Predicting epileptic seizures based on a multi-convolution fusion network.
10.7507/1001-5515.202502059
- Author:
Xueting SHEN
1
;
Yan PIAO
1
;
Huiru YANG
1
;
Haitong ZHAO
1
Author Information
1. School of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun 130022, P. R. China.
- Publication Type:Journal Article
- Keywords:
Attention mechanism;
Epilepsy prediction;
Focal loss training strategy;
Multi-scale sparse adaptive mechanism
- MeSH:
Humans;
Electroencephalography/methods*;
Epilepsy/physiopathology*;
Neural Networks, Computer;
Seizures/physiopathology*;
Signal Processing, Computer-Assisted;
Algorithms
- From:
Journal of Biomedical Engineering
2025;42(5):987-993
- CountryChina
- Language:Chinese
-
Abstract:
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.
