Sustainability of Healthcare Data Analysis IoT-Based Systems Using Deep Federated Learning

Abstract

Due to recent privacy trends and the increase in data breaches in various industries, it has become imperative to adopt new technologies that support data privacy, maintain accuracy, and ensure sustainability at the same time. The healthcare industry is one of the most vulnerable sectors to cyberattacks and data breaches as health data are highly sensitive and distributed in nature. The use of IoT devices with machine learning models to monitor the health status has made the challenge more acute, as it increases the distribution of health data and adds a decentralized structure to healthcare systems. A new privacy-preserving technology, namely, federated learning (FL), is promising for such a challenge as implementing solutions that integrate FL with deep learning, for healthcare applications that rely on IoT, provides several benefits by mainly preserving data privacy, building robust and high accuracy models, and dealing with the decentralized structure, thus achieving sustainability. This article proposes a deep FL (DFL) framework for healthcare data monitoring and analysis using IoT devices. Moreover, it proposes an FL algorithm that addresses the local training data acquisition process. Furthermore, it presents an experiment to detect skin diseases using the proposed framework. The extensive results collected show that the DFL models can preserve data privacy without sharing it, maintain the decentralized structure of the system made by IoT devices, improve the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">area under the curve</i> (AUC) of the model to reach 97%, and reduce the operational costs (OC) for service providers.

Ähnliche Arbeiten