Automatic sleep staging method based on multi-parameter feature combination
A feature fusion, sleep staging technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as the accuracy rate of only 81.65%, and achieve improved accuracy and generalization ability, good application prospects, and reliability. high effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2017-08-04
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to a sleep staging method, in particular to an automatic sleep staging method based on multi-parameter feature fusion. Background technique
[0002] With fierce competition in modern society, fast-paced work and life have had a huge impact on people's sleep. According to the World Health Organization statistics, 27% of people have sleep disorders. At present, sleep disorder has been confirmed as a disease with public hazards, and more and more people pay more and more attention to it. Staging the sleep state of the human body through various physiological signals is an effective method for objectively evaluating sleep quality.
[0003] Extracting the characteristic parameters of the electroencephalogram (EEG) through different analysis methods, and then using a classifier to classify is a classic method of sleep staging. In the prior art, someone divides the sleep state into five phases by performing nonlinear symbolic dynamics...
Examples
Embodiment Construction
[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.
[0027] 1. Data Acquisition and Preprocessing
[0028] The data used in this case comes from the MIT-BIH polysomnographic database (Goldberger AL, Amaral LAN, Glass L, et al. MIT-BIH Polysomnographic database. [DB / OL]. [2000-06-13]), the database records Signals of multiple physiological parameters during sleep of 16 test subjects were obtained, and the sampling frequency was 250Hz. Among the 16 test subjects, only slp32, slp41, slp45, and slp48 test individuals contained complete EEG, ECG, EMG (from the jaw), respiratory signals and complete sleep stages, so samples slp32, slp41, slp45, and slp48 were selected as experimental subjects. All the data is divided into one section every 30 seconds, and the sleep staging is judged by experts according to the R&K standard. In this ...