importance of precise placement, contoured designs, and larger surface areas in optimizing the ergonomic benefits of shoe inserts. These findings have practical implications for the design of ergonomic footwear and orthotics, particularly for individuals in occupations requiring prolonged standing.

在日常活动中，如走路和站立，人的脚承受着巨大的力量，通常承受着个人体重的1.5至5倍的负荷。这些力量通过下肢肌肉骨骼结构传播，对关键关节施加压力，这可能导致不适，肌肉骨骼问题，并降低生产力。鞋垫（si）已成为有效的人体工程学干预措施，提供额外的支持和重新分配压力，以减轻不适和增强步态稳定性。目的探讨静站立时鞋垫的位置、形状和表面积对感知舒适性和足底压力分布的人体工程学影响。方法采用不同表面积（30 × 30 mm2、40 × 40 mm2和50 × 50 mm2）的平面和轮廓刀片对26名健康男性受试者进行评估。使用视觉模拟量表（VAS）测量舒适度评分，使用F-Scan传感器评估足底压力（峰值和平均值）。数据分析采用配对t检验和重复测量方差分析，多重比较采用Bonferroni校正。结果放置在外侧中足区前2-4 cm处的支架舒适度评分最高。在提高舒适性和减少所有表面区域的足底压力方面，轮廓插入始终优于平面设计(p <；0.017)。较大表面积的植入物（50 × 50 mm2）在增强主观和客观结果方面最有效，与较小的设计相比，显示出显着的改善(p <；0.001)。结论：本研究强调了精确放置、轮廓设计和更大表面积在优化鞋内垫的人体工程学效益方面的重要性。这些发现对人体工程学鞋类和矫形器的设计具有实际意义，特别是对需要长时间站立的职业的个人。

{"title":"Ergonomic design of shoe inserts for reducing lower extremity musculoskeletal discomfort in male Participants: An analysis of shape and size","authors":"Waseem Ahmad , Md Sarfaraz Alam","doi":"10.1016/j.ergon.2025.103754","DOIUrl":"10.1016/j.ergon.2025.103754","url":null,"abstract":"<div><h3>Background</h3><div>The human foot endures substantial forces during daily activities such as walking and standing, often bearing loads 1.5 to 5 times the individual's body weight. These forces propagate through the lower extremity musculoskeletal structures, placing stress on critical joints, which can lead to discomfort, musculoskeletal issues, and reduced productivity. Shoe inserts (SIs) have emerged as effective ergonomic interventions, provided additional support and redistributed pressure to alleviate discomfort and enhance gait stability.</div></div><div><h3>Objective</h3><div>This study investigates the ergonomic effects of shoe insert placement, shape, and surface area on perceived comfort and plantar pressure distribution during static standing.</div></div><div><h3>Methods</h3><div>Twenty-six healthy male participants were assessed using flat and contoured inserts of varying surface areas (30 × 30 mm<sup>2</sup>, 40 × 40 mm<sup>2</sup>, and 50 × 50 mm<sup>2</sup>). Comfort ratings were measured using a Visual Analogue Scale (VAS), while plantar pressures (peak and mean) were evaluated using F-Scan sensors. Data were analysed using paired t-tests and repeated-measures ANOVA, with Bonferroni corrections applied for multiple comparisons.</div></div><div><h3>Results</h3><div>Inserts placed 2–4 cm anterior to the lateral midfoot region provided the highest comfort ratings. Contoured inserts consistently outperformed flat designs in improving comfort and reducing plantar pressures across all surface areas (p < 0.017). Larger surface area inserts (50 × 50 mm<sup>2</sup>) were the most effective in enhancing subjective and objective outcomes, demonstrating significant improvements compared to smaller designs (p < 0.001).</div></div><div><h3>Conclusion</h3><div>This study underscores the importance of precise placement, contoured designs, and larger surface areas in optimizing the ergonomic benefits of shoe inserts. These findings have practical implications for the design of ergonomic footwear and orthotics, particularly for individuals in occupations requiring prolonged standing.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"107 ","pages":"Article 103754"},"PeriodicalIF":2.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A data-driven approach to classifying manual material handling tasks using markerless motion capture and recurrent neural networks 一种使用无标记动作捕捉和循环神经网络对人工材料处理任务进行分类的数据驱动方法

IF 2.5 2区工程技术 Q2 ENGINEERING, INDUSTRIAL

International Journal of Industrial Ergonomics

Pub Date : 2025-05-01 DOI: 10.1016/j.ergon.2025.103755

Aanuoluwapo Ojelade , Mohammad Sadra Rajabi , Sunwook Kim , Maury A. Nussbaum

Work-related musculoskeletal disorders (WMSDs) are prevalent problems that encompass a range of conditions affecting muscles, tendons, and nerves due to repetitive strain, non-neutral postures, and forceful exertions. These disorders lead to pain, reduced productivity and substantial healthcare costs. Effective physical exposure assessment tools are needed in the workplace to quantify WMSD risks and the association between exposure and risks. While several tools are available, they are often limited in scope and lack the ability to assess physical risks continuously. In this study, we evaluated a data-driven approach to continuously classify manual material handling tasks and specific task conditions using different feature sets and machine learning algorithms. Specifically, kinematic data from markerless motion capture (MMC) system was used as input for various recurrent neural networks to classify among eight distinct manual material handling tasks: box lifting, asymmetric box lifting, box carriage, box pushing, box pulling, cart pushing, overhead lifting, and box lowering. The models we tested include bidirectional long-short term memory, gated recurrent units, and bidirectional gated recurrent units. We also classified specific task conditions, such as hand configurations and initial lifting height. Overall, using the MMC's kinematic data led to satisfactory results (e.g., accuracy of 80–94 %) in classifying the tasks and the task conditions. Our results, though, also emphasize that classification performance varied across different feature sets, tasks, and between males and females. Nonetheless, use of MMC demonstrates clear potential for physical exposure assessment.

与工作相关的肌肉骨骼疾病（WMSDs）是一种普遍的问题，包括一系列影响肌肉、肌腱和神经的疾病，原因是重复性劳损、非中性姿势和用力。这些疾病导致疼痛、生产力下降和大量医疗保健费用。工作场所需要有效的物理暴露评估工具来量化WMSD风险以及暴露与风险之间的关系。虽然有几种工具可用，但它们的范围往往有限，并且缺乏持续评估物理风险的能力。在本研究中，我们评估了一种数据驱动的方法，该方法使用不同的特征集和机器学习算法连续分类人工材料处理任务和特定任务条件。具体来说，来自无标记运动捕捉（MMC）系统的运动学数据被用作各种递归神经网络的输入，以分类8种不同的人工物料搬运任务：提箱、非对称提箱、运箱、推箱、拉箱、推车、顶升和放箱。我们测试的模型包括双向长短期记忆、门控循环单元和双向门控循环单元。我们还对具体的任务条件进行了分类，例如手的配置和初始提升高度。总的来说，使用MMC的运动学数据在分类任务和任务条件方面取得了令人满意的结果（例如，准确率为80 - 94%）。然而，我们的结果也强调，分类性能在不同的特征集、任务以及男性和女性之间存在差异。尽管如此，MMC的使用显示了物理暴露评估的明显潜力。

{"title":"A data-driven approach to classifying manual material handling tasks using markerless motion capture and recurrent neural networks","authors":"Aanuoluwapo Ojelade , Mohammad Sadra Rajabi , Sunwook Kim , Maury A. Nussbaum","doi":"10.1016/j.ergon.2025.103755","DOIUrl":"10.1016/j.ergon.2025.103755","url":null,"abstract":"<div><div>Work-related musculoskeletal disorders (WMSDs) are prevalent problems that encompass a range of conditions affecting muscles, tendons, and nerves due to repetitive strain, non-neutral postures, and forceful exertions. These disorders lead to pain, reduced productivity and substantial healthcare costs. Effective physical exposure assessment tools are needed in the workplace to quantify WMSD risks and the association between exposure and risks. While several tools are available, they are often limited in scope and lack the ability to assess physical risks continuously. In this study, we evaluated a data-driven approach to continuously classify manual material handling tasks and specific task conditions using different feature sets and machine learning algorithms. Specifically, kinematic data from markerless motion capture (MMC) system was used as input for various recurrent neural networks to classify among eight distinct manual material handling tasks: box lifting, asymmetric box lifting, box carriage, box pushing, box pulling, cart pushing, overhead lifting, and box lowering. The models we tested include bidirectional long-short term memory, gated recurrent units, and bidirectional gated recurrent units. We also classified specific task conditions, such as hand configurations and initial lifting height. Overall, using the MMC's kinematic data led to satisfactory results (e.g., accuracy of 80–94 %) in classifying the tasks and the task conditions. Our results, though, also emphasize that classification performance varied across different feature sets, tasks, and between males and females. Nonetheless, use of MMC demonstrates clear potential for physical exposure assessment.</div></div>","PeriodicalId":50317,"journal":{"name":"International Journal of Industrial Ergonomics","volume":"107 ","pages":"Article 103755"},"PeriodicalIF":2.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0