Recurrent Deep Neural Networks for Real-Time Sleep Stage Classification From Single Channel EEG.

Recurrent Deep Neural Networks for Real-Time Sleep Stage Classification From Single Channel EEG.
复制标题

DOI:
10.3389/fncom.2018.00085
复制
发表时间:
2018
影响因子:
3.2
通讯作者:
Garcia-Molina G
Garcia-Molina G
中科院分区:
医学4区
文献类型:
--
作者:
Bresch E;Großekathöfer U;Garcia-Molina G

文献摘要

参考文献

被引文献

相似文献

目的:我们研究了深度递归神经网络的设计,用于从非专家用户在家中记录的单通道EEG信号中检测睡眠阶段。我们报告了数据集大小,架构选择,正则化和个性化对分类性能的影响。方法:我们使用三重交叉验证评估了58种不同的架构和训练配置。结果如下:由卷积(CONV)层和长短期记忆(LSTM)层组成的网络可以使用19个受试者的训练数据集与Cohen Kappa的人类注释者达成约0.73的协议。正规化和个性化并不会带来业绩增长。总结:最佳神经网络架构实现了非常接近先前报告的人类专家间Kappa 0.75的一致性的性能。重要性:我们首次详细介绍了CONV/LSTM网络设计过程,用于单通道家庭环境中的EEG睡眠分期。
Objective: We investigate the design of deep recurrent neural networks for detecting sleep stages from single channel EEG signals recorded at home by non-expert users. We report the effect of data set size, architecture choices, regularization, and personalization on the classification performance. Methods: We evaluated 58 different architectures and training configurations using three-fold cross validation. Results: A network consisting of convolutional (CONV) layers and long short term memory (LSTM) layers can achieve an agreement with a human annotator of Cohen's Kappa of ~0.73 using a training data set of 19 subjects. Regularization and personalization do not lead to a performance gain. Conclusion: The optimal neural network architecture achieves a performance that is very close to the previously reported human inter-expert agreement of Kappa 0.75. Significance: We give the first detailed account of CONV/LSTM network design process for EEG sleep staging in single channel home based setting.
DOI: 10.1371/journal.pbio.0060216
发表时间: 2008-08-26
期刊: PLoS biology
影响因子: 9.8
作者:
Cirelli C;Tononi G
通讯作者: Tononi G
DOI: 10.1093/sleep/27.7.1255
发表时间: 2004-11-01
期刊: SLEEP
影响因子: 5.6
作者:
Ohayon, MM;Carskadon, MA;Vitiello, MV
通讯作者: Vitiello, MV
DOI: 10.1111/j.1460-9568.2010.07543.x
发表时间: 2011-02-01
影响因子: 3.4
作者:
Carrier, Julie;Viens, Isabelle;Filipini, Daniel
通讯作者: Filipini, Daniel
DOI: 10.1523/jneurosci.2725-04.2004
发表时间: 2004-11-03
影响因子: 5.3
作者:
Marshall, L;Mölle, M;Born, J
通讯作者: Born, J
DOI: 10.1109/tnsre.2017.2721116
发表时间: 2017-11-01
影响因子: 4.9
作者:
Supratak, Akara;Dong, Hao;Guo, Yike
通讯作者: Guo, Yike