Research Of Sleep Stage Based On Hopfield Neural Network During Day Time Nap Sleep

Sleep is essential to maintain the functions of human body. With the development of modern society, sleep problem becomes one of the serious social problems. Besides the overnight long term sleep, daytime short term sleep plays a supporting role for our health. It may compensate the insufficient amount of nighttime sleep or take relaxation and mode refreshing from pressure, tiredness, etc.In this paper, the study subject is short sleep during the day, which is mainly to solve the stages issues of short time sleep during the day. The subjects of the environment are different which between the night and the day. For example, the light during the day is strong, but it is weak in the night; the noise outside during the day play a greater impact on the subjects, and there are almost no noise at night; the temperature in the daytime is higher than it at night; besides the difference between the subjects is also obvious, some subjects have stable sleep state, but others may have significantly volatile sleep state. According to the characteristics of short time sleep during the day, the paper is mainly to study feature extraction method and classification method for sleep stages during the daytime.All the obtained raw date was separated into20seconds per segment for sleep stage classification. The visual inspection of sleep stage awake, stage1and stage2had been made for comparison. The characteristics of electroencephalograph (EEG) are analyzed for stage awake, stage1and stage2. The energy of characterized waveforms is calculated by fast Fourier transform (FFT) and the ratio of each band is obtained. The EEG of the short sleep during the day were analyzed by the measurements of multiscale entropy (MSE). According to the result, these parameters can better reflect the trends in changes of sleep depth during daytime sleep. Next, all the features were analyzed, Based on these features which are in time and frequency, the day time nap sleep was classified with Hopfield neural network, and then compared the feature from MSE, the result showed that this can improve the accuracy rate of sleep stage...