A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging
Sleep staging is a vital process for evaluating sleep quality and diagnosing sleep-related diseases. Most of the existing automatic sleep staging methods focus on time-domain information and often ignore the transformation relationship between sleep stages. To deal with the above problems, we propos...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10024753/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849762002635849728 |
|---|---|
| author | Guidan Fu Yueying Zhou Peiliang Gong Pengpai Wang Wei Shao Daoqiang Zhang |
| author_facet | Guidan Fu Yueying Zhou Peiliang Gong Pengpai Wang Wei Shao Daoqiang Zhang |
| author_sort | Guidan Fu |
| collection | DOAJ |
| description | Sleep staging is a vital process for evaluating sleep quality and diagnosing sleep-related diseases. Most of the existing automatic sleep staging methods focus on time-domain information and often ignore the transformation relationship between sleep stages. To deal with the above problems, we propose a Temporal-Spectral fused and Attention-based deep neural Network model (TSA-Net) for automatic sleep staging, using a single-channel electroencephalogram (EEG) signal. The TSA-Net is composed of a two-stream feature extractor, feature context learning, and conditional random field (CRF). Specifically, the two-stream feature extractor module can automatically extract and fuse EEG features from time and frequency domains, considering that both temporal and spectral features can provide abundant distinguishing information for sleep staging. Subsequently, the feature context learning module learns the dependencies between features using the multi-head self-attention mechanism and outputs a preliminary sleep stage. Finally, the CRF module further applies transition rules to improve classification performance. We evaluate our model on two public datasets, Sleep-EDF-20 and Sleep-EDF-78. In terms of accuracy, the TSA-Net achieves 86.64% and 82.21% on the Fpz-Cz channel, respectively. The experimental results illustrate that our TSA-Net can optimize the performance of sleep staging and achieve better staging performance than state-of-the-art methods. |
| format | Article |
| id | doaj-art-a4e4a0e6e7344b4fb4bb3c956b5abdd9 |
| institution | DOAJ |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-a4e4a0e6e7344b4fb4bb3c956b5abdd92025-08-20T03:05:52ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102023-01-01311008101810.1109/TNSRE.2023.323885210024753A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep StagingGuidan Fu0https://orcid.org/0000-0002-7985-5102Yueying Zhou1https://orcid.org/0000-0003-0971-9428Peiliang Gong2https://orcid.org/0000-0003-2611-3145Pengpai Wang3https://orcid.org/0000-0002-8414-8146Wei Shao4Daoqiang Zhang5https://orcid.org/0000-0002-5658-7643MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaSleep staging is a vital process for evaluating sleep quality and diagnosing sleep-related diseases. Most of the existing automatic sleep staging methods focus on time-domain information and often ignore the transformation relationship between sleep stages. To deal with the above problems, we propose a Temporal-Spectral fused and Attention-based deep neural Network model (TSA-Net) for automatic sleep staging, using a single-channel electroencephalogram (EEG) signal. The TSA-Net is composed of a two-stream feature extractor, feature context learning, and conditional random field (CRF). Specifically, the two-stream feature extractor module can automatically extract and fuse EEG features from time and frequency domains, considering that both temporal and spectral features can provide abundant distinguishing information for sleep staging. Subsequently, the feature context learning module learns the dependencies between features using the multi-head self-attention mechanism and outputs a preliminary sleep stage. Finally, the CRF module further applies transition rules to improve classification performance. We evaluate our model on two public datasets, Sleep-EDF-20 and Sleep-EDF-78. In terms of accuracy, the TSA-Net achieves 86.64% and 82.21% on the Fpz-Cz channel, respectively. The experimental results illustrate that our TSA-Net can optimize the performance of sleep staging and achieve better staging performance than state-of-the-art methods.https://ieeexplore.ieee.org/document/10024753/Sleep stagingEEGfeature fusionmulti-head attentionconditional random field |
| spellingShingle | Guidan Fu Yueying Zhou Peiliang Gong Pengpai Wang Wei Shao Daoqiang Zhang A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging IEEE Transactions on Neural Systems and Rehabilitation Engineering Sleep staging EEG feature fusion multi-head attention conditional random field |
| title | A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging |
| title_full | A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging |
| title_fullStr | A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging |
| title_full_unstemmed | A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging |
| title_short | A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging |
| title_sort | temporal spectral fused and attention based deep model for automatic sleep staging |
| topic | Sleep staging EEG feature fusion multi-head attention conditional random field |
| url | https://ieeexplore.ieee.org/document/10024753/ |
| work_keys_str_mv | AT guidanfu atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT yueyingzhou atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT peilianggong atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT pengpaiwang atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT weishao atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT daoqiangzhang atemporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT guidanfu temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT yueyingzhou temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT peilianggong temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT pengpaiwang temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT weishao temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging AT daoqiangzhang temporalspectralfusedandattentionbaseddeepmodelforautomaticsleepstaging |