FedCure: A Heterogeneity-Aware Personalized Federated Learning Framework for Intelligent Healthcare Applications in IoMT Environments
Sachin D.N., B. Annappa, Saumya Hegde, Chunduru Sri Abhijit, Sateesh Ambesange
Abstract
The emergence of the Internet of Medical Things (IoMT) devices has sparked a healthcare revolution, ushering in a new era of intelligent applications powered by Artificial Intelligence (AI). These innovative technologies have substantially impacted the healthcare field and have played a vital role in improving the quality of life on a global scale. Recently, Federated Learning (FL) has gained popularity as a technique to create universally shareable models using the vast datasets collected from IoMT devices, all while preserving data privacy. However, the intricate variations in IoMT environments, including diverse devices, data characteristics, and model complexities, pose challenges to the straightforward application of traditional FL methods. Consequently, it is not ideally suited for deployment in such contexts. This paper introduces FedCure, a personalized FL framework tailored for intelligent IoMT-based healthcare applications operating within a cloud-edge architecture. FedCure is adept at addressing the challenges within IoMT environments by employing personalized FL techniques that can effectively mitigate the impact of heterogeneity. Furthermore, the integration of edge computing technology enhances processing speed and minimizes latency in intelligent IoMT applications. Lastly, this research showcases several case studies encompassing IoMT-based applications, such as Eye Retinopathy Detection, Diabetes Monitoring, Maternal Health, Remote Health Monitoring, and Human Activity Recognition. These case studies provide a means to assess the effectiveness of the proposed FedCure framework and showcase exceptional performance with accuracy and minimal communication overhead, especially in addressing the challenges posed by heterogeneity.