• Home
  • Search
  • Three-stage transfer learning for motor imagery EEG recognition.
  • Cite Icon8
  • https://doi.org/10.1007/s11517-024-03036-9Copy DOI Icon

Three-stage transfer learning for motor imagery EEG recognition.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Motor imagery (MI) paradigms have been widely used in neural rehabilitation and drowsiness state assessment. The progress in brain-computer interface (BCI) technology has emphasized the importance of accurately and efficiently detecting motor imagery intentions from electroencephalogram (EEG). Despite the recent breakthroughs made in developing EEG-based algorithms for decoding MI, the accuracy and efficiency of these models remain limited by technical challenges posed by cross-subject heterogeneity in EEG data processing and the scarcity of EEG data for training. Inspired by the optimal transport theory, this study aims to develop a novel three-stage transfer learning (TSTL) method, which uses the existing labeled data from a source domain to improve classification performance on an unlabeled target domain. Notably, the proposed method comprises three components, namely, the Riemannian tangent space mapping (RTSM), source domain transformer (SDT), and optimal subspace mapping (OSM). The RTSM maps a symmetric positive definite matrix from the Riemannian space to the tangent space to minimize the marginal probability distribution drift. The SDT transforms the source domain to a target domain by finding the optimal transport mapping matrix to reduce the joint probability distribution differences. The OSM finally maps the transformed source domain and original target domain to the same subspace to further mitigate the distribution discrepancy. The performance of the proposed method was validated on two public BCI datasets, and the average accuracy of the algorithm on two datasets was 72.24% and 69.29%. Our results demonstrated the improved performance of EEG-based MI detection in comparison with state-of-the-art algorithms.

Similar Papers
  • Research Article
  • Citations114

Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification.

  • Jan 01, 2023
  • IEEE Transactions on Neural Systems and Rehabilitation Engineering
  • Qingshan She +5
  • Book Chapter
  • Citations28

A Unified Framework for Domain Adaptation Using Metric Learning on Manifolds

  • Jan 01, 2019
  • Sridhar Mahadevan +2
  • Research Article
  • Citations10

Multi-source transfer learning via optimal transport feature ranking for EEG classification

  • May 28, 2024
  • Neurocomputing
  • Junhao Li +4
  • Research Article
  • Citations2

Supervised and Semisupervised Manifold Embedded Knowledge Transfer in Motor Imagery-Based BCI

  • Oct 17, 2022
  • Computational Intelligence and Neuroscience
  • Yilu Xu +6
  • Research Article
  • Citations11

Transfer learning with data alignment and optimal transport for EEG based motor imagery classification

  • Jan 31, 2024
  • Journal of Neural Engineering
  • Chao Chu +5
  • Research Article
  • Citations4

Multi-layer transfer learning algorithm based on improved common spatial pattern for brain-computer interfaces

  • Mar 01, 2025
  • Journal of Neuroscience Methods
  • Zhuo Cai +4
  • Research Article
  • Citations31

MI-DAGSC: A domain adaptation approach incorporating comprehensive information from MI-EEG signals

  • Aug 09, 2023
  • Neural Networks
  • Dongxue Zhang +3
  • Dissertation

Mitigating technical challenges in brain-computer interfaces for stroke rehabilitation

  • Jan 01, 2024
  • Aarthy Nagarajan
  • Research Article
  • Citations157

Heterogeneous Domain Adaptation: An Unsupervised Approach.

  • Nov 30, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Feng Liu +2
  • Research Article
  • Citations22

EEG-Based Motor Imagery Recognition Framework via Multisubject Dynamic Transfer and Iterative Self-Training.

  • Aug 01, 2024
  • IEEE transactions on neural networks and learning systems
  • He Wang +7
  • Conference Article
  • Citations3

Kernel-based relevant feature extraction to support Motor Imagery classification

  • Sep 01, 2015
  • L Arias-Mora +5
  • Research Article
  • Citations39

Transfer Learning With Optimal Transportation and Frequency Mixup for EEG-Based Motor Imagery Recognition.

  • Jan 01, 2022
  • IEEE Transactions on Neural Systems and Rehabilitation Engineering
  • Peiyin Chen +5
  • PDF
  • Research Article
  • Citations28

Selective Cross-Subject Transfer Learning Based on Riemannian Tangent Space for Motor Imagery Brain-Computer Interface.

  • Nov 03, 2021
  • Frontiers in Neuroscience
  • Yilu Xu +2
  • Research Article

Unlocking Cross-Domain Synergies for Domain Adaptive Semantic Segmentation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Qin Xu +5
  • PDF
  • Research Article
  • Citations9

Generalized Zero-Shot Domain Adaptation for Unsupervised Cross-Domain PolSAR Image Classification

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Rong Gui +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.