Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques
Yükleniyor...
Tarih
2018
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
It is extremely significant to identify sleep stages accurately in the diagnosis of obstructive sleep apnea. In the study, it was aimed at determining sleep and wakefulness using a practical and applicable method. For this purpose , the signal of heart rate variability (HRV) has been derived from photoplethysmography (PPG). Feature extraction has been made from PPG and HRV signals. Afterward, the features, which will represent sleep and wakefulness in the best possible way, have been selected using F-score feature selection method. The selected features were classified with k-nearest neighbors classification algorithm and support vector machines. According to the results of the classification, the classification accuracy rate was found to be 73.36 %, sensivity 0.81, and specificity 0.77. Examining the performance of the classification, classifier kappa value was obtained as 0.59, area under an receiver operating characteristic value as 0.79, tenfold cross-validation as 77.35 %, and F-measurement value as 0.79. According to the results accomplished, it was concluded that PPG and HRV signals could be used for sleep staging process. It is a great advantage that PPG signal can be measured more practically compared to the other sleep staging signals used in the literature. Improving the systems, in which these signals will be used, will make diagnosis methods more practical.
Açıklama
Anahtar Kelimeler
Obstructive Sleep Apnea, Automatic Sleep Staging, Biomedical SignalProcessing, Biomedical Signal Classification, Photoplethysmography, Heart Rate Variability, k-Nearest Neighbors Classification Algorithm, Support Vector Machines
Kaynak
Neural Computing & Applications
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
29
Sayı
8
