Biomechanical Risk Assessment of Human Lifting Tasks via Supervised Classification of Multiple Sensor Data

Manual lifting tasks are among the primary causes of work-related lower back disorders (WLBD), which are the most common and costly musculoskeletal conditions reported. Aiming to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established a method to evaluate lifting activities based on the kinematic parameters of the lift. The resulting Lifting Index (LI) proved to be a good indicator of the associated biomechanical risk, but it only considers job-related factors, is constrained by equations and parameters, and cannot be calculated when lifting is performed with the assistance of a human-robot collaboration technology such as an exoskeleton. In this paper, we exploit a k-nearest neighbors algorithm to combine and compare different types of sensor information in their ability to classify the risk level associated with lifting tasks. Data are collected on eight healthy participants while performing six load lifting under different task conditions. An instantaneous lifting index (i-LI) is estimated to refine the risk computation. Based on it, an actual lifting index (a-LI) is computed to train the learning algorithm. Then, three different data sets are designed, which include only kinematic data, only muscle electrical activity data, and their combination, respectively, and compared based on the algorithm's performance. Results prove that our framework can classify the ergonomic risk level with high accuracy and show its potential in the automatic and comprehensive assessment of lifting tasks. A very similar performance was found among different sensor data, highlighting its generalization capability.