Hybrid Attention Network for Epileptic EEG Classification

被引:18
作者
Zhao, Yanna [1 ]
He, Jiatong [1 ]
Zhu, Fenglin [1 ]
Xiao, Tiantian [1 ]
Zhang, Yongfeng [1 ]
Wang, Ziwei [1 ]
Xu, Fangzhou [2 ,3 ]
Niu, Yi [1 ]
机构
[1] Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250358, Peoples R China
[2] Qilu Univ Technol, Shandong Acad Sci, Int Sch Optoelect Engn, Jinan 250353, Peoples R China
[3] Jinan Engn Lab Human Machine Intelligent Cooperat, Jinan 250353, Peoples R China
基金
中国国家自然科学基金;
关键词
Seizure detection; EEG; graph attention network; transformer; focal loss; SEIZURE DETECTION;
D O I
10.1142/S0129065723500314
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automatic seizure detection from electroencephalography (EEG) based on deep learning has been significantly improved. However, existing works have not adequately excavate the spatial-temporal information between EEG channels. Besides, most works mainly focus on patient-specific scenarios while cross-patient seizure detection is more challenging and meaningful. Regarding the above problems, we propose a hybrid attention network (HAN) for automatic seizure detection. Specifically, the graph attention network (GAT) extracts spatial features at the front end, and Transformer gets time features as the back end. HAN leverages the attention mechanism and fully extracts the spatial-temporal correlation of EEG signals. The focal loss function is introduced to HAN to deal with the imbalance of the dataset accompanied by seizure detection based on EEG. Both patient-specific and patient-independent experiments are carried out on the public CHB-MIT database. Experimental results demonstrate the efficacy of HAN in both experimental settings.
引用
收藏
页数:14
相关论文
共 69 条
[1]  
Acharya D., 2021, SOFT COMPUTING PROBL, P245
[2]   A spatio-temporal wavelet-chaos methodology for EEG-based diagnosis of Alzheimer's disease [J].
Adeli, Hojjat ;
Ghosh-Dastidar, Samanwoy ;
Dadmehr, Nahid .
NEUROSCIENCE LETTERS, 2008, 444 (02) :190-194
[3]   Spatiotemporal Analysis of Relative Convergence of EEGs Reveals Differences Between Brain Dynamics of Depressive Women and Men [J].
Ahmadlou, Mehran ;
Adeli, Hojjat ;
Adeli, Amir .
CLINICAL EEG AND NEUROSCIENCE, 2013, 44 (03) :175-181
[4]   Leveraging spatial-temporal convolutional features for EEG-based emotion recognition [J].
An, Yi ;
Xu, Ning ;
Qu, Zhen .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 69
[5]   Epileptic Seizure Prediction Using Deep Transformer Model [J].
Bhattacharya, Abhijeet ;
Baweja, Tanmay ;
Karri, S. P. K. .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2022, 32 (02)
[6]   Automatic seizure detection by convolutional neural networks with computational complexity analysis [J].
Cimr, Dalibor ;
Fujita, Hamido ;
Tomaskova, Hana ;
Cimler, Richard ;
Selamat, Ali .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 229
[7]   Epilepsy stigma: Moving from a global problem to global solutions [J].
de Boer, Hanneke M. .
SEIZURE-EUROPEAN JOURNAL OF EPILEPSY, 2010, 19 (10) :630-636
[8]  
Delvigne V., 2022, arXiv
[9]  
Dosovitskiy A, 2021, Arxiv, DOI arXiv:2010.11929
[10]   An Automatic Method for Epileptic Seizure Detection Based on Deep Metric Learning [J].
Duan, Lijuan ;
Wang, Zeyu ;
Qiao, Yuanhua ;
Wang, Yue ;
Huang, Zhaoyang ;
Zhang, Baochang .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (05) :2147-2157