Predicting epileptic seizures based on a multi-convolution fusion network_Journal of Biomedical Engineering

Authors：

SHEN Xueting ,  PIAO Yan , YANG Huiru , ZHAO Haitong

School of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun 130022, P. R. China;

Corresponding?author：

PIAO Yan, Email: piaoyan@cust.edu.cn

Keywords：

Epilepsy prediction; Multi-scale sparse adaptive mechanism; Attention mechanism; Focal loss training strategy

DOI：

10.7507/1001-5515.202502059

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Current epilepsy prediction methods are not effective in characterizing the multi-domain features of complex long-term electroencephalogram (EEG) data, leading to suboptimal prediction performance. Therefore, this paper proposes a novel multi-scale sparse adaptive convolutional network based on multi-head attention mechanism (MS-SACN-MM) model to effectively characterize the multi-domain features. The model first preprocesses the EEG data, constructs multiple convolutional layers to effectively avoid information overload, and uses a multi-layer perceptron and multi-head attention mechanism to focus the network on critical pre-seizure features. Then, it adopts a focal loss training strategy to alleviate class imbalance and enhance the model's robustness. Experimental results show that on the publicly created dataset (CHB-MIT) by MIT and Boston Children's Hospital, the MS-SACN-MM model achieves a maximum accuracy of 0.999 for seizure prediction 10-15 minutes in advance. This demonstrates good predictive performance and holds significant importance for early intervention and intelligent clinical management of epilepsy patients.

1.	Al-Hadeethi H, Abdulla S, Diykh M, et al. Adaptive boost LS-SVM classification approach for time-series signal classification in epileptic seizure diagnosis applications. Expert Systems with Applications, 2020, 161: 113676.
2.	易芳吉, 鐘麗莎, 李章勇. 基于SVM分類器的癲癇腦電時空特征提取方法的研究. 重慶郵電大學學報(自然科學版), 2022, 34(3): 444-450.
3.	Vicnesh J, Hagiwara Y. Accurate detection of seizure using nonlinear parameters extracted from EEG signals. Journal of Mechanics in Medicine and Biology, 2019, 19(1): 1940004.
4.	周夢妮, 崔會芳, 曹銳, 等. 基于排列熵和支持向量機的癲癇發作預測研究. 計算機應用研究, 2019, 36(6): 1696-1699.
5.	Singh K, Malhotra J. Prediction of epileptic seizures from spectral features of intracranial EEG recordings using deep learning approach. Multimed Tools, 2022, 81: 28875-28898 .
6.	Mane R, Robinson N, Vinod A P, et al. A multi-view CNN with novel variancelayer for motor imagery brain computer Interface. Annu Int Conf IEEE Eng Med Biol Soc, 2020: 2950-2953.
7.	Avcu M T, Zhang Z, Chan D W S. Seizure detection using least EEG channels by deep convolutional neural network//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton: IEEE, 2019: 1120-1124.
8.	Yang X, Zhao J, Sun Q, et al. An effective dual self-attention residual network for seizure prediction. IEEE Trans Neural Syst Rehabil Eng, 2021, 29: 1604-1613.
9.	Jia M, Liu W, Duan J, et al. Efficient graph convolutional networks for seizure prediction using scalp EEG. Front Neurosci, 2022, 16: 967116.
10.	廖杰, 李華, 詹聰, 等. 基于 Stockwell 變換結合生成對抗與長短期記憶網絡的半監督癲癇發作預測模型構建. 南方醫科大學學報, 2023, 43(1): 17-28.
11.	Liu S, Wang X, Zhao L, et al. 3DCANN: a spatio-temporal convolution attention neural network for EEG emotion recognition. IEEE J Biomed Health Inform, 2022, 26(11): 5321-5331.
12.	Kumar A J R, Bhanu B. Uncovering hidden emotions with adaptive multi-attention graph networks//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2024: 4822-4831.
13.	歐陽慧, 李宇堂, 婁曉越, 等. 基于小型神經網絡的癲癇發作預測研究. 首都醫科大學學報, 2025, 46(1): 91-98.
14.	Daoud H, Bayoumi M A. Efficient epileptic seizure prediction based on deep learning. IEEE Trans Biomed Circuits Syst, 2019, 13(5): 804-813.
15.	Díaz-Montiel A A, Zhang R, Lankarany M. Optimal graph representations and neural networks for multichannel time series data in seizure phase classification. Sci Rep, 2025, 15: 19552.
16.	王蒙昊, 方慧娟, 龔亨翔, 等. 應用多尺度混合卷積網絡的腦電信號特征提取與識別. 華僑大學學報(自然科學版), 2023, 44(5): 628-635.
17.	黃瑞梅, 杜守洪, 陳子怡, 等. 癲癇腦電及節律波的非線性動力學特征研究. 生物醫學工程學雜志, 2014, 31(1): 18-22.
18.	Xiang J, Li Y, Wu X, et al. Synchronization-based graph spatio-temporal attention network for seizure prediction. Sci, Rep, 2025, 15: 4080.
19.	Sheykhivand S, Rezaii T Y, Mousavi Z, et al. Automatic identification of epileptic seizures from EEG signals using sparse representation-based classification. IEEE Access, 2020, 8: 138834-138845.
20.	陳嘉俊, 劉波, 林偉偉, 等. 基于Transformer的時間序列預測方法綜述. 計算機科學, 2025, 52(6): 96-105.
21.	Guo L, Yu T, Zhao S, et al. Triple-attention-based spatio-temporal-spectral convolutional network for epileptic seizure prediction. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 3915-3926.
22.	Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment. Cam bridge: Massachusetts Institute of Technology, 2009.
23.	馬樂蓉, 李珊珊, 郭帥. PSO-LSTM優化的癲癇預測和分類研究. 天津職業技術師范大學學報, 2024, 34(3): 21-26.
24.	Li Y, Liu Y, Cui W G, et al. Epileptic seizure detection in EEG signals using a unified temporal-spectral squeeze-and-excitation network. IEEE Trans Neural Syst Rehabil Eng, 2020, 28(4): 782-794.
25.	彭睿旻, 江軍, 匡光濤, 等. 基于EEG的癲癇自動檢測: 綜述與展望. 自動化學報, 2022, 48(2): 350.
26.	Truong N D, Nguyen A D, Kuhlmann L, et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw, 2018, 105: 104-111.
27.	Ji H, Xu T, Xue T, et al. An effective usion model for seizure prediction: GAMRNN. Front Neurosci, 2023, 17: 1246995.
28.	Duan L, Hou J, Qiao Y, et al. Epileptic seizure prediction based on convolutional recurrent neural network with multi-timescale//Proceedings of the International Conference on Intelligent Science and Big Data Engineering (ICISBDE), Nanjing: Nanjing University & ICISBDE Organizing Committee, 2019: 139-150.
29.	Lee D, Kim B, Kim T, et al. A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning. Sci Rep, 2024, 14: 1319.
30.	Zhang J, Zheng S, Chen W, et al. A scheme combining feature fusion and hybrid deep learning models for epileptic seizure detection and prediction. Sci Rep, 2024, 14: 16916.

1. Al-Hadeethi H, Abdulla S, Diykh M, et al. Adaptive boost LS-SVM classification approach for time-series signal classification in epileptic seizure diagnosis applications. Expert Systems with Applications, 2020, 161: 113676.
2. 易芳吉, 鐘麗莎, 李章勇. 基于SVM分類器的癲癇腦電時空特征提取方法的研究. 重慶郵電大學學報(自然科學版), 2022, 34(3): 444-450.
3. Vicnesh J, Hagiwara Y. Accurate detection of seizure using nonlinear parameters extracted from EEG signals. Journal of Mechanics in Medicine and Biology, 2019, 19(1): 1940004.
4. 周夢妮, 崔會芳, 曹銳, 等. 基于排列熵和支持向量機的癲癇發作預測研究. 計算機應用研究, 2019, 36(6): 1696-1699.
5. Singh K, Malhotra J. Prediction of epileptic seizures from spectral features of intracranial EEG recordings using deep learning approach. Multimed Tools, 2022, 81: 28875-28898 .
6. Mane R, Robinson N, Vinod A P, et al. A multi-view CNN with novel variancelayer for motor imagery brain computer Interface. Annu Int Conf IEEE Eng Med Biol Soc, 2020: 2950-2953.
7. Avcu M T, Zhang Z, Chan D W S. Seizure detection using least EEG channels by deep convolutional neural network//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton: IEEE, 2019: 1120-1124.
8. Yang X, Zhao J, Sun Q, et al. An effective dual self-attention residual network for seizure prediction. IEEE Trans Neural Syst Rehabil Eng, 2021, 29: 1604-1613.
9. Jia M, Liu W, Duan J, et al. Efficient graph convolutional networks for seizure prediction using scalp EEG. Front Neurosci, 2022, 16: 967116.
10. 廖杰, 李華, 詹聰, 等. 基于 Stockwell 變換結合生成對抗與長短期記憶網絡的半監督癲癇發作預測模型構建. 南方醫科大學學報, 2023, 43(1): 17-28.
11. Liu S, Wang X, Zhao L, et al. 3DCANN: a spatio-temporal convolution attention neural network for EEG emotion recognition. IEEE J Biomed Health Inform, 2022, 26(11): 5321-5331.
12. Kumar A J R, Bhanu B. Uncovering hidden emotions with adaptive multi-attention graph networks//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2024: 4822-4831.
13. 歐陽慧, 李宇堂, 婁曉越, 等. 基于小型神經網絡的癲癇發作預測研究. 首都醫科大學學報, 2025, 46(1): 91-98.
14. Daoud H, Bayoumi M A. Efficient epileptic seizure prediction based on deep learning. IEEE Trans Biomed Circuits Syst, 2019, 13(5): 804-813.
15. Díaz-Montiel A A, Zhang R, Lankarany M. Optimal graph representations and neural networks for multichannel time series data in seizure phase classification. Sci Rep, 2025, 15: 19552.
16. 王蒙昊, 方慧娟, 龔亨翔, 等. 應用多尺度混合卷積網絡的腦電信號特征提取與識別. 華僑大學學報(自然科學版), 2023, 44(5): 628-635.
17. 黃瑞梅, 杜守洪, 陳子怡, 等. 癲癇腦電及節律波的非線性動力學特征研究. 生物醫學工程學雜志, 2014, 31(1): 18-22.
18. Xiang J, Li Y, Wu X, et al. Synchronization-based graph spatio-temporal attention network for seizure prediction. Sci, Rep, 2025, 15: 4080.
19. Sheykhivand S, Rezaii T Y, Mousavi Z, et al. Automatic identification of epileptic seizures from EEG signals using sparse representation-based classification. IEEE Access, 2020, 8: 138834-138845.
20. 陳嘉俊, 劉波, 林偉偉, 等. 基于Transformer的時間序列預測方法綜述. 計算機科學, 2025, 52(6): 96-105.
21. Guo L, Yu T, Zhao S, et al. Triple-attention-based spatio-temporal-spectral convolutional network for epileptic seizure prediction. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 3915-3926.
22. Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment. Cam bridge: Massachusetts Institute of Technology, 2009.
23. 馬樂蓉, 李珊珊, 郭帥. PSO-LSTM優化的癲癇預測和分類研究. 天津職業技術師范大學學報, 2024, 34(3): 21-26.
24. Li Y, Liu Y, Cui W G, et al. Epileptic seizure detection in EEG signals using a unified temporal-spectral squeeze-and-excitation network. IEEE Trans Neural Syst Rehabil Eng, 2020, 28(4): 782-794.
25. 彭睿旻, 江軍, 匡光濤, 等. 基于EEG的癲癇自動檢測: 綜述與展望. 自動化學報, 2022, 48(2): 350.
26. Truong N D, Nguyen A D, Kuhlmann L, et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw, 2018, 105: 104-111.
27. Ji H, Xu T, Xue T, et al. An effective usion model for seizure prediction: GAMRNN. Front Neurosci, 2023, 17: 1246995.
28. Duan L, Hou J, Qiao Y, et al. Epileptic seizure prediction based on convolutional recurrent neural network with multi-timescale//Proceedings of the International Conference on Intelligent Science and Big Data Engineering (ICISBDE), Nanjing: Nanjing University & ICISBDE Organizing Committee, 2019: 139-150.
29. Lee D, Kim B, Kim T, et al. A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning. Sci Rep, 2024, 14: 1319.
30. Zhang J, Zheng S, Chen W, et al. A scheme combining feature fusion and hybrid deep learning models for epileptic seizure detection and prediction. Sci Rep, 2024, 14: 16916.

Journal of Biomedical Engineering

Latest ArticlesPredicting epileptic seizures based on a multi-convolution fusion network

Abstract Full text Figures/Tables Video References Cited by

Format

Content