EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface
A major challenge in EEG-based brain-computer interfaces (BCIs) is the intersession nonstationarity in the EEG data that often leads to deteriorated BCI performances. To address this issue, this letter proposes a novel data space adaptation technique, EEG data space adaptation (EEG-DSA), to linearly...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/100036 http://hdl.handle.net/10220/18440 |
| _version_ | 1826113290122559488 |
|---|---|
| author | Arvaneh, Mahnaz Guan, Cuntai Ang, Kai Keng Quek, Chai |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Arvaneh, Mahnaz Guan, Cuntai Ang, Kai Keng Quek, Chai |
| author_sort | Arvaneh, Mahnaz |
| collection | NTU |
| description | A major challenge in EEG-based brain-computer interfaces (BCIs) is the intersession nonstationarity in the EEG data that often leads to deteriorated BCI performances. To address this issue, this letter proposes a novel data space adaptation technique, EEG data space adaptation (EEG-DSA), to linearly transform the EEG data from the target space (evaluation session), such that the distribution difference to the source space (training session) is minimized. Using the Kullback-Leibler (KL) divergence criterion, we propose two versions of the EEG-DSA algorithm: the supervised version, when labeled data are available in the evaluation session, and the unsupervised version, when labeled data are not available. The performance of the proposed EEG-DSA algorithm is evaluated on the publicly available BCI Competition IV data set IIa and a data set recorded from 16 subjects performing motor imagery tasks on different days. The results show that the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the results without adaptation in terms of classification accuracy. The results also show that for subjects with poor BCI performances when no adaptation is applied, the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the unsupervised bias adaptation algorithm (PMean). |
| first_indexed | 2024-10-01T03:20:46Z |
| format | Journal Article |
| id | ntu-10356/100036 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:20:46Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | ntu-10356/1000362020-05-28T07:17:34Z EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface Arvaneh, Mahnaz Guan, Cuntai Ang, Kai Keng Quek, Chai School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computer applications A major challenge in EEG-based brain-computer interfaces (BCIs) is the intersession nonstationarity in the EEG data that often leads to deteriorated BCI performances. To address this issue, this letter proposes a novel data space adaptation technique, EEG data space adaptation (EEG-DSA), to linearly transform the EEG data from the target space (evaluation session), such that the distribution difference to the source space (training session) is minimized. Using the Kullback-Leibler (KL) divergence criterion, we propose two versions of the EEG-DSA algorithm: the supervised version, when labeled data are available in the evaluation session, and the unsupervised version, when labeled data are not available. The performance of the proposed EEG-DSA algorithm is evaluated on the publicly available BCI Competition IV data set IIa and a data set recorded from 16 subjects performing motor imagery tasks on different days. The results show that the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the results without adaptation in terms of classification accuracy. The results also show that for subjects with poor BCI performances when no adaptation is applied, the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the unsupervised bias adaptation algorithm (PMean). ASTAR (Agency for Sci., Tech. and Research, S’pore) Published version 2014-01-10T04:17:30Z 2019-12-06T20:15:33Z 2014-01-10T04:17:30Z 2019-12-06T20:15:33Z 2013 2013 Journal Article Arvaneh, M., Guan, C., Ang, K. K., & Quek, C. (2013). EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface. Neural computation, 25(8), 2146-2171. 0899-7667 https://hdl.handle.net/10356/100036 http://hdl.handle.net/10220/18440 10.1162/NECO_a_00474 en Neural computation © 2013 Massachusetts Institute of Technology. This paper was published in Neural Computation and is made available as an electronic reprint (preprint) with permission of Massachusetts Institute of Technology. The paper can be found at the following official DOI: [http://dx.doi.org/10.1162/NECO_a_00474]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computer applications Arvaneh, Mahnaz Guan, Cuntai Ang, Kai Keng Quek, Chai EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title | EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title_full | EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title_fullStr | EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title_full_unstemmed | EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title_short | EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface |
| title_sort | eeg data space adaptation to reduce intersession nonstationarity in brain computer interface |
| topic | DRNTU::Engineering::Computer science and engineering::Computer applications |
| url | https://hdl.handle.net/10356/100036 http://hdl.handle.net/10220/18440 |
| work_keys_str_mv | AT arvanehmahnaz eegdataspaceadaptationtoreduceintersessionnonstationarityinbraincomputerinterface AT guancuntai eegdataspaceadaptationtoreduceintersessionnonstationarityinbraincomputerinterface AT angkaikeng eegdataspaceadaptationtoreduceintersessionnonstationarityinbraincomputerinterface AT quekchai eegdataspaceadaptationtoreduceintersessionnonstationarityinbraincomputerinterface |