Automatic detection of awake state during sleep based on the approximate entropy of EMG

Sleep is important to human beings. A good sleep can bring sufficient energy and keep healthy. Sleep process contains several sleep stages. There are also several short-duration awake states appeared in sleep process. The amount of those awake states during sleep would be related to evaluate the sleep quality. In this study, the automatic detection method of awake state is investigated on the sleep recording of patient with sleep disorder. Two nonlinear features of ApEN and Mc-ApEN are calculated based on the EMG signal recorded during one's overnight sleep process. The detection performance is analyzed and compared. The obtained results showed that the presented method is feasible for awake state detection during sleep, where Mc-ApEN is slightly better than ApEN. It can be an assistant tool for sleep evaluation.