A hybrid self-attention deep learning framework for multivariate sleep stage classification
Abstract Background Sleep is a complex and dynamic biological process characterized by different sleep patterns. Comprehensive sleep monitoring and analysis using multivariate polysomnography (PSG) records has achieved significant efforts to prevent sleep-related disorders. To alleviate the time con...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-019-3075-z |
| _version_ | 1819173814151413760 |
|---|---|
| author | Ye Yuan Kebin Jia Fenglong Ma Guangxu Xun Yaqing Wang Lu Su Aidong Zhang |
| author_facet | Ye Yuan Kebin Jia Fenglong Ma Guangxu Xun Yaqing Wang Lu Su Aidong Zhang |
| author_sort | Ye Yuan |
| collection | DOAJ |
| description | Abstract Background Sleep is a complex and dynamic biological process characterized by different sleep patterns. Comprehensive sleep monitoring and analysis using multivariate polysomnography (PSG) records has achieved significant efforts to prevent sleep-related disorders. To alleviate the time consumption caused by manual visual inspection of PSG, automatic multivariate sleep stage classification has become an important research topic in medical and bioinformatics. Results We present a unified hybrid self-attention deep learning framework, namely HybridAtt, to automatically classify sleep stages by capturing channel and temporal correlations from multivariate PSG records. We construct a new multi-view convolutional representation module to learn channel-specific and global view features from the heterogeneous PSG inputs. The hybrid attention mechanism is designed to further fuse the multi-view features by inferring their dependencies without any additional supervision. The learned attentional representation is subsequently fed through a softmax layer to train an end-to-end deep learning model. Conclusions We empirically evaluate our proposed HybridAtt model on a benchmark PSG dataset in two feature domains, referred to as the time and frequency domains. Experimental results show that HybridAtt consistently outperforms ten baseline methods in both feature spaces, demonstrating the effectiveness of HybridAtt in the task of sleep stage classification. |
| first_indexed | 2024-12-22T20:29:03Z |
| format | Article |
| id | doaj.art-838a6ce5ba54489e8b67912ff7787eb8 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-22T20:29:03Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-838a6ce5ba54489e8b67912ff7787eb82022-12-21T18:13:39ZengBMCBMC Bioinformatics1471-21052019-12-0120S1611010.1186/s12859-019-3075-zA hybrid self-attention deep learning framework for multivariate sleep stage classificationYe Yuan0Kebin Jia1Fenglong Ma2Guangxu Xun3Yaqing Wang4Lu Su5Aidong Zhang6College of Information and Communication Engineering, Beijing University of TechnologyCollege of Information and Communication Engineering, Beijing University of TechnologyDepartment of Computer Science and Engineering, State University of New York at BuffaloDepartment of Computer Science, University of VirginiaDepartment of Computer Science and Engineering, State University of New York at BuffaloDepartment of Computer Science and Engineering, State University of New York at BuffaloDepartment of Computer Science, University of VirginiaAbstract Background Sleep is a complex and dynamic biological process characterized by different sleep patterns. Comprehensive sleep monitoring and analysis using multivariate polysomnography (PSG) records has achieved significant efforts to prevent sleep-related disorders. To alleviate the time consumption caused by manual visual inspection of PSG, automatic multivariate sleep stage classification has become an important research topic in medical and bioinformatics. Results We present a unified hybrid self-attention deep learning framework, namely HybridAtt, to automatically classify sleep stages by capturing channel and temporal correlations from multivariate PSG records. We construct a new multi-view convolutional representation module to learn channel-specific and global view features from the heterogeneous PSG inputs. The hybrid attention mechanism is designed to further fuse the multi-view features by inferring their dependencies without any additional supervision. The learned attentional representation is subsequently fed through a softmax layer to train an end-to-end deep learning model. Conclusions We empirically evaluate our proposed HybridAtt model on a benchmark PSG dataset in two feature domains, referred to as the time and frequency domains. Experimental results show that HybridAtt consistently outperforms ten baseline methods in both feature spaces, demonstrating the effectiveness of HybridAtt in the task of sleep stage classification.https://doi.org/10.1186/s12859-019-3075-zAttention mechanismDeep learningSleep stage classificationPolysomnographyMultivariate time series |
| spellingShingle | Ye Yuan Kebin Jia Fenglong Ma Guangxu Xun Yaqing Wang Lu Su Aidong Zhang A hybrid self-attention deep learning framework for multivariate sleep stage classification BMC Bioinformatics Attention mechanism Deep learning Sleep stage classification Polysomnography Multivariate time series |
| title | A hybrid self-attention deep learning framework for multivariate sleep stage classification |
| title_full | A hybrid self-attention deep learning framework for multivariate sleep stage classification |
| title_fullStr | A hybrid self-attention deep learning framework for multivariate sleep stage classification |
| title_full_unstemmed | A hybrid self-attention deep learning framework for multivariate sleep stage classification |
| title_short | A hybrid self-attention deep learning framework for multivariate sleep stage classification |
| title_sort | hybrid self attention deep learning framework for multivariate sleep stage classification |
| topic | Attention mechanism Deep learning Sleep stage classification Polysomnography Multivariate time series |
| url | https://doi.org/10.1186/s12859-019-3075-z |
| work_keys_str_mv | AT yeyuan ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT kebinjia ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT fenglongma ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT guangxuxun ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT yaqingwang ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT lusu ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT aidongzhang ahybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT yeyuan hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT kebinjia hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT fenglongma hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT guangxuxun hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT yaqingwang hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT lusu hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification AT aidongzhang hybridselfattentiondeeplearningframeworkformultivariatesleepstageclassification |