Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification
Motor Imagery (MI) systems in Brain-Computer Interface (BCI) research provide communication and control solutions for individuals with motor impairments, yet cross-subject classification remains challenging due to substantial inter-subject variability. In this study, we propose the Minima Possible W...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10878971/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849716453732777984 |
|---|---|
| author | Quang Pham Lam Dinh Isao Nambu |
| author_facet | Quang Pham Lam Dinh Isao Nambu |
| author_sort | Quang Pham Lam Dinh |
| collection | DOAJ |
| description | Motor Imagery (MI) systems in Brain-Computer Interface (BCI) research provide communication and control solutions for individuals with motor impairments, yet cross-subject classification remains challenging due to substantial inter-subject variability. In this study, we propose the Minima Possible Weights (MPW) method, an unsupervised learning approach designed to enhance MI classification through ensemble deep learning. MPW aggregates predicted probabilities from multiple models and selects the class with the lowest associated weight for the final prediction. We evaluated MPW against various ensemble learning and test-time adaptation methods using two benchmark datasets: BCI Competition IV Dataset 2a and PhysionetMI. Our results indicate that MPW achieves cross-subject classification accuracy of up to 64.75% on BCI Competition IV Dataset 2a and 66.92% on PhysionetMI. Although the current performance is not yet sufficient for practical BCI applications, MPW shows potential in reducing calibration time and easing the burden of adapting models to new subjects. |
| format | Article |
| id | doaj-art-080e7b0acf5347afa443e33448ed1e19 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-080e7b0acf5347afa443e33448ed1e192025-08-20T03:12:58ZengIEEEIEEE Access2169-35362025-01-0113291342914610.1109/ACCESS.2025.354016410878971Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery ClassificationQuang Pham Lam Dinh0https://orcid.org/0009-0008-9560-8823Isao Nambu1https://orcid.org/0000-0002-1705-6268Graduate School of Engineering, Nagaoka University of Technology, Niigata, JapanGraduate School of Engineering, Nagaoka University of Technology, Niigata, JapanMotor Imagery (MI) systems in Brain-Computer Interface (BCI) research provide communication and control solutions for individuals with motor impairments, yet cross-subject classification remains challenging due to substantial inter-subject variability. In this study, we propose the Minima Possible Weights (MPW) method, an unsupervised learning approach designed to enhance MI classification through ensemble deep learning. MPW aggregates predicted probabilities from multiple models and selects the class with the lowest associated weight for the final prediction. We evaluated MPW against various ensemble learning and test-time adaptation methods using two benchmark datasets: BCI Competition IV Dataset 2a and PhysionetMI. Our results indicate that MPW achieves cross-subject classification accuracy of up to 64.75% on BCI Competition IV Dataset 2a and 66.92% on PhysionetMI. Although the current performance is not yet sufficient for practical BCI applications, MPW shows potential in reducing calibration time and easing the burden of adapting models to new subjects.https://ieeexplore.ieee.org/document/10878971/Brain-computer interfacecross-subjectdeep ensemble learningmulti-class classificationmotor imageryunsupervised learning |
| spellingShingle | Quang Pham Lam Dinh Isao Nambu Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification IEEE Access Brain-computer interface cross-subject deep ensemble learning multi-class classification motor imagery unsupervised learning |
| title | Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification |
| title_full | Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification |
| title_fullStr | Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification |
| title_full_unstemmed | Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification |
| title_short | Minima Possible Weights: A Homogenous Deep Ensemble Method for Cross-Subject Motor Imagery Classification |
| title_sort | minima possible weights a homogenous deep ensemble method for cross subject motor imagery classification |
| topic | Brain-computer interface cross-subject deep ensemble learning multi-class classification motor imagery unsupervised learning |
| url | https://ieeexplore.ieee.org/document/10878971/ |
| work_keys_str_mv | AT quangphamlamdinh minimapossibleweightsahomogenousdeepensemblemethodforcrosssubjectmotorimageryclassification AT isaonambu minimapossibleweightsahomogenousdeepensemblemethodforcrosssubjectmotorimageryclassification |