Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China.
Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China; Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China; CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China; Engineering Research Center of Open Source Software and Real-Time System (Lanzhou University), Ministry of Education, Lanzhou, China.
Comput Biol Med. 2021 May;132:104338. doi: 10.1016/j.compbiomed.2021.104338. Epub 2021 Mar 16.
Epileptic seizure detection is of great significance in the diagnosis of epilepsy and relieving the heavy workload of visual inspection of electroencephalogram (EEG) recordings. This paper presents a novel method for seizure detection using the Stein kernel-based sparse representation (SR) for EEG recordings. Different from the traditional SR scheme that works with vector data in Euclidean space, the Stein kernel-based SR framework is constructed for seizure detection in the space of the symmetric positive definite (SPD) matrices, which form a Riemannian manifold. Due to the non-Euclidean geometry of the Riemannian manifold, the Stein kernel on the manifold permits the embedding of the manifold in a high-dimensional reproducing kernel Hilbert space (RKHS) to perform SR. In the Stein kernel-based SR framework, EEG samples are described by SPD matrices in the form of covariance descriptors (CovDs). Then, a test EEG sample is sparsely represented on the training set, and the test sample is classified as a member of the class, which leads to the minimum reconstructed residual. Finally, by using three widely used EEG datasets to evaluate the detection performance of the proposed method, the experimental results demonstrate that it achieves good classification accuracy on each dataset. Furthermore, the fast computational speed of the Stein kernel-based SR also meets the basic requirements for real-time seizure detection.
癫痫发作检测在癫痫诊断和减轻脑电图 (EEG) 记录的视觉检查的繁重工作负荷方面具有重要意义。本文提出了一种使用基于 Stein 核的稀疏表示 (SR) 对 EEG 记录进行癫痫发作检测的新方法。与在欧几里得空间中使用向量数据的传统 SR 方案不同，基于 Stein 核的 SR 框架是在对称正定 (SPD) 矩阵的空间中构建的，该空间形成了黎曼流形。由于黎曼流形的非欧几里得几何形状，流形上的 Stein 核允许将流形嵌入到高维再生核希尔伯特空间 (RKHS) 中以执行 SR。在基于 Stein 核的 SR 框架中，EEG 样本通过协方差描述符 (CovD) 以 SPD 矩阵的形式表示。然后，测试 EEG 样本在训练集上进行稀疏表示，并将测试样本分类为导致重建残差最小的类成员。最后，通过使用三个广泛使用的 EEG 数据集来评估所提出方法的检测性能，实验结果表明，该方法在每个数据集上都实现了良好的分类准确性。此外，基于 Stein 核的 SR 的快速计算速度也满足了实时癫痫发作检测的基本要求。
