Identification of potential improvement assembly movements using worker classification by motion capture and machine learning

Recently, the manufacturing industry has been digitizing skills through motion capture to solve issues such as human resource development and the transmission of skills. However, the amount of data on body movements obtained from motion capture is enormous, and the use of machine learning is required for data mining. This study proposes an identification method for the potential improvement of work by analyzing the differences between experienced and inexperienced worker motion using a classification method with a deep learning software for the worker’s experience level.