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 50 条
  • [11] DETECTION AND CLASSIFICATION OF EPILEPTIC TRANSIENTS IN THE EEG
    KRISTENSEN, LE
    ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1985, 61 (03): : S49 - S50
  • [12] Functional Connectivity Network based on Graph Analysis of Scalp EEG for Epileptic Classification
    Sargolzaei, Saman
    Cabrerizo, Mercedes
    Goryawala, Mohammed
    Eddin, Anas Salah
    Adjouadi, Malek
    2013 IEEE SIGNAL PROCESSING IN MEDICINE AND BIOLOGY SYMPOSIUM (SPMB), 2013,
  • [13] WTRPNet: An Explainable Graph Feature Convolutional Neural Network for Epileptic EEG Classification
    Xin, Qi
    Hu, Shaohao
    Liu, Shuaiqi
    Zhao, Ling
    Wang, Shuihua
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (03)
  • [14] SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification
    Wang, Jialin
    Gao, Rui
    Zheng, Haotian
    Zhu, Hao
    Shi, C. -J. Richard
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (09) : 12157 - 12171
  • [15] ABC optimized RBF network for classification of EEG signal for epileptic seizure identification
    Satapathy, Sandeep Kumar
    Dehuri, Satchidananda
    Jagadev, Alok Kumar
    EGYPTIAN INFORMATICS JOURNAL, 2017, 18 (01) : 55 - 66
  • [16] Adaptive hybrid attention network for hyperspectral image classification *
    Pande, Shivam
    Banerjee, Biplab
    PATTERN RECOGNITION LETTERS, 2021, 144 : 6 - 12
  • [17] A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism
    Chirasani, Sateesh Kumar Reddy
    Manikandan, Suchetha
    SOFT COMPUTING, 2022, 26 (11) : 5389 - 5397
  • [18] A composite improved attention convolutional network for motor imagery EEG classification
    Liao, Wenzhe
    Miao, Zipeng
    Liang, Shuaibo
    Zhang, Linyan
    Li, Chen
    FRONTIERS IN NEUROSCIENCE, 2025, 19
  • [19] Deep Neural Network with Attention Mechanism for Classification of Motor Imagery EEG
    Huang, Yen-Cheng
    Chang, Jia-Ren
    Chen, Li-Fen
    Chen, Yong-Sheng
    2019 9TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER), 2019, : 1130 - 1133
  • [20] Combined strategy neural network using AR parameters for epileptic EEG signals classification
    Boukari, Nassim
    Djemili, Rafik
    INTERNATIONAL JOURNAL OF BIOMEDICAL ENGINEERING AND TECHNOLOGY, 2016, 21 (01) : 67 - 79