A privacy-preserved IoMT-based mental stress detection framework with federated learning.

Internet of Medical Things (IoMT) can be leveraged for periodic sensing and recording of different health parameters using sensors, wireless communications, and computation platforms. Health care systems can be enhanced by using IoMT for remote patient monitoring and data-driven diagnosis powered by machine learning algorithms. In the context of IoMT, federated learning (FL) is an excellent choice to manage machine learning (ML) algorithms to drive this analysis. This is because FL models can be trained in a distributed manner on local heterogeneous datasets that all contribute to the "collective wisdom". The model parameters can be regulated and shared without sharing the actual health data, ensuring confidentiality and security. This paper makes a case for the viability of FL-based analysis of data acquired via IoMT by presenting some use cases and recent work in this area and proposing a novel framework for data analysis using FL specifically in the context of mental stress detection. It shows that FL-based methods can significantly reduce the required communication overhead for each local device from 10.02MB/day up to only 754B/day as compared to non-FL techniques. [ABSTRACT FROM AUTHOR]