FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare

TLDR

Wearable devices enable easy collection of health data, and smart healthcare relies on machine learning trained on large user datasets, but data isolation and privacy concerns hinder aggregation and personalization. The authors propose FedHealth, a federated transfer learning framework for wearable healthcare to address data isolation and personalization issues. FedHealth aggregates data via federated learning and then applies transfer learning to build personalized models. Experiments on activity recognition and Parkinson’s disease diagnosis demonstrate that FedHealth delivers accurate, personalized healthcare while preserving privacy, and it is generalizable to other applications.

Abstract

With the rapid development of computing technology, wearable devices make it easy to get access to people's health information. Smart healthcare achieves great success by training machine learning models on a large quantity of user personal data. However, there are two critical challenges. First, user data often exist in the form of isolated islands, making it difficult to perform aggregation without compromising privacy security. Second, the models trained on the cloud fail on personalization. In this article, we propose FedHealth, the first federated transfer learning framework for wearable healthcare to tackle these challenges. FedHealth performs data aggregation through federated learning, and then builds relatively personalized models by transfer learning. Wearable activity recognition experiments and real Parkinson's disease auxiliary diagnosis application have evaluated that FedHealth is able to achieve accurate and personalized healthcare without compromising privacy and security. FedHealth is general and extensible in many healthcare applications.