Analyzing sleep microstructure by using support vector machine

Abstract

The brain activity during sleep gives us a lot of useful information related to the quality of sleep. Analyzing the appearance of the microwave in the microscopic structure of sleep is especially important. The frequency of occurrence and duration of microwave appear are directly related to the diagnosis and treatment of disorders related to sleep. Arousal is typical behavior for fragmentation level of sleep, which is determined by the events per hour. In this study, we use the Support Vector Machine (SVM) for analysis two types of waves: K-complex and arousal by combining data of EEG and EMG. We build a program with friendly user interface. It can send out alerts and export reports, these reports can be used to support information for doctor’s treatment.