Abstract
Sleep apnea is a potentially serious sleep disorder characterised by abnormal pauses in breathing. Electroencephalogram (EEG) signal analysis plays an important role for detecting sleep apnea events. In this research work, a method is proposed on the basis of inter-band energy ratio features obtained from multi-band EEG signals for subject-specific classification of sleep apnea and non-apnea events. The K-nearest neighbourhood classifier is used for classification purpose. Unlike conventional methods, instead of classifying apnea patient and healthy person, the objective here is to differentiate apnea and non-apnea events of an apnea patient, which makes the task very challenging. Extensive experimentation is carried out on EEG data of several subjects obtained from a publicly available database. Comprehensive experimental results reveal that the proposed method offers very satisfactory classification performance in terms of sensitivity, specificity and accuracy.
Highlights
Apnea is a sleep disorder which causes sleep deprivation and lessens sleep quality
The main focus of this research work is to develop an automatic effective sleep apnea event detection method for apnea subject based on inter-band energy ratios of frequency band-limited EEG signals
The K-nearest neighbourhood (KNN) classifier is used for apnea and non-apnea classifications
Summary
Apnea is a sleep disorder which causes sleep deprivation and lessens sleep quality. It yields severe headaches, hypertension, daytime sleepiness, diminished neurocognitive performance and cardiovascular diseases [1, 2]. Several researches have been pursued to develop automatic apnea detection process utilising different bio-signals including EEG, EOG, ECG and EMG [5]. Duration of obstructive sleep apnea event within patient’s overnight EEG data is detected in [9] utilising the variation in Hilbert spectrum frequency in particular frequency bands. In [10], the expectancy of identifying sleep-disordered breathing events within an apnea patient is studied analysing the characteristics of EEG frequency bands and EMG signal. In [11], apnea events within an apnea patient are detected using entropy values computed from each frequency band of EEG signal. The main focus of this research work is to develop an automatic effective sleep apnea event detection method for apnea subject based on inter-band energy ratios of frequency band-limited EEG signals. The K-nearest neighbourhood (KNN) classifier is used for apnea and non-apnea classifications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
