Sleep staging automatic interpretation method based on step-by-step clustering model

Abstract

The invention relates to a sleep staging automatic interpretation method based on a step-by-step clustering model. According to the method, the step-by-step clustering model is designed and constructed by utilizing the correlation between different electroencephalogram signal characteristics and each sleep stage. Meanwhile, in the clustering process, key steps of the algorithm are optimized and adjusted, an initial clustering center is selected in combination with a density and distance considering method, and a Gaussian kernel function is adopted to calculate a weight factor to adjust and update the clustering center. Besides, after clustering, a distance correction coefficient is designed to improve the rationality of a clustering result in combination with an actual conversion rule of the sleep state. According to the sleep staging automatic interpretation method based on the step-by-step clustering model, the objective clustering effect of individualized complex feature distribution in sleep staging can be reflected, the classification performance of the clustering algorithm on the sleep staging problem is improved, the clustering algorithm is closer to the experience mode of manual interpretation, and an effective and feasible auxiliary interpretation tool can be provided for clinical application.

Description

technical field [0001] The invention relates to the technical field of sleep assessment, in particular to a method for automatically interpreting sleep stages based on a step-by-step clustering model. Background technique [0002] The sleep process is a dynamic process consisting of several sleep stages representing different sleep states. During the sleep process, except for the awake period W, sleep is divided into the rapid eye movement period (REM) and the non-rapid eye movement period according to the movement state of human eyeballs. In the non-rapid eye movement period, as the sleep state progresses from shallow to deep, it is further divided into four sleep stages, namely light sleep stage S1, light sleep stage S2, and deep sleep stages S3 and S4. Among them, S3 and S4 are often combined into a slow wave sleep period SS. [0003] Interpretation of sleep stages means analyzing the characteristics of synchronously recorded EEG and other bioelectrical signals during s...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for automatically interpreting sleep stages based on a step-by-step clustering model in order to overcome the above-mentioned defects in the prior art. Aiming at the characteristics of sleep EEG signals and their association with different sleep stages, a method is designed and constructed. The step-by-step clustering model not only objectively reflects the clustering effect of individual complex feature distribution in sleep staging, but also improves the classification performance of the clustering algorithm in sleep staging discrimination, making it closer to the empirical method of manual interpretation , can provide an effective and feasible auxiliary interpretation tool for clinical application

Images