Seizure Prediction Based on Transformer Using Scalp Electroencephalogram
Epilepsy is a chronic and recurrent brain dysfunction disease. An acute epileptic attack will interfere with a patient’s normal behavior and consciousness, having a great impact on their life. The purpose of this study was to design a seizure prediction model to improve the quality of patients’ live...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4158 |
| _version_ | 1827673399199006720 |
|---|---|
| author | Jianzhuo Yan Jinnan Li Hongxia Xu Yongchuan Yu Tianyu Xu |
| author_facet | Jianzhuo Yan Jinnan Li Hongxia Xu Yongchuan Yu Tianyu Xu |
| author_sort | Jianzhuo Yan |
| collection | DOAJ |
| description | Epilepsy is a chronic and recurrent brain dysfunction disease. An acute epileptic attack will interfere with a patient’s normal behavior and consciousness, having a great impact on their life. The purpose of this study was to design a seizure prediction model to improve the quality of patients’ lives and assist doctors in making diagnostic decisions. This paper presents a transformer-based seizure prediction model. Firstly, the time-frequency characteristics of electroencephalogram (EEG) signals were extracted by short-time Fourier transform (STFT). Secondly, a three transformer tower model was used to fuse and classify the features of the EEG signals. Finally, when combined with the attention mechanism of transformer networks, the EEG signal was processed as a whole, which solves the problem of length limitations in deep learning models. Experiments were conducted with a Children’s Hospital Boston and the Massachusetts Institute of Technology database to evaluate the performance of the model. The experimental results show that, compared with previous EEG classification models, our model can enhance the ability to use time, frequency, and channel information from EEG signals to improve the accuracy of seizure prediction. |
| first_indexed | 2024-03-10T04:23:17Z |
| format | Article |
| id | doaj.art-d9747641a05942f9965d50f3310b9ad7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:23:17Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d9747641a05942f9965d50f3310b9ad72023-11-23T07:45:03ZengMDPI AGApplied Sciences2076-34172022-04-01129415810.3390/app12094158Seizure Prediction Based on Transformer Using Scalp ElectroencephalogramJianzhuo Yan0Jinnan Li1Hongxia Xu2Yongchuan Yu3Tianyu Xu4Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaEpilepsy is a chronic and recurrent brain dysfunction disease. An acute epileptic attack will interfere with a patient’s normal behavior and consciousness, having a great impact on their life. The purpose of this study was to design a seizure prediction model to improve the quality of patients’ lives and assist doctors in making diagnostic decisions. This paper presents a transformer-based seizure prediction model. Firstly, the time-frequency characteristics of electroencephalogram (EEG) signals were extracted by short-time Fourier transform (STFT). Secondly, a three transformer tower model was used to fuse and classify the features of the EEG signals. Finally, when combined with the attention mechanism of transformer networks, the EEG signal was processed as a whole, which solves the problem of length limitations in deep learning models. Experiments were conducted with a Children’s Hospital Boston and the Massachusetts Institute of Technology database to evaluate the performance of the model. The experimental results show that, compared with previous EEG classification models, our model can enhance the ability to use time, frequency, and channel information from EEG signals to improve the accuracy of seizure prediction.https://www.mdpi.com/2076-3417/12/9/4158transformerSTFTepilepsyelectroencephalogramseizure prediction |
| spellingShingle | Jianzhuo Yan Jinnan Li Hongxia Xu Yongchuan Yu Tianyu Xu Seizure Prediction Based on Transformer Using Scalp Electroencephalogram Applied Sciences transformer STFT epilepsy electroencephalogram seizure prediction |
| title | Seizure Prediction Based on Transformer Using Scalp Electroencephalogram |
| title_full | Seizure Prediction Based on Transformer Using Scalp Electroencephalogram |
| title_fullStr | Seizure Prediction Based on Transformer Using Scalp Electroencephalogram |
| title_full_unstemmed | Seizure Prediction Based on Transformer Using Scalp Electroencephalogram |
| title_short | Seizure Prediction Based on Transformer Using Scalp Electroencephalogram |
| title_sort | seizure prediction based on transformer using scalp electroencephalogram |
| topic | transformer STFT epilepsy electroencephalogram seizure prediction |
| url | https://www.mdpi.com/2076-3417/12/9/4158 |
| work_keys_str_mv | AT jianzhuoyan seizurepredictionbasedontransformerusingscalpelectroencephalogram AT jinnanli seizurepredictionbasedontransformerusingscalpelectroencephalogram AT hongxiaxu seizurepredictionbasedontransformerusingscalpelectroencephalogram AT yongchuanyu seizurepredictionbasedontransformerusingscalpelectroencephalogram AT tianyuxu seizurepredictionbasedontransformerusingscalpelectroencephalogram |