Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Sleep stage classification method based on complex networks and deep learning and application thereof

A sleep stage, complex network technology, applied in applications, medical science, sensors, etc., can solve the problem that the classification effect cannot be very accurate, and achieve high accuracy

Inactive Publication Date: 2019-10-25
TIANJIN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the training models in the past were shallow, and the classification effect could not be very accurate.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sleep stage classification method based on complex networks and deep learning and application thereof
  • Sleep stage classification method based on complex networks and deep learning and application thereof
  • Sleep stage classification method based on complex networks and deep learning and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The sleep stage classification method and application based on complex network and deep learning of the present invention will be described in detail below in conjunction with the embodiments and drawings.

[0033] The sleep stage classification method based on complex network and deep learning of the present invention is to construct a complex network of visual graphs from EEG signals, extract complex network feature indicators, and combine long and short-term memory networks to realize the classification of sleep states.

[0034] Such as figure 1 Shown, the sleep stage classification method based on complex network and deep learning of the present invention, comprises the following steps:

[0035] 1) Obtain the characteristic indicators of the complex network with limited traversal visualization, including:

[0036] (1) For a sleep stage EEG segment of length T Establish a finite traversal visual graph complex network, where, x t Represents the i-th node of the EE...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A sleep stage classification method based on complex networks and deep learning and application thereof are provided. The sleep stage classification method comprises: acquiring characteristic indexesof a finite passage visibility graph complex network, to be specific, establishing the finite passage visibility graph complex network to extract node degrees, acquiring a node degree sequence according to the node degrees, and applying the node degree sequence as a characteristic index of the finite passage visibility graph complex network; establishing finite passage visibility graph complex networks having a finite passage visual range of 1 for sleep stage electroencephalography fragments; classifying the sleep stage electroencephalogram fragments into four classes according to awake stage,light sleep stage, deep sleep stage and rapid eye movement stage by means of 10-fold cross validation and a long short term memory model. The method of the invention is applicable to head-set intelligent wearable devices; by analyzing sleep electroencephalogram measured by the intelligent wearable devices, it is possible to understand the brain state of a user and provide necessary early warnings.

Description

technical field [0001] The invention relates to a sleep stage monitoring method and application. In particular, it relates to a sleep stage classification method and application based on complex network and deep learning. Background technique [0002] Sleep is an important, dynamic and regular process that occurs in human beings. It has an important impact on a person's daily activities. Sleep is one of the most important functions of brain activity. A healthy human brain goes through several psycho-physiological states, known as sleep stages, during sleep. With the increasing pressure of social life, more and more people are troubled by sleep-related diseases, such as sleep apnea, insomnia, lethargy, and fainting. This will seriously affect people's health and quality of life. More and more people hope to understand their sleep state through continuous EEG signal collection and analysis and sleep monitoring. Sleep stage detection is to classify sleep stages, which plays ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/00A61B5/04A61B5/0476
CPCA61B5/4812A61B5/6803A61B5/7267A61B5/746A61B5/316A61B5/369
Inventor 高忠科蔡清
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products