School of Information Science and Engineering, Shandong University, Qingdao, 266237, China.
Center for Optics Research and Engineering, Shandong University, Qingdao, 266237, China.
Med Biol Eng Comput. 2024 Jan;62(1):307-326. doi: 10.1007/s11517-023-02914-y. Epub 2023 Oct 7.
Epilepsy is a chronic brain disease, and identifying seizures based on electroencephalogram (EEG) signals would be conducive to implement interventions to help patients reduce impairment and improve quality of life. In this paper, we propose a classification algorithm to apply dynamical graph neural network with attention mechanism to single channel EEG signals. Empirical mode decomposition (EMD) are adopted to construct graphs and the optimal adjacency matrix is obtained by model optimization. A multilayer dynamic graph neural network with attention mechanism is proposed to learn more discriminative graph features. The MLP-pooling structure is proposed to fuse graph features. We performed 12 classification tasks on the epileptic EEG database of the University of Bonn, and experimental results showed that using 25 runs of ten-fold cross-validation produced the best classification results with an average of 99.83[Formula: see text] accuracy, 99.91[Formula: see text] specificity, 99.78[Formula: see text] sensitivity, 99.87[Formula: see text] precision, and 99.47[Formula: see text] [Formula: see text] score for the 12 classification tasks.
癫痫是一种慢性脑部疾病，基于脑电图（EEG）信号识别癫痫发作有助于实施干预措施，帮助患者减少损伤，提高生活质量。在本文中，我们提出了一种分类算法，将具有注意力机制的动态图神经网络应用于单通道 EEG 信号。采用经验模态分解（EMD）构建图，并通过模型优化得到最优邻接矩阵。提出了一种具有注意力机制的多层动态图神经网络，以学习更具判别力的图特征。提出了 MLP-池化结构来融合图特征。我们在波恩大学的癫痫 EEG 数据库上进行了 12 项分类任务，实验结果表明，使用 25 次十折交叉验证的运行次数可获得最佳分类结果，平均准确率为 99.83[Formula: see text]，特异性为 99.91[Formula: see text]，敏感性为 99.78[Formula: see text]，精度为 99.87[Formula: see text]，12 项分类任务的 F1 得分为 99.47[Formula: see text]。
