期刊
TRAITEMENT DU SIGNAL
卷 38, 期 5, 页码 1423-1430出版社
INT INFORMATION & ENGINEERING TECHNOLOGY ASSOC
DOI: 10.18280/ts.380517
关键词
electroencephalogram (EEG); Siamese neural networks (SNNs); automatic sleep staging; convolutional neural networks (CNNs); classification; data augmentation
Sleep staging problem of irregularly distributed stages during sleep is solved using Siamese neural networks. The adoption of Bray-Curtis and Cosine methods for classification outperformed traditional methods with promising results.
Sleep staging aims to gather biological signals during sleep, and categorize them by sleep stages: waking (W), non-REM-1 (N1), non-REM-2 (N2), non-REM-3 (N3), and REM (R). These stages are distributed irregularly, and their number varies with sleep quality. These features adversely affect the performance of automatic sleep staging systems. This paper adopts Siamese neural networks (SNNs) to solve the problem. During the network design, seven distance measurement methods, namely, Euclidean, Manhattan, Jaccard, Cosine, Canberra, Bray-Curtis, and Kullback Leibler divergence (KLD), were compared, revealing that Bray-Curtis (83.52%) and Cosine (84.94%) methods boast the best classification performance. The results of our approach are promising compared to traditional methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据