MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network
<p dir="ltr">Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion art...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2022
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513545973006336 |
|---|---|
| author | Sakib Mahmud (15302404) |
| author2 | Md Shafayet Hossain (21623759) Muhammad E. H. Chowdhury (14150526) Mamun Bin Ibne Reaz (16875933) |
| author2_role | author author author |
| author_facet | Sakib Mahmud (15302404) Md Shafayet Hossain (21623759) Muhammad E. H. Chowdhury (14150526) Mamun Bin Ibne Reaz (16875933) |
| author_role | author |
| dc.creator.none.fl_str_mv | Sakib Mahmud (15302404) Md Shafayet Hossain (21623759) Muhammad E. H. Chowdhury (14150526) Mamun Bin Ibne Reaz (16875933) |
| dc.date.none.fl_str_mv | 2022-12-21T06:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1007/s00521-022-08111-6 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/MLMRS-Net_Electroencephalography_EEG_motion_artifacts_removal_using_a_multi-layer_multi-resolution_spatially_pooled_1D_signal_reconstruction_network/29435972 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biomedical and clinical sciences Clinical sciences Engineering Biomedical engineering Health sciences Health services and systems Electroencephalography (EEG) Motion artifacts correction 1D-segmentation Signal reconstruction Signal to signal synthesis 1D convolutional neural networks (1D-CNN) Deep learning |
| dc.title.none.fl_str_mv | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (<i>η</i>). The proposedMLMRS-Netmodel has shown the best denoising performance, producing an average ΔSNR,<i>η</i>, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of averageηimprovement.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-022-08111-6" target="_blank">https://dx.doi.org/10.1007/s00521-022-08111-6</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_4d6d535341ba3f33c46cc580b1f3d29a |
| identifier_str_mv | 10.1007/s00521-022-08111-6 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/29435972 |
| publishDate | 2022 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction networkSakib Mahmud (15302404)Md Shafayet Hossain (21623759)Muhammad E. H. Chowdhury (14150526)Mamun Bin Ibne Reaz (16875933)Biomedical and clinical sciencesClinical sciencesEngineeringBiomedical engineeringHealth sciencesHealth services and systemsElectroencephalography (EEG)Motion artifacts correction1D-segmentationSignal reconstructionSignal to signal synthesis1D convolutional neural networks (1D-CNN)Deep learning<p dir="ltr">Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (<i>η</i>). The proposedMLMRS-Netmodel has shown the best denoising performance, producing an average ΔSNR,<i>η</i>, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of averageηimprovement.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-022-08111-6" target="_blank">https://dx.doi.org/10.1007/s00521-022-08111-6</a></p>2022-12-21T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00521-022-08111-6https://figshare.com/articles/journal_contribution/MLMRS-Net_Electroencephalography_EEG_motion_artifacts_removal_using_a_multi-layer_multi-resolution_spatially_pooled_1D_signal_reconstruction_network/29435972CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294359722022-12-21T06:00:00Z |
| spellingShingle | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network Sakib Mahmud (15302404) Biomedical and clinical sciences Clinical sciences Engineering Biomedical engineering Health sciences Health services and systems Electroencephalography (EEG) Motion artifacts correction 1D-segmentation Signal reconstruction Signal to signal synthesis 1D convolutional neural networks (1D-CNN) Deep learning |
| status_str | publishedVersion |
| title | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| title_full | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| title_fullStr | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| title_full_unstemmed | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| title_short | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| title_sort | MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network |
| topic | Biomedical and clinical sciences Clinical sciences Engineering Biomedical engineering Health sciences Health services and systems Electroencephalography (EEG) Motion artifacts correction 1D-segmentation Signal reconstruction Signal to signal synthesis 1D convolutional neural networks (1D-CNN) Deep learning |