A Smart Detection Method of Sleep Quality Using EEG Signal and Long Short-Term Memory Model

Sleep is the most important physiological process related to human health. The development of society has accelerated pace people’s lives and also increased life pressure. As a result, more people suffer from reduced sleep quality, resulting diseases are increasing. In response this problem, study proposes quality detection management method based on electroencephalogram (EEG). mainly achieved by staging EEG signals. First, wavelet packet decomposition (WPD) preprocesses collected original extract four rhythm waves EEG. Second, relative energy characteristics nonlinear each wave extracted. multisample entropy (MSE) values different scales calculated as main features, rest auxiliary features. Finally, long short-term memory (LSTM) model applied classify extracted final result obtained. Experiments were conducted in MIT-BIH public database. experimental results show that used article high accuracy rate for detection. For detected data, data managed combination with mobile terminal software. Management embodied two aspects. One query display historical data. second when there periodic abnormalities user will be reminded so can respond time ensure physical fitness.