64
IRUS Total
Downloads
  Altmetric

Generalizable movement intention recognition with multiple heterogenous EEG datasets

File Description SizeFormat 
23_MI_ICRA_Camera_Ready_spiral.pdfAccepted version1.69 MBAdobe PDFView/Open
Title: Generalizable movement intention recognition with multiple heterogenous EEG datasets
Authors: Gu, X
Han, J
Yang, G-Z
Lo, B
Item Type: Conference Paper
Abstract: Human movement intention recognition is important for human-robot interaction. Existing work based on motor imagery electroencephalogram (EEG) provides a non-invasive and portable solution for intention detection. However, the data-driven methods may suffer from the limited scale and diversity of the training datasets, which result in poor generalization performance on new test subjects. It is practically difficult to directly aggregate data from multiple datasets for training, since they often employ different channels and collected data suffers from significant domain shifts caused by different devices, experiment setup, etc. On the other hand, the inter-subject heterogeneity is also substantial due to individual differences in EEG representations. In this work, we developed two networks to learn from both the shared and the complete channels across datasets, handling inter-subject and inter-dataset heterogeneity respectively. Based on both networks, we further developed an online knowledge co-distillation framework to collaboratively learn from both networks, achieving coherent performance boosts. Experimental results have shown that our proposed method can effectively aggregate knowledge from multiple datasets, demonstrating better generalization in the context of cross-subject validation.
Issue Date: 4-Jul-2023
Date of Acceptance: 17-Jan-2023
URI: http://hdl.handle.net/10044/1/103145
DOI: 10.1109/ICRA48891.2023.10160462
Publisher: IEEE
Start Page: 9858
End Page: 9864
Copyright Statement: Copyright © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Conference Name: the 2023 IEEE International Conference on Robotics and Automation (ICRA)
Publication Status: Published
Start Date: 2023-05-29
Finish Date: 2023-06-02
Conference Place: London, UK
Online Publication Date: 2023-07-04
Appears in Collections:Central Faculty