An attention-based deep learning approach for sleep stage classification with single-channel EEG
Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155623 |
| _version_ | 1826113450335535104 |
|---|---|
| author | Eldele, Emadeldeen Chen, Zhenghua Liu, Chengyu Wu, Min Kwoh, Chee Keong Li, Xiaoli Guan, Cuntai |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Eldele, Emadeldeen Chen, Zhenghua Liu, Chengyu Wu, Min Kwoh, Chee Keong Li, Xiaoli Guan, Cuntai |
| author_sort | Eldele, Emadeldeen |
| collection | NTU |
| description | Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction module based on multi-resolution convolutional neural network (MRCNN) and adaptive feature recalibration (AFR). The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features. The second module is the temporal context encoder (TCE) that leverages a multi-head attention mechanism to capture the temporal dependencies among the extracted features. Particularly, the multi-head attention deploys causal convolutions to model the temporal relations in the input features. We evaluate the performance of our proposed AttnSleep model using three public datasets. The results show that our AttnSleep outperforms state-of-the-art techniques in terms of different evaluation metrics. Our source codes, experimental data, and supplementary materials are available at https://github.com/emadeldeen24/AttnSleep. |
| first_indexed | 2024-10-01T03:23:26Z |
| format | Journal Article |
| id | ntu-10356/155623 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:23:26Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1556232022-03-14T02:33:26Z An attention-based deep learning approach for sleep stage classification with single-channel EEG Eldele, Emadeldeen Chen, Zhenghua Liu, Chengyu Wu, Min Kwoh, Chee Keong Li, Xiaoli Guan, Cuntai School of Computer Science and Engineering Computer and Information Science Engineering Sleep stage classification, sleep-edf, SHHS Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction module based on multi-resolution convolutional neural network (MRCNN) and adaptive feature recalibration (AFR). The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features. The second module is the temporal context encoder (TCE) that leverages a multi-head attention mechanism to capture the temporal dependencies among the extracted features. Particularly, the multi-head attention deploys causal convolutions to model the temporal relations in the input features. We evaluate the performance of our proposed AttnSleep model using three public datasets. The results show that our AttnSleep outperforms state-of-the-art techniques in terms of different evaluation metrics. Our source codes, experimental data, and supplementary materials are available at https://github.com/emadeldeen24/AttnSleep. Agency for Science, Technology and Research (A*STAR) Published version The work of Emadeldeen Eldele was supported by A*STAR SINGA Scholarship. 2022-03-14T02:33:26Z 2022-03-14T02:33:26Z 2021 Journal Article Eldele, E., Chen, Z., Liu, C., Wu, M., Kwoh, C. K., Li, X. & Guan, C. (2021). An attention-based deep learning approach for sleep stage classification with single-channel EEG. IEEE Transactions On Neural Systems and Rehabilitation Engineering, 29, 809-818. https://dx.doi.org/10.1109/TNSRE.2021.3076234 1534-4320 https://hdl.handle.net/10356/155623 10.1109/TNSRE.2021.3076234 33909566 2-s2.0-85105092101 29 809 818 en IEEE Transactions on Neural Systems and Rehabilitation Engineering 10.21979/N9/EUHGHS 10.21979/N9/EAMYFO 10.21979/N9/MA1AVG © 2021 The Author(s). Published by IEEE. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ application/pdf |
| spellingShingle | Computer and Information Science Engineering Sleep stage classification, sleep-edf, SHHS Eldele, Emadeldeen Chen, Zhenghua Liu, Chengyu Wu, Min Kwoh, Chee Keong Li, Xiaoli Guan, Cuntai An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title | An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title_full | An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title_fullStr | An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title_full_unstemmed | An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title_short | An attention-based deep learning approach for sleep stage classification with single-channel EEG |
| title_sort | attention based deep learning approach for sleep stage classification with single channel eeg |
| topic | Computer and Information Science Engineering Sleep stage classification, sleep-edf, SHHS |
| url | https://hdl.handle.net/10356/155623 |
| work_keys_str_mv | AT eldeleemadeldeen anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT chenzhenghua anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT liuchengyu anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT wumin anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT kwohcheekeong anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT lixiaoli anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT guancuntai anattentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT eldeleemadeldeen attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT chenzhenghua attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT liuchengyu attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT wumin attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT kwohcheekeong attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT lixiaoli attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg AT guancuntai attentionbaseddeeplearningapproachforsleepstageclassificationwithsinglechanneleeg |