“Chatty Devices” and edge-based activity classification

Abstract With increasing automation of manufacturing processes (focusing on technologies such as robotics and human-robot interaction), there is a realisation that the process artefacts/products it produces can be better connected post-production. Built this requirement, “chatty" factory involves creating products which are able to send data back manufacturing/production environment they used, whilst still ensuring user privacy. The intended use product during design phase may different significantly from actual usage. Understanding how used support continuous refinement, dynamically adapted based availability provides number opportunities. We describe collected to: (i) classify use; (ii) associate label with using unsupervised learning—making edge-based analytics; (iii) transmission cloud where labels compared across same type. Federated learning strategies edge devices ensure any captured analysed locally (ensuring privacy).