Auto sleep staging and sleep quality estimation based on BP neural network / 生物医学工程学杂志

ABSTRACT

To estimate the sleep quality, a 3-layer BP neural network was studied. The EEG complexity and the power spectrum of sleep-multigraph served as the input vector of the network . All-night sleep-stage scoring was performed. Then several parameters (sleep period, shallow sleep period, deep sleep period, REM period, ratio of the wakeful period and sleep one) were defined to estimate the sleep quality. The experiments revealed that the estimated sleep condition was the same as the subjects' impression. The data on six cases of all-night sleep show that this method is available to estimate the sleep quality.