I-Corps: A machine learning approach to reduce musculoskeletal disorders-related injuries among workers performing labor-intensive repetitive tasks

这个i-Corps项目的更广泛的影响/商业潜力是开发一种技术，该技术可以提供特定于任务的最佳人体工学解决方案，以降低执行劳动密集型重复任务的工人发生肌肉骨骼疾病相关伤害(MSD)的风险。在美国，MSD的总成本在每年450亿至540亿美元之间，即每名伤员约15,000美元。这项技术在建筑、搬家服务、杂货店、装配线、清洁服务和仓库等劳动密集型重复性任务普遍存在的行业中有广泛的应用。暴露在与MSD相关的伤害中的工人会遭受生活质量的损失，错过工资，并增加医疗费用。这项拟议的技术可能会帮助他们过上更健康、更好的生活。监督工人的管理人员可能能够维持工作时间表和工作质量，因为减少了现场的健康问题，减少了培训新工人以取代受伤工人的需要。部署工人的公司可能会看到生产率的提高和与工人赔偿相关的索赔的减少。这项拟议的技术也可能对普通公众有用，因为它改善了日常手工重复任务的人体工效学。这个i-Corps项目基于一种软件技术的开发，该技术利用机器学习算法来预测不同身体关节诱导的独特动作和时刻，从而计算出用于劳动密集型重复活动的“安全工作程序”。人体骨骼跟踪技术，如深度传感相机，用于收集工人执行任务的姿势数据。该实时姿势数据作为机器学习模型的输入。工业上的普遍做法是遵守监管机构规定的最低安全标准。与实践相反，该项目实施了一种新的方法来确定现场可达到的最大安全水平，即“安全边界”，这可能会作为监测劳动密集型重复性任务安全的更高基准。此外，该项目确定了“可持续安全”，这是一种在正常工作条件下可以实现和维持的最佳人体工程学解决方案。这些安全级别的引入可能会促进对安全动态的理解，并提供一种全面的方法来分析工人的安全。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is the development of a technology that may provide a task-specific optimal ergonomic solution to reduce the risk of musculoskeletal disorders-related injuries (MSDs) among workers performing labor-intensive repetitive tasks. The total cost of MSDs in the US is between $45-54 billion a year, which is around $15,000 per injury. The technology has a wide range of applications in industries like construction, moving services, grocery stores, assemble lines, cleaning services, and warehouses where labor-intensive repetitive tasks are prevalent. Workers exposed to MSD-related injuries suffer a loss in quality of life, missed wages, and increased health expenses. This proposed technology may help them live a healthier and better life. Managers supervising workers may be able to maintain the work schedule and quality of work because of reductions in health issues on site and reduced need to train new workers to replace the injured ones. The companies deploying the workers potentially may observe increased productivity and decreased workers compensation-related claims. The proposed technology also may be useful to the general public by improving the ergonomics of their day-to-day manual repetitive tasks.This I-Corps project is based on the development of a software technology utilizing a machine-learning algorithm to predict unique actions and moments induced in different body joints to compute a “safe working procedure” for labor-intensive repetitive activities. Human skeletal tracking technology, such as a depth-sensing camera, is used to collect postural data of workers performing their tasks. This real-time posture data serves as the input for the machine learning model. The common practice in industry is to comply with the minimum safety standards prescribed by a regulatory body. Contrary to the practice, the project implements a novel method to identify the maximum achievable level of safety on site, the “Safety Frontier,” which may serve as a higher benchmark in monitoring safety in labor-intensive repetitive tasks. In addition, the project identifies “Sustainable Safety,” an optimal ergonomic solution that may be achieved and sustained under normal working conditions. The introduction of these safety levels may advance the understanding of safety dynamics and provide a holistic approach to analyze safety of workers.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.