Training method and system of sleep-state classifier

Abstract

The invention relates to a training method and system of a sleep-state classifier, wherein the method comprises the following steps: constructing feature vectors of sample data of a plurality of sleep-state types and a cluster center formed by aggregating the feature vectors, and establishing an objective function according to the feature vectors and the cluster center of the feather vectors; using the objective function to characterize the distance between the minimized sample data of same types and dictionary atoms, and the distance among maximized atoms of different types; respectively selecting a plurality of the feature vectors from the sample data of a plurality of the sleep-state types to be taken as initial values of the atoms, distributing various sample data to the atoms and solving the objective function, thus obtaining a classification dictionary; using the classification dictionary to classify the sample data, comparing the types and the distances of the atoms which are closest to the sample data, if the distance is less than a preset threshold value, judging that the types of the sample data are consistent with the types of the atoms; training the sleep-state classifier according to the classified sample data. By adopting the training method and system of the sleep-state classifier, a more accurate sleep-state classifier can be trained.

Description

technical field [0001] The invention relates to the technical field of sleep aids, in particular to a training method and system for a sleep state classifier. Background technique [0002] During sleep, the human body undergoes a process of self-relaxation and recovery, so good sleep is a basic condition for maintaining good health; however, due to work pressure, irregular life schedule and other reasons, some people have poor sleep quality , manifested as insomnia, waking up in the middle of the night, etc. [0003] There are already some devices on the market to help people fall asleep and improve the quality of sleep. For example, in a specific sleep state, manual intervention such as sound and light signals can be used to avoid waking up the user in a deep sleep state. For devices that assist sleep, in order to truly improve the user's sleep quality, it is very important to correctly detect the user's sleep state. [0004] At present, polysomnography is mainly used cl...

AI Technical Summary

Problems solved by technology

[0004] At present, polysomnography is mainly used clinically to identify the sleep state, mainly using EEG signals to analyze sleep, and to identify the sleep state of the subject by training the sleep state model, such as judging which stage the user is in sleep, but due to The specificity of the EEG signal is strong, and the intensity is very weak and it is easy to be disturbed by the outside world

The classifier trained by the existing technology has errors in the detection of many users, and the accuracy is difficult to guarantee

Images