Positional multi-length and mutual-attention network for epileptic seizure classification
The automatic classification of epilepsy electroencephalogram (EEG) signals plays a crucial role in diagnosing neurological diseases. Although promising results have been achieved by deep learning methods in this task, capturing the minute abnormal characteristics, contextual information, and long d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2024.1358780/full |
| _version_ | 1797347137056407552 |
|---|---|
| author | Guokai Zhang Aiming Zhang Huan Liu Jihao Luo Jianqing Chen |
| author_facet | Guokai Zhang Aiming Zhang Huan Liu Jihao Luo Jianqing Chen |
| author_sort | Guokai Zhang |
| collection | DOAJ |
| description | The automatic classification of epilepsy electroencephalogram (EEG) signals plays a crucial role in diagnosing neurological diseases. Although promising results have been achieved by deep learning methods in this task, capturing the minute abnormal characteristics, contextual information, and long dependencies of EEG signals remains a challenge. To address this challenge, a positional multi-length and mutual-attention (PMM) network is proposed for the automatic classification of epilepsy EEG signals. The PMM network incorporates a positional feature encoding process that extracts minute abnormal characteristics from the EEG signal and utilizes a multi-length feature learning process with a hierarchy residual dilated LSTM (RDLSTM) to capture long contextual dependencies. Furthermore, a mutual-attention feature reinforcement process is employed to learn the global and relative feature dependencies and enhance the discriminative abilities of the network. To validate the effectiveness PMM network, we conduct extensive experiments on the public dataset and the experimental results demonstrate the superior performance of the PMM network compared to state-of-the-art methods. |
| first_indexed | 2024-03-08T11:43:18Z |
| format | Article |
| id | doaj.art-375d0a7a86834cddb1f973f707c6a268 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-03-08T11:43:18Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-375d0a7a86834cddb1f973f707c6a2682024-01-25T04:24:24ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882024-01-011810.3389/fncom.2024.13587801358780Positional multi-length and mutual-attention network for epileptic seizure classificationGuokai Zhang0Aiming Zhang1Huan Liu2Jihao Luo3Jianqing Chen4School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, ChinaSchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, ChinaDepartment of Hematology, Affiliated Qingdao Central Hospital of Qingdao University, Qingdao Cancer Hospital, Qingdao, ChinaSchool of Computing, National University of Singapore, Singapore, SingaporeDepartment of Otolaryngology, Head and Neck Surgery, Shanghai Ninth People's Hospital, Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, ChinaThe automatic classification of epilepsy electroencephalogram (EEG) signals plays a crucial role in diagnosing neurological diseases. Although promising results have been achieved by deep learning methods in this task, capturing the minute abnormal characteristics, contextual information, and long dependencies of EEG signals remains a challenge. To address this challenge, a positional multi-length and mutual-attention (PMM) network is proposed for the automatic classification of epilepsy EEG signals. The PMM network incorporates a positional feature encoding process that extracts minute abnormal characteristics from the EEG signal and utilizes a multi-length feature learning process with a hierarchy residual dilated LSTM (RDLSTM) to capture long contextual dependencies. Furthermore, a mutual-attention feature reinforcement process is employed to learn the global and relative feature dependencies and enhance the discriminative abilities of the network. To validate the effectiveness PMM network, we conduct extensive experiments on the public dataset and the experimental results demonstrate the superior performance of the PMM network compared to state-of-the-art methods.https://www.frontiersin.org/articles/10.3389/fncom.2024.1358780/fullEEG signalfeature encodingmulti-lengthfeature reinforcementdeep learning |
| spellingShingle | Guokai Zhang Aiming Zhang Huan Liu Jihao Luo Jianqing Chen Positional multi-length and mutual-attention network for epileptic seizure classification Frontiers in Computational Neuroscience EEG signal feature encoding multi-length feature reinforcement deep learning |
| title | Positional multi-length and mutual-attention network for epileptic seizure classification |
| title_full | Positional multi-length and mutual-attention network for epileptic seizure classification |
| title_fullStr | Positional multi-length and mutual-attention network for epileptic seizure classification |
| title_full_unstemmed | Positional multi-length and mutual-attention network for epileptic seizure classification |
| title_short | Positional multi-length and mutual-attention network for epileptic seizure classification |
| title_sort | positional multi length and mutual attention network for epileptic seizure classification |
| topic | EEG signal feature encoding multi-length feature reinforcement deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2024.1358780/full |
| work_keys_str_mv | AT guokaizhang positionalmultilengthandmutualattentionnetworkforepilepticseizureclassification AT aimingzhang positionalmultilengthandmutualattentionnetworkforepilepticseizureclassification AT huanliu positionalmultilengthandmutualattentionnetworkforepilepticseizureclassification AT jihaoluo positionalmultilengthandmutualattentionnetworkforepilepticseizureclassification AT jianqingchen positionalmultilengthandmutualattentionnetworkforepilepticseizureclassification |