Review of deep learning based methods for sleep apnea detection

Abstract

One of the most prevalent and serious causes of sleep disorders is sleep apnea syndrome. Manual identification of such disorders by investigating the EEG recordings is a time-consuming task. Hence, automatic detection of sleep apnea in EEG signals could be a preferred solution. In recent years, many deep learning algorithms are being reported for automatic sleep apnea detection. In this paper, a comprehensive review of various recently reported deep learning techniques like convolutional neural network (CNN), Bi-directional Long short-term memory (Bi-LSTM), recurrent neural network (RNN), etc., are presented and the performance of those techniques are compared.