Automated Worker’s Skill Evaluation System Based on the Time Series Elemental Processes for Improving Productivity

In order to enhance and improve labor productivity, we have developed an automated system for evaluating the worker’s skills by using labeled latent Dirichlet allocation (L-LDA). Since the L-LDA learns the characteristic motions automatically, we do not need to find and define any features of the motion. The elemental processes are analyzed by the L-LDA. The worker’s skills are evaluated based on the analyzed time series elemental process data. The evaluated worker’s skills are correctness, stability, speed, and rhythm of the work. The results confirmed that our proposed evaluation system is capable of automatically providing a new analysis over the conventional evaluation method with only working time. For example, an evaluation experiment was done to one subject. This result showed the speed category to be lower than the other categories. Then, we know that the subject lacks parallelism work skill. These results give new knowledge that never obtained by the conventional evaluation method.