Federated Transfer Learning for EEG Signal Classification

Abstract

The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets. Privacy concerns associated with EEG signals limit the possibility of constructing a large EEG-BCI dataset by the conglomeration of multiple small ones for jointly training machine learning models. Hence, in this paper, we propose a novel privacy-preserving DL architecture named federated transfer learning (FTL) for EEG classification that is based on the federated learning framework. Working with the single-trial covariance matrix, the proposed architecture extracts common discriminative information from multi-subject EEG data with the help of domain adaptation techniques. We evaluate the performance of the proposed architecture on the PhysioNet dataset for 2-class motor imagery classification. While avoiding the actual data sharing, our FTL approach achieves 2% higher classification accuracy in a subject-adaptive analysis. Also, in the absence of multi-subject data, our architecture provides 6% better accuracy compared to other state-of-the-art DL architectures.

arXiv comment6 pages, 2 figures, Accepted for IEEE Engineering in Medicine and Biology Society (EMBC) 2020 GitHub: https://github.com/DashanGao/Federated-Transfer-Leraning-for-EEG

References in corpus (1)

• EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces

Cited by in corpus (11)

• Vertical Federated Learning: Concepts, Advances and Challenges
• Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
• Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification
• Privacy-Preserving Brain-Computer Interfaces: A Systematic Review
• Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis
• Federated Motor Imagery Classification for Privacy-Preserving Brain-Computer Interfaces
• PhysioCHI: Towards Best Practices for Integrating Physiological Signals in HCI
• Federated Learning -- Methods, Applications and beyond
• A Distributed Privacy Preserving Model for the Detection of Alzheimer's Disease
• Score-Based Data Generation for EEG Spatial Covariance Matrices: Towards Boosting BCI Performance
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community