Sleep spindle is the characteristic waveform of electroencephalogram (EEG)\nwhich is important for clinical diagnosis. In this study, an automatic sleep\nspindle detection method was developed. The EEG signals were recorded\nbased on the standard polysomnogram (PSG) measurement. A preprocessing\nprocedure is introduced to exclude the unnecessary data segments and normalized\nthe necessary data segments. Complex demodulation method is\nadopted to detect the candidate sleep spindle waveforms and calculate the\nfeatures. The sleep spindles are recognized based on a decision tree model.\nFinally, the detected sleep spindles were utilized to amend the sleep stage recognition\nresults. The sleep EEG data from 3 patients with sleep disorders were\nanalyzed. The obtained results showed that the detected sleep spindles in EEG\nsignal improved the accuracy of sleep stage recognition.
Loading....