META-EEG: Meta-learning-based class-relevant EEG representation learning for zero-calibration brain–computer interfaces

Ji Wung Han, Soyeon Bak, Jun Mo Kim, Woo Hyeok Choi, Dong Hee Shin, Young Han Son, Tae Eui Kam

Research output: Contribution to journalArticlepeer-review

Abstract

Transfer learning for motor imagery-based brain–computer interfaces (MI-BCIs) struggles with inter-subject variability, hindering its generalization to new users. This paper proposes an advanced implicit transfer learning framework, META-EEG, designed to overcome the challenge arising from inter-subject variability. By incorporating gradient-based meta-learning with an intermittent freezing strategy, META-EEG ensures efficient feature representation learning, providing a robust zero-calibration solution. A comparative analysis reveals that META-EEG significantly outperforms all the baseline methods and competing methods on three different public datasets. Moreover, we demonstrate the efficiency of the proposed model through a neurophysiological and feature-representational analysis. With its robustness and superior performance on challenging datasets, META-EEG provides an effective solution for calibration-free MI-EEG classification, facilitating broader usability.

Original languageEnglish
Article number121986
JournalExpert Systems With Applications
Volume238
DOIs
Publication statusPublished - 2024 Mar 15

Bibliographical note

Publisher Copyright:
© 2023 Elsevier Ltd

Keywords

  • Brain–computer interface
  • Electroencephalography
  • Inter-subject variability
  • Meta-learning
  • Motor imagery
  • Zero-calibration

ASJC Scopus subject areas

  • General Engineering
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'META-EEG: Meta-learning-based class-relevant EEG representation learning for zero-calibration brain–computer interfaces'. Together they form a unique fingerprint.

Cite this