Deep Convolutional Neural Network Based Sleep Apnea Detection Scheme Using Spectro-temporal Subframes of EEG Signal

Sleep apnea, a common sleep disorder, has been affecting millions of people all over the world. For automatic detection of sleep apnea from various bio-signals, the Electroencephalogram (EEG) signal is getting more attention because of its physiological interpretation with this disease. In this paper, a patient independent sub-frame based approach for the automatic detection of apnea frames using only EEG signal is proposed. Here instead of directly using a whole frame of EEG data, spectro-temporal subframes are used that are obtained by first extracting frequency band limited signals and then dividing each of them into smaller subframes. Next the extracted subframes are fed into the proposed local convolutional neural network (CNN) blocks. The local features thus produced are then processed using the proposed global CNN block to obtain global features. These features are optimized using deep neural network classifier. The method is evaluated on multiple patients taken from a publicly available database. From extensive analysis it is found that the proposed method offers consistently significant performance in terms of accuracy, sensitivity and specificity. The proposed scheme has the potential to be used for the better detection of sleep apnea in real life application.