Motor imagery EEG signal classification with a multivariate time series approach
Abstract Background Electroencephalogram (EEG) signals record electrical activity on the scalp. Measured signals, especially EEG motor imagery signals, are often inconsistent or distorted, which compromises their classification accuracy. Achieving a reliable classification of motor imagery EEG signa...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-03-01
|
Series: | BioMedical Engineering OnLine |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12938-023-01079-x |
_version_ | 1797859864125374464 |
---|---|
author | I. Velasco A. Sipols C. Simon De Blas L. Pastor S. Bayona |
author_facet | I. Velasco A. Sipols C. Simon De Blas L. Pastor S. Bayona |
author_sort | I. Velasco |
collection | DOAJ |
description | Abstract Background Electroencephalogram (EEG) signals record electrical activity on the scalp. Measured signals, especially EEG motor imagery signals, are often inconsistent or distorted, which compromises their classification accuracy. Achieving a reliable classification of motor imagery EEG signals opens the door to possibilities such as the assessment of consciousness, brain computer interfaces or diagnostic tools. We seek a method that works with a reduced number of variables, in order to avoid overfitting and to improve interpretability. This work aims to enhance EEG signal classification accuracy by using methods based on time series analysis. Previous work on this line, usually took a univariate approach, thus losing the possibility to take advantage of the correlation information existing within the time series provided by the different electrodes. To overcome this problem, we propose a multivariate approach that can fully capture the relationships among the different time series included in the EEG data. To perform the multivariate time series analysis, we use a multi-resolution analysis approach based on the discrete wavelet transform, together with a stepwise discriminant that selects the most discriminant variables provided by the discrete wavelet transform analysis Results Applying this methodology to EEG data to differentiate between the motor imagery tasks of moving either hands or feet has yielded very good classification results, achieving in some cases up to 100% of accuracy for this 2-class pre-processed dataset. Besides, the fact that these results were achieved using a reduced number of variables (55 out of 22,176) can shed light on the relevance and impact of those variables. Conclusions This work has a potentially large impact, as it enables classification of EEG data based on multivariate time series analysis in an interpretable way with high accuracy. The method allows a model with a reduced number of features, facilitating its interpretability and improving overfitting. Future work will extend the application of this classification method to help in diagnosis procedures for detecting brain pathologies and for its use in brain computer interfaces. In addition, the results presented here suggest that this method could be applied to other fields for the successful analysis of multivariate temporal data. |
first_indexed | 2024-04-09T21:36:28Z |
format | Article |
id | doaj.art-0aee529278ce4159bd3c5eda8bdb728e |
institution | Directory Open Access Journal |
issn | 1475-925X |
language | English |
last_indexed | 2024-04-09T21:36:28Z |
publishDate | 2023-03-01 |
publisher | BMC |
record_format | Article |
series | BioMedical Engineering OnLine |
spelling | doaj.art-0aee529278ce4159bd3c5eda8bdb728e2023-03-26T11:15:00ZengBMCBioMedical Engineering OnLine1475-925X2023-03-0122112410.1186/s12938-023-01079-xMotor imagery EEG signal classification with a multivariate time series approachI. Velasco0A. Sipols1C. Simon De Blas2L. Pastor3S. Bayona4Department of Computer Science and Statistics, Rey Juan Carlos UniversityDepartment of Applied Mathematics, Science and Engineering of Materials and Electronic Technology, Rey Juan Carlos UniversityDepartment of Computer Science and Statistics, Rey Juan Carlos UniversityDepartment of Computer Science and Statistics, Rey Juan Carlos UniversityDepartment of Computer Science and Statistics, Rey Juan Carlos UniversityAbstract Background Electroencephalogram (EEG) signals record electrical activity on the scalp. Measured signals, especially EEG motor imagery signals, are often inconsistent or distorted, which compromises their classification accuracy. Achieving a reliable classification of motor imagery EEG signals opens the door to possibilities such as the assessment of consciousness, brain computer interfaces or diagnostic tools. We seek a method that works with a reduced number of variables, in order to avoid overfitting and to improve interpretability. This work aims to enhance EEG signal classification accuracy by using methods based on time series analysis. Previous work on this line, usually took a univariate approach, thus losing the possibility to take advantage of the correlation information existing within the time series provided by the different electrodes. To overcome this problem, we propose a multivariate approach that can fully capture the relationships among the different time series included in the EEG data. To perform the multivariate time series analysis, we use a multi-resolution analysis approach based on the discrete wavelet transform, together with a stepwise discriminant that selects the most discriminant variables provided by the discrete wavelet transform analysis Results Applying this methodology to EEG data to differentiate between the motor imagery tasks of moving either hands or feet has yielded very good classification results, achieving in some cases up to 100% of accuracy for this 2-class pre-processed dataset. Besides, the fact that these results were achieved using a reduced number of variables (55 out of 22,176) can shed light on the relevance and impact of those variables. Conclusions This work has a potentially large impact, as it enables classification of EEG data based on multivariate time series analysis in an interpretable way with high accuracy. The method allows a model with a reduced number of features, facilitating its interpretability and improving overfitting. Future work will extend the application of this classification method to help in diagnosis procedures for detecting brain pathologies and for its use in brain computer interfaces. In addition, the results presented here suggest that this method could be applied to other fields for the successful analysis of multivariate temporal data.https://doi.org/10.1186/s12938-023-01079-xEEGClassificationMulti-resolutionMulti-variate time seriesDiscrete Wavelet Transform (DWT) |
spellingShingle | I. Velasco A. Sipols C. Simon De Blas L. Pastor S. Bayona Motor imagery EEG signal classification with a multivariate time series approach BioMedical Engineering OnLine EEG Classification Multi-resolution Multi-variate time series Discrete Wavelet Transform (DWT) |
title | Motor imagery EEG signal classification with a multivariate time series approach |
title_full | Motor imagery EEG signal classification with a multivariate time series approach |
title_fullStr | Motor imagery EEG signal classification with a multivariate time series approach |
title_full_unstemmed | Motor imagery EEG signal classification with a multivariate time series approach |
title_short | Motor imagery EEG signal classification with a multivariate time series approach |
title_sort | motor imagery eeg signal classification with a multivariate time series approach |
topic | EEG Classification Multi-resolution Multi-variate time series Discrete Wavelet Transform (DWT) |
url | https://doi.org/10.1186/s12938-023-01079-x |
work_keys_str_mv | AT ivelasco motorimageryeegsignalclassificationwithamultivariatetimeseriesapproach AT asipols motorimageryeegsignalclassificationwithamultivariatetimeseriesapproach AT csimondeblas motorimageryeegsignalclassificationwithamultivariatetimeseriesapproach AT lpastor motorimageryeegsignalclassificationwithamultivariatetimeseriesapproach AT sbayona motorimageryeegsignalclassificationwithamultivariatetimeseriesapproach |