TY - GEN
T1 - Automatic Sleep Stage Detection Based on HRV Spectrum Analysis
AU - Widasari, Edita Rosana
AU - Tanno, Koichi
AU - Tamura, Hiroki
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - In this research proposes and validates an algorithm that uses only electrocardiogram (ECG) for automatic sleep stage detection. Polysomnography (PSG) is the conventional method of sleep stage monitoring. This method requires many sensors, complex procedure, expensive and need to implement in the special laboratory. The ECG signal measurement are much easier to conduct and record. This would make it possible for realizing the non-intrusive method, home-diagnostic systems, reducing a lot of effort and cost. Therefore, an automatic sleep stage detection algorithm that uses only the features of Heart Rate Variability (HRV) spectrum analysis, which recorded via ECG is proposed. The features were classified using the Decision-Tree-Based Support Vector Machines (DTB-SVM) to distinguish Wake, Light (NREM-1 and NREM-2), Deep (NREM-3 and NREM-4) and REM of the sleep stages. The classification accuracy of the proposed algorithm was 89.2%. The result showed that the proposed algorithm has good accuracy for automatic sleep stage detection and it can become a great foundation for future research.
AB - In this research proposes and validates an algorithm that uses only electrocardiogram (ECG) for automatic sleep stage detection. Polysomnography (PSG) is the conventional method of sleep stage monitoring. This method requires many sensors, complex procedure, expensive and need to implement in the special laboratory. The ECG signal measurement are much easier to conduct and record. This would make it possible for realizing the non-intrusive method, home-diagnostic systems, reducing a lot of effort and cost. Therefore, an automatic sleep stage detection algorithm that uses only the features of Heart Rate Variability (HRV) spectrum analysis, which recorded via ECG is proposed. The features were classified using the Decision-Tree-Based Support Vector Machines (DTB-SVM) to distinguish Wake, Light (NREM-1 and NREM-2), Deep (NREM-3 and NREM-4) and REM of the sleep stages. The classification accuracy of the proposed algorithm was 89.2%. The result showed that the proposed algorithm has good accuracy for automatic sleep stage detection and it can become a great foundation for future research.
KW - DTB-SVM
KW - ECG
KW - HRV
KW - sleep stage
UR - https://www.scopus.com/pages/publications/85062239125
U2 - 10.1109/SMC.2018.00155
DO - 10.1109/SMC.2018.00155
M3 - Conference contribution
AN - SCOPUS:85062239125
T3 - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
SP - 869
EP - 874
BT - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
Y2 - 7 October 2018 through 10 October 2018
ER -