MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification
Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI...
| Main Authors: | , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162519 |
| _version_ | 1826120378819280896 |
|---|---|
| author | Autthasan, Phairot Chaisaen, Rattanaphon Sudhawiyangkul, Thapanun Rangpong, Phurin Kiatthaveephong, Suktipol Dilokthanakul, Nat Bhakdisongkhram, Gun Phan, Huy Guan, Cuntai Wilaiprasitporn, Theerawit |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Autthasan, Phairot Chaisaen, Rattanaphon Sudhawiyangkul, Thapanun Rangpong, Phurin Kiatthaveephong, Suktipol Dilokthanakul, Nat Bhakdisongkhram, Gun Phan, Huy Guan, Cuntai Wilaiprasitporn, Theerawit |
| author_sort | Autthasan, Phairot |
| collection | NTU |
| description | Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subjectindependent manner. Methods: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. Results: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. Conclusion: We demonstrate that MIN2Net improves discriminative information in the latent representation. Significance: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration. |
| first_indexed | 2024-10-01T05:15:12Z |
| format | Journal Article |
| id | ntu-10356/162519 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:15:12Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1625192022-10-26T06:34:23Z MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification Autthasan, Phairot Chaisaen, Rattanaphon Sudhawiyangkul, Thapanun Rangpong, Phurin Kiatthaveephong, Suktipol Dilokthanakul, Nat Bhakdisongkhram, Gun Phan, Huy Guan, Cuntai Wilaiprasitporn, Theerawit School of Computer Science and Engineering Engineering::Computer science and engineering Brain-Computer Interfaces Motor Imagery Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subjectindependent manner. Methods: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. Results: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. Conclusion: We demonstrate that MIN2Net improves discriminative information in the latent representation. Significance: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration. This work was supported in part by PTT Public Company Limited, in part by The SCB Public Company Limited, in part by Thailand Science Research, and Innovation under Grant SRI62W1501, in part by The Office of the Permanent Secretary of the Ministry of Higher Education, Science, Research, and Innovation, Thailand under Grant RGNS63-252, and in part by the National Research Council of Thailand under Grant N41A640131. 2022-10-26T06:31:33Z 2022-10-26T06:31:33Z 2021 Journal Article Autthasan, P., Chaisaen, R., Sudhawiyangkul, T., Rangpong, P., Kiatthaveephong, S., Dilokthanakul, N., Bhakdisongkhram, G., Phan, H., Guan, C. & Wilaiprasitporn, T. (2022). MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification. IEEE Transactions On Bio-Medical Engineering, 69(6), 2105-2118. https://dx.doi.org/10.1109/TBME.2021.3137184 0018-9294 https://hdl.handle.net/10356/162519 10.1109/TBME.2021.3137184 34932469 2-s2.0-85122078918 6 69 2105 2118 en IEEE Transactions on Bio-Medical Engineering © 2021 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Brain-Computer Interfaces Motor Imagery Autthasan, Phairot Chaisaen, Rattanaphon Sudhawiyangkul, Thapanun Rangpong, Phurin Kiatthaveephong, Suktipol Dilokthanakul, Nat Bhakdisongkhram, Gun Phan, Huy Guan, Cuntai Wilaiprasitporn, Theerawit MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title | MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title_full | MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title_fullStr | MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title_full_unstemmed | MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title_short | MIN2Net: end-to-end multi-task learning for subject-independent motor imagery EEG classification |
| title_sort | min2net end to end multi task learning for subject independent motor imagery eeg classification |
| topic | Engineering::Computer science and engineering Brain-Computer Interfaces Motor Imagery |
| url | https://hdl.handle.net/10356/162519 |
| work_keys_str_mv | AT autthasanphairot min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT chaisaenrattanaphon min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT sudhawiyangkulthapanun min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT rangpongphurin min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT kiatthaveephongsuktipol min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT dilokthanakulnat min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT bhakdisongkhramgun min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT phanhuy min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT guancuntai min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification AT wilaiprasitporntheerawit min2netendtoendmultitasklearningforsubjectindependentmotorimageryeegclassification |