[Extraction of sleep structure information from heart rate variability based on spectrum analysis]

In this study we made full use of the heart rate spectrum analysis to obtain the character parameters of heart rate variability related to EEG sleep phase information, and then we discarded the correlation between characteristics by employing Principal Component Analysis. Finally, by means of the decision tree based on Fisher rules, we established two full automatic models for identifying healthy people and sleep apnea hypopnea syndroma (SAHS) patients respectively. The result of experiments indicates that the model is accurate and robust.