Federated Transfer Learning for EEG Signal Classification

• Published in: arXiv.org
• Main Authors: Ju, Ce, Gao, Dashan, Mane, Ravikiran, Tan, Ben, Liu, Yang, Guan, Cuntai
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 25.01.2021
• Subjects: Accuracy; Architecture; Classification; Computer Science - Learning; Covariance matrix; Data retrieval; Datasets; Electroencephalography; Human-computer interface; Image classification; Machine learning; Privacy; Signal classification
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2004.12321

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.