Wang Fengqin, Ke Hengjin
Huangshi Key Laboratory of Photoelectric Technology and Materials, College of Physics and Electronics Science, Hubei Normal University, Huangshi, China.
Computer School, Wuhan University, Wuhan, China.
Front Hum Neurosci. 2018 Oct 2;12:396. doi: 10.3389/fnhum.2018.00396. eCollection 2018.
A longstanding challenge in epilepsy research and practice is the need to classify synchronization patterns hidden in multivariate electroencephalography (EEG) data that is routinely superimposed with intensive noise. It is essential to select a suitable feature extraction method to achieve high recognition performance. A typical approach is to extract the mutual information (MI) between pairs of channels. This calculation, which considers the differences between the sequence pairs to build a reasonable partition, can improve the classification performance. On this basis, however, it is even more difficult to adaptively classify the synchronization patterns hidden in multivariate EEG data under circumstances of insufficient knowledge of domain dependency, such as denoising, feature extraction on a special patient, etc. To address these problems by (1) effectively calculating the MI matrix (synchronization pattern) and (2) accurately classifying the seizure or non-seizure state, this study first accurately measures the synchronization between channel pairs in terms of affinity propagation clustering partition MI (APCPMI). The global synchronization measurement is then obtained by organizing APCPMIs of all channel pairs into a correlation matrix. Finally, a cross-layer fully connected net is designed to characterize the synchronization dynamics correlation matrices adaptively and identify seizure or non-seizure states automatically. Experiments are performed using the CHB-MIT scalp EEG dataset to evaluate the proposed approach. Seizure states are identified with an accuracy, sensitivity, and specificity of 0.9793 ± 0.002, 0.9942 ± 0.0005, and 0.9676 ± 0.003, respectively; the resulting performance is superior to those achieved by most existing methods over the same dataset. Furthermore, the approach alleviates the necessity for strictly preprocessing (denoising, removing interferences and artifacts) the EEG data using prior knowledge, which is usually required by existing approaches.
癫痫研究与实践中一个长期存在的挑战是，需要对隐藏在多变量脑电图（EEG）数据中的同步模式进行分类，而这些数据通常叠加有强烈噪声。选择合适的特征提取方法以实现高识别性能至关重要。一种典型方法是提取通道对之间的互信息（MI）。这种计算考虑序列对之间的差异以构建合理划分，可提高分类性能。然而在此基础上，在诸如去噪、对特殊患者进行特征提取等领域依赖性知识不足的情况下，要对隐藏在多变量EEG数据中的同步模式进行自适应分类则更加困难。为通过（1）有效计算MI矩阵（同步模式）和（2）准确分类癫痫发作或非癫痫发作状态来解决这些问题，本研究首先根据亲和传播聚类划分MI（APCPMI）准确测量通道对之间的同步。然后通过将所有通道对的APCPMI组织成相关矩阵来获得全局同步测量。最后，设计一个跨层全连接网络来自适应地表征同步动态相关矩阵并自动识别癫痫发作或非癫痫发作状态。使用CHB - MIT头皮EEG数据集进行实验以评估所提出的方法。癫痫发作状态的识别准确率、灵敏度和特异性分别为0.9793±0.002、0.9942±0.0005和0.9676±0.003；所得性能优于同一数据集上大多数现有方法所取得的性能。此外，该方法减轻了使用现有方法通常所需的先验知识对EEG数据进行严格预处理（去噪、去除干扰和伪迹）的必要性。
