Deploying a Human Robot Interaction Model for Dementia Care in Federated Learning

Data privacy is the main concern when using machine learning methods to solve dementia care problems. This paper makes the first attempt to deploy a human robot interaction model for dementia care in federated learning settings so that the privacy for persons with dementia (PwDs) can be retained. Numerical experiments of deploying the human-robot interaction model for cognitive therapy in the federated setting is conducted to show the feasibility of the federated learning setting. The simulated experiments in the case study shows the influence of different factors, i.e., client local training speed, the number of clients, homogenous and/or heterogenous patients.