TY - JOUR
T1 - HyCLASSS
T2 - A Hybrid Classifier for Automatic Sleep Stage Scoring
AU - Li, Xiaojin
AU - Cui, Licong
AU - Tao, Shiqiang
AU - Chen, Jing
AU - Zhang, Xiang
AU - Zhang, Guo Qiang
N1 - Funding Information:
Manuscript received July 8, 2016; revised December 10, 2016 and January 31, 2017; accepted February 6, 2017. Date of publication February 17, 2017; date of current version March 5, 2018. This work was supported in part by the University of Kentucky, in part by the Center for Clinical and Translational Science Award UL1TR001998, in part by the National Sleep Research Resource under Grant NHLBI R24 HL114473, and in part by the National Science Foundation under Grant 1626364. (Corresponding author: Guo-Qiang Zhang.) X. Li is with the Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH 44106-7078 USA, and also with the Institute for Biomedical Informatics, University of Kentucky, Lexington, KY 40506 USA (e-mail: xxl509@case.edu).
Funding Information:
This work was supported in part by the University of Kentucky, in part by the Center for Clinical and Translational Science Award UL1TR001998, in part by the National Sleep Research Resource under Grant NHLBI R24 HL114473, and in part by the National Science Foundation under Grant 1626364.
Publisher Copyright:
© 2013 IEEE.
PY - 2018/3
Y1 - 2018/3
N2 - Automatic identification of sleep stage is an important step in a sleep study. In this paper, we propose a hybrid automatic sleep stage scoring approach, named HyCLASSS, based on single channel electroencephalogram (EEG). HyCLASSS, for the first time, leverages both signal and stage transition features of human sleep for automatic identification of sleep stages. HyCLASSS consists of two parts: A random forest classifier and correction rules. Random forest classifier is trained using 30 EEG signal features, including temporal, frequency, and nonlinear features. The correction rules are constructed based on stage transition feature, importing the continuity property of sleep, and characteristic of sleep stage transition. Compared with the gold standard of manual scoring using Rechtschaffen and Kales criterion, the overall accuracy and kappa coefficient applied on 198 subjects has reached 85.95% and 0.8046 in our experiment, respectively. The performance of HyCLASS compared favorably to previous work, and it could be integrated with sleep evaluation or sleep diagnosis system in the future.
AB - Automatic identification of sleep stage is an important step in a sleep study. In this paper, we propose a hybrid automatic sleep stage scoring approach, named HyCLASSS, based on single channel electroencephalogram (EEG). HyCLASSS, for the first time, leverages both signal and stage transition features of human sleep for automatic identification of sleep stages. HyCLASSS consists of two parts: A random forest classifier and correction rules. Random forest classifier is trained using 30 EEG signal features, including temporal, frequency, and nonlinear features. The correction rules are constructed based on stage transition feature, importing the continuity property of sleep, and characteristic of sleep stage transition. Compared with the gold standard of manual scoring using Rechtschaffen and Kales criterion, the overall accuracy and kappa coefficient applied on 198 subjects has reached 85.95% and 0.8046 in our experiment, respectively. The performance of HyCLASS compared favorably to previous work, and it could be integrated with sleep evaluation or sleep diagnosis system in the future.
UR - http://www.scopus.com/inward/record.url?scp=85043578987&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85043578987&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2017.2668993
DO - 10.1109/JBHI.2017.2668993
M3 - Article
C2 - 28222004
AN - SCOPUS:85043578987
VL - 22
SP - 375
EP - 385
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
SN - 2168-2194
IS - 2
ER -