TY - GEN
T1 - A novel sleep staging algorithm based on hybrid neural network
AU - Hao, Jingwei
AU - Luo, Senlin
AU - Pan, Limin
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Sleep quality has gradually become an important issue concerned by people in today's society, and the judgment of sleep quality requires professional doctors to stage the subjects' sleep stage all night, and doctors need to spend a lot of time and energy to stage sleep. Lack of medical resources in China, the proportion of small problems, this paper proposes a new sleep staging algorithm based on hybrid neural network, this algorithm can be collected by the data of sleep, the hybrid neural network training. The proposed hybrid neural network model mainly includes two parts: The feature learning and extraction stage based on convolutional neural network, and the learning stage based on the sleep sequence rule of short and long time memory network. The trained hybrid neural network can perform automatic sleep staging based on single channel EEG and generate sleep phase diagrams. The proposed algorithm was tested in sleep-EDF database, and the accuracy of Sleep staging reached 92.21%. The results show that the proposed algorithm has higher accuracy and better robustness in the case of higher noise in the data.
AB - Sleep quality has gradually become an important issue concerned by people in today's society, and the judgment of sleep quality requires professional doctors to stage the subjects' sleep stage all night, and doctors need to spend a lot of time and energy to stage sleep. Lack of medical resources in China, the proportion of small problems, this paper proposes a new sleep staging algorithm based on hybrid neural network, this algorithm can be collected by the data of sleep, the hybrid neural network training. The proposed hybrid neural network model mainly includes two parts: The feature learning and extraction stage based on convolutional neural network, and the learning stage based on the sleep sequence rule of short and long time memory network. The trained hybrid neural network can perform automatic sleep staging based on single channel EEG and generate sleep phase diagrams. The proposed algorithm was tested in sleep-EDF database, and the accuracy of Sleep staging reached 92.21%. The results show that the proposed algorithm has higher accuracy and better robustness in the case of higher noise in the data.
KW - component
KW - convolutional neural network
KW - long and short time memory network
KW - sleep stage classification
UR - http://www.scopus.com/inward/record.url?scp=85071118847&partnerID=8YFLogxK
U2 - 10.1109/ICEIEC.2019.8784612
DO - 10.1109/ICEIEC.2019.8784612
M3 - Conference contribution
AN - SCOPUS:85071118847
T3 - ICEIEC 2019 - Proceedings of 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication
SP - 158
EP - 161
BT - ICEIEC 2019 - Proceedings of 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication
A2 - Li, Wenzheng
A2 - Zuo, Guomin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2019
Y2 - 12 July 2019 through 14 July 2019
ER -
