Detection of sleep apnea using sub-frame based temporal variation of energy in beta band in EEG

Sleep apnea is a sleep disorder that affects one's breathing during sleep. A large number of people all over the world are suffering from this disease. Electroencephalogram (EEG) provides electrical activity of the brain signal that enables physicians to diagnose and monitor sleep apnea events. In this paper, an efficient scheme for classifying apnea and non-apnea events of an apnea patient is proposed based on temporal variation of Beta band energy in a frame of EEG data. Unlike conventional approaches, instead of extracting features from the whole frame at a time, a given test frame of EEG signal is divided into overlapping sub-frames and spectral characteristics are extracted from each pre-processed sub-frame. By investigating the spectro-temporal characteristics of all the traditional frequency bands of EEG signal, it is found that the temporal variation of spectral energy in Beta band plays the dominant role in classifying apnea and non-apnea events. Statistical features are extracted from the temporal pattern of Beta band energy and are used in K nearest neighborhood classifier. Extensive experimentation is carried out on several apnea patients with various apnea indices and a very satisfactory apnea detection performance is achieved in comparison to that obtained by some existing methods.