A machine learning approach for improved shop-floor operator support using a two-level collaborative filtering and gamification features
Nikolaos Nikolakis, George Siaterlis, Kosmas Alexopoulos
Abstract
The increasing gap in shopfloor operators’ skillset regarding advanced information and communication technologies along with workforce’s diversity require a cognitive system bridging such technical gaps in order to address evolving production demands and satisfy the human need for self-fulfillment and self-actualization at work. This study discusses on a two-level collaborative filtering approach to improve the distribution of information content provided to an operator for completing a manufacturing activity while considering his or her feedback. A prototype implementation is evaluated in a case study related to the operator’s job rotation on a shopfloor that involves multiple workstations and tasks.