SIGNAL DETECTION METHOD AND SYSTEM FOR ASSESSING SLEEP APNEA

摘要

Disclosed are a signal detection method and system for assessing sleep apnea. The signal detection method comprises the following steps: acquiring vital sign signals of a sleeping user (S1); performing structured processing on the vital sign signals of the user to remove invalid signals to obtain a set of valid vital sign signals (S2); extracting multidimensional morphological features from a sleep breathing sample signal and performing feature training on an initial model of a classifier by means of the multidimensional morphological features so as to obtain a sleep breathing detection model (S3); and inputting the set of valid vital sign signals into the sleep breathing detection model and performing signal processing to obtain probability data relating to the probability of the user experiencing sleep apnea (S4). The signal detection method for assessing sleep apnea employs multidimensional morphological features to perform feature training on an initial model of a classifier to strengthen the performance of a resulting sleep breathing detection model. As a result, data relating to the probability of a user experiencing sleep apnea can be more accurately obtained, thereby facilitating the determination of whether a sleep apnea event occurs during sleep.