Differential Private Federated Transfer Learning for Mental Health Monitoring in Everyday Settings: A Case Study on Stress Detection

TL;DR

This paper presents a novel framework combining differential privacy, federated learning, and transfer learning to improve mental health monitoring, specifically stress detection, while addressing privacy concerns and data limitations.

Contribution

It introduces a differential private federated transfer learning framework that enhances privacy and data sufficiency for mental health monitoring applications.

Findings

Achieved a 10% increase in accuracy.

Realized a 21% improvement in recall.

Ensured privacy protection in stress detection.

Abstract

Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality. The surge in data-driven methodologies for mental health monitoring has underscored the importance of privacy-preserving techniques in handling sensitive health data. Despite strides in federated learning for mental health monitoring, existing approaches struggle with vulnerabilities to certain cyber-attacks and data insufficiency in real-world applications. In this paper, we introduce a differential private federated transfer learning framework for mental health monitoring to enhance data privacy and enrich data sufficiency. To accomplish this, we integrate federated learning with two pivotal elements: (1) differential privacy, achieved by introducing noise into the updates, and (2) transfer learning, employing a pre-trained universal model to adeptly address issues of data imbalance and insufficiency. We evaluate the framework by a case study on stress detection, employing a dataset of physiological and contextual data from a longitudinal study. Our finding show that the proposed approach can attain a 10% boost in accuracy and a 21% enhancement in recall, while ensuring privacy protection.