research-article

Open access

Riemannian Geometric Instance Filtering for Transfer Learning in Brain-Computer Interfaces

Authors:

Shuailei Zhang,

Dezhi ZhengAuthors Info & Claims

SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems

Pages 1162 - 1167

https://doi.org/10.1145/3560905.3568434

Published: 24 January 2023 Publication History

Abstract

Due to the inter-subject variability of Electroencephalogram(EEG) signals, a long calibration time is required to collect a large number of labeled trials to calibrate classifier parameters before using the Brain-computer Interface(BCI). This challenge greatly limits the practical roll-out of BCIs. To address this problem, we propose a novel instance-based transfer learning framework named Riemannian Geometric Instance Filtering (RGIF) to reduce calibration time without sacrificing accuracy. A new inter-subject similarity metric based on Riemannian geometry is proposed to measure the similarity between a few trials from the target subject and adequate trials from source subjects. The classification model for the target subject is then trained with the help of abundant trials from similar source subjects with high similarity to the target subject. We evaluate our method on two open-source EEG datasets. The results show that our approach improves significantly compared with other baselines. Furthermore, compared with using all source subjects data, our method reduces the training time by at least half and achieves slightly better accuracy.

References

[1]

Jonathan R Wolpaw, Niels Birbaumer, Dennis J McFarland, Gert Pfurtscheller, and Theresa M Vaughan. Brain-computer interfaces for communication and control. Clinical neurophysiology, 113(6):767--791, 2002.

[2]

Rui Na, Dezhi Zheng, Ying Sun, Mingzhe Han, Shuai Wang, Shuailei Zhang, Qianxin Hui, Xinlei Chen, Jun Zhang, and Chun Hu. A wearable low-power collaborative sensing system for high-quality ssvep-bci signal acquisition. IEEE Internet of Things Journal, 9(10):7273--7285, 2021.

[3]

Ying Sun, Wenzheng Ding, Xiaolin Liu, Dezhi Zheng, Xinlei Chen, Qianxin Hui, Rui Na, Shuai Wang, and Shangchun Fan. Cross-subject fusion based on time-weighting canonical correlation analysis in ssvep-bcis. Measurement, 199:111524, 2022.

[4]

Xinqi Jin, Lingkun Li, Fan Dang, Xinlei Chen, and Yunhao Liu. A survey on edge computing for wearable technology. Digital Signal Processing, 125:103146, 2022.

Digital Library

[5]

Francis R Willett, Donald T Avansino, Leigh R Hochberg, Jaimie M Henderson, and Krishna V Shenoy. High-performance brain-to-text communication via handwriting. Nature, 593(7858):249--254, 2021.

[6]

Patrick D Ganzer, Samuel C Colachis 4th, Michael A Schwemmer, David A Friedenberg, Collin F Dunlap, Carly E Swiftney, Adam F Jacobowitz, Doug J Weber, Marcia A Bockbrader, and Gaurav Sharma. Restoring the sense of touch using a sensorimotor demultiplexing neural interface. Cell, 181(4):763--773, 2020.

[7]

Xinlei Chen, Aveek Purohit, Shijia Pan, Carlos Ruiz, Jun Han, Zheng Sun, Frank Mokaya, Patric Tague, and Pei Zhang. Design experiences in minimalistic flying sensor node platform through sensorfly. ACM Transactions on Sensor Networks (TOSN), 13(4):1--37, 2017.

[8]

Shuailei Zhang, Kai Keng Ang, Dezhi Zheng, Qianxin Hui, Xinlei Chen, Yang Li, Ning Tang, Effie Chew, Rosary Yuting Lim, and Cuntai Guan. Learning eeg representations with weighted convolutional siamese network: a large multi-session post-stroke rehabilitation study. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022.

[9]

Ahmed M Azab, Lyudmila Mihaylova, Kai Keng Ang, and Mahnaz Arvaneh. Weighted transfer learning for improving motor imagery-based brain-computer interface. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(7):1352--1359, 2019.

[10]

Kai Zhang, Guanghua Xu, Longtin Chen, Peiyuan Tian, ChengCheng Han, Sicong Zhang, and Nan Duan. Instance transfer subject-dependent strategy for motor imagery signal classification using deep convolutional neural networks. Computational and Mathematical Methods in Medicine, 2020, 2020.

[11]

Xiaolin Liu, Rongye Shi, Qianxin Hui, Susu Xu, Shuai Wang, Rui Na, Ying Sun, Wenbo Ding, Dezhi Zheng, and Xinlei Chen. Tcacnet: Temporal and channel attention convolutional network for motor imagery classification of eeg-based bci. Information Processing & Management, 59(5):103001, 2022.

Digital Library

[12]

Joshua Giles, Kai Keng Ang, Lyudmila S Mihaylova, and Mahnaz Arvaneh. A subject-to-subject transfer learning framework based on jensen-shannon divergence for improving brain-computer interface. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 3087--3091. IEEE, 2019.

[13]

Wojciech Samek, Frank C Meinecke, and Klaus-Robert Müller. Transferring subspaces between subjects in brain-computer interfacing. IEEE Transactions on Biomedical Engineering, 60(8):2289--2298, 2013.

[14]

Vinay Jayaram, Morteza Alamgir, Yasemin Altun, Bernhard Scholkopf, and Moritz Grosse-Wentrup. Transfer learning in brain-computer interfaces. IEEE Computational Intelligence Magazine, 11(1):20--31, 2016.

Digital Library

[15]

Dongye Zhao, Fengzhen Tang, Bailu Si, and Xisheng Feng. Learning joint space-time-frequency features for eeg decoding on small labeled data. Neural Networks, 114:67--77, 2019.

Digital Library

[16]

Kai Zhang, Guanghua Xu, Xiaowei Zheng, Huanzhong Li, Sicong Zhang, Yunhui Yu, and Renghao Liang. Application of transfer learning in eeg decoding based on brain-computer interfaces: A review. Sensors, 20(21):6321, 2020.

[17]

Bianca Zadrozny. Learning and evaluating classifiers under sample selection bias. In Proceedings of the twenty-first international conference on Machine learning, page 114, 2004.

Digital Library

[18]

Marco Congedo, Alexandre Barachant, and Rajendra Bhatia. Riemannian geometry for eeg-based brain-computer interfaces; a primer and a review. Brain-Computer Interfaces, 4(3):155--174, 2017.

[19]

Florian Yger, Maxime Berar, and Fabien Lotte. Riemannian approaches in brain-computer interfaces: a review. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(10):1753--1762, 2016.

[20]

Alexandre Barachant, Stéphane Bonnet, Marco Congedo, and Christian Jutten. Multiclass brain-computer interface classification by riemannian geometry. IEEE Transactions on Biomedical Engineering, 59(4):920--928, 2011.

[21]

Xiaofeng Xie, Zhu Liang Yu, Haiping Lu, Zhenghui Gu, and Yuanqing Li. Motor imagery classification based on bilinear sub-manifold learning of symmetric positive-definite matrices. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(6):504--516, 2016.

[22]

Kaishuo Zhang, Neethu Robinson, Seong-Whan Lee, and Cuntai Guan. Adaptive transfer learning for eeg motor imagery classification with deep convolutional neural network. Neural Networks, 136:1--10, 2021.

[23]

Kai Keng Ang, Zheng Yang Chin, Haihong Zhang, and Cuntai Guan. Filter bank common spatial pattern (fbcsp) in brain-computer interface. In 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), pages 2390--2397. IEEE, 2008.

[24]

Robin Tibor Schirrmeister, Jost Tobias Springenberg, Lukas Dominique Josef Fiederer, Martin Glasstetter, Katharina Eggensperger, Michael Tangermann, Frank Hutter, Wolfram Burgard, and Tonio Ball. Deep learning with convolutional neural networks for eeg decoding and visualization. Human brain mapping, 38(11):5391--5420, 2017.

Cited By

Pan SShen TLian YShi L(2024)A Task-Related EEG Microstate Clustering Algorithm Based on Spatial Patterns, Riemannian Distance, and a Deep AutoencoderBrain Sciences10.3390/brainsci1501002715:1(27)Online publication date: 29-Dec-2024
https://doi.org/10.3390/brainsci15010027
Wang CZhuo YLi HChen X(2024)Poster Abstract: TCT: Zero-training two staged Contrastive Transformer network for SSVEP classification2024 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)10.1109/IPSN61024.2024.00048(295-296)Online publication date: 13-May-2024
https://doi.org/10.1109/IPSN61024.2024.00048
Sun YLiu XNa RWang SZheng DFan S(2023)Cross-domain Feature Distillation Framework for Enhancing Classification in Ear-EEG Brain-Computer InterfacesAdjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing10.1145/3594739.3612911(706-711)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1145/3594739.3612911
Show More Cited By

Index Terms

Riemannian Geometric Instance Filtering for Transfer Learning in Brain-Computer Interfaces
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Instance-based learning
2. Human-centered computing
  1. Human computer interaction (HCI)
    1. HCI design and evaluation methods
      1. User models

Recommendations

Subject-independent meta-learning framework towards optimal training of EEG-based classifiers
Abstract
Advances in deep learning have shown great promise towards the application of performing high-accuracy Electroencephalography (EEG) signal classification in a variety of tasks. However, many EEG-based datasets are often plagued by the issue of ...
Highlights
- The framework optimally learns parameters that generalizes towards target subjects.
- We show how the framework is applied across different EEG classification paradigms.
- State-of-the-art accuracy is achieved while utilizing fewer ...
Quantification of event related brain patterns for the motor imagery tasks using inter-trial variance technique
Abstract
Quantification of event-related (de) synchronization (ERD/ERS) patterns is a challenging task in the field of motor imagery (MI)-based brain–computer interface (BCI). Accurately determining the optimal time and frequency band for localizing the ...
Incremental Training of Neural Network for Motor Tasks Recognition Based on Brain-Computer Interface
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Abstract
Brain-computer interfaces (BCI) based on motor imagery tasks (MI) have been established as a promising solution for restoring communication and control of people with motor disabilities. Physically impaired people may perform different motor ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems

November 2022

1280 pages

ISBN:9781450398862

DOI:10.1145/3560905

General Chairs:
Jeremy Gummeson
University of Massachusetts Amherst
,
Sunghoon Ivan Lee
University of Massachusetts Amherst
,
Program Chairs:
Jie Gao
Rutgers University
,
Guoliang Xing
The Chinese University of Hong Kong

Copyright © 2022 Owner/Author.

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 January 2023

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Universities-Youth Talent Support Program of Beihang University award
National Natural Science Foundation of China
Key Laboratory of Precision Opto-mechatronics Technology, Ministry of Education (Beihang University) award
Institute for Web and Digital Media Research (Beihang University) award

Conference

SenSys '22

Sponsor:

SenSys '22: The 20th ACM Conference on Embedded Networked Sensor Systems

November 6 - 9, 2022

Massachusetts, Boston

Acceptance Rates

SenSys '22 Paper Acceptance Rate 52 of 187 submissions, 28%;

Overall Acceptance Rate 198 of 990 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
327
Total Downloads

Downloads (Last 12 months)166
Downloads (Last 6 weeks)29

Reflects downloads up to 27 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Pan SShen TLian YShi L(2024)A Task-Related EEG Microstate Clustering Algorithm Based on Spatial Patterns, Riemannian Distance, and a Deep AutoencoderBrain Sciences10.3390/brainsci1501002715:1(27)Online publication date: 29-Dec-2024
https://doi.org/10.3390/brainsci15010027
Wang CZhuo YLi HChen X(2024)Poster Abstract: TCT: Zero-training two staged Contrastive Transformer network for SSVEP classification2024 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)10.1109/IPSN61024.2024.00048(295-296)Online publication date: 13-May-2024
https://doi.org/10.1109/IPSN61024.2024.00048
Sun YLiu XNa RWang SZheng DFan S(2023)Cross-domain Feature Distillation Framework for Enhancing Classification in Ear-EEG Brain-Computer InterfacesAdjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing10.1145/3594739.3612911(706-711)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1145/3594739.3612911
Li JGe CTao JWang JXu XChen XGui WLiang XDing W(2023)SolareSkin: Self-powered Visible Light Sensing Through a Solar Cell E-SkinAdjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing10.1145/3594739.3612904(664-669)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1145/3594739.3612904

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten