Check patentability & draft patents in minutes with Patsnap Eureka AI!

Construction method of SVM (Support Vector Machine) classifier for monitoring sleep as well as system and method for monitoring sleep

A construction method and a classifier technology are applied in the field of sleep monitoring to achieve the effects of reducing computational complexity, improving computational speed, and improving detection accuracy

Inactive Publication Date: 2020-02-21
QILU UNIV OF TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical task of the present invention is to address the above deficiencies, to provide a method, system and method for constructing an SVM classifier for monitoring sleep, to solve the problem of how to provide a system with simple structure and easy operation to efficiently and quickly monitor and analyze sleep quality

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
  • Construction method of SVM (Support Vector Machine) classifier for monitoring sleep as well as system and method for monitoring sleep
  • Construction method of SVM (Support Vector Machine) classifier for monitoring sleep as well as system and method for monitoring sleep
  • Construction method of SVM (Support Vector Machine) classifier for monitoring sleep as well as system and method for monitoring sleep

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A method for constructing an SVM classifier for monitoring sleep in the present invention uses digital data in blood oxygen saturation as training data to construct an SVM classifier, optimizes the SVM classifier based on the stochastic gradient ascent method, and obtains a trained SVM classifier .

[0061] SVM (Support Vector Machine in Chinese) is a widely used supervised machine learning method, which uses training data to build models for classification. It is a nonlinear modeling method, suitable for solving small sample and high latitude modeling problems. An SVM classifier is built from the training data, and then the SVM classifier classifies each instance in the test set. The main concept of support vector machines is to maximize the distance between two parallel boundaries or hyperplanes defined by support vectors.

[0062] Wherein, the kernel function of SVM classifier in the present embodiment is radial basis function, and its principle is:

[0063] The S...

Embodiment 2

[0078] An SVM-based continuous sleep monitoring system of the present invention includes a wearable device, a mobile terminal and a cloud terminal, and the wearable device, the mobile terminal and the cloud terminal are sequentially connected wirelessly.

[0079] Among them, wearable devices are used to collect human body data. Human body data includes blood oxygen saturation, respiration rate, inhaled carbon dioxide concentration, end-tidal carbon dioxide concentration, and pulse rate. Both blood oxygen saturation and respiration rate include digital data and waveform data.

[0080] The wearable device is configured with a first wireless communication module, which encodes the human body data through the first wireless communication module and uploads the encoded human body data to the mobile terminal.

[0081] The wearable device used in this embodiment is a fingertip blood oxygen probe and a carbon dioxide nasal cannula. Both the fingertip blood oxygen probe and the carbon d...

Embodiment 3

[0120] A method for monitoring sleep of the present invention, based on the public system of Embodiment 2, a system for monitoring sleep, collecting blood oxygen saturation, classifying the digital numbers in blood oxygen saturation by SVM classifier, and based on Classification results generate diagnostic reports.

[0121] In this embodiment, the wearable device has a Bluetooth communication function, the mobile terminal is a mobile phone, and has Bluetooth communication, 3G / 4G, and WIFI communication functions, that is, the wearable device and the mobile terminal are connected wirelessly in a Bluetooth manner, and the mobile terminal and the cloud terminal are connected via Bluetooth. The WIFI connection is wireless connection; the cloud terminal is composed of a server and a display, and the server has a WIFI communication function.

[0122] as attached figure 2 As shown, the method steps are as follows:

[0123] S100. Collect five kinds of human body data through wearab...

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

The invention discloses a construction method of an SVM (Support Vector Machine) classifier for monitoring sleep as well as a system and a method for monitoring the sleep, and belongs to the field ofmonitoring of the sleep. The technical problem to be solved is how to provide a system being simple in structure and convenient in operation for effectively and quickly monitoring and analyzing the quality of the sleep. The construction method comprises the following steps: building the SVM classifier based on numbers and data in blood oxygen saturation as training data; optimizing parameters of the SVM classifier based on a stochastic gradient rising method to obtain the trained SVM classifier. The system is used for collecting the blood oxygen saturation, classifying the numbers and the datain the blood oxygen saturation through the SVM classifier, evaluating a classified result, and generating a diagnosis report including wearable equipment, a mobile terminal and a cloud terminal. Themethod comprises the following steps: collecting the blood oxygen saturation through the system, classifying the numbers and the data in the blood oxygen saturation through the SVM classifier, evaluating the classified result and generating the diagnosis report.

Description

technical field [0001] The invention relates to the field of sleep monitoring, in particular to a method, system and method for constructing an SVM classifier for monitoring sleep. Background technique [0002] With the accelerated pace of society, long-term work pressure and competitive pressure, working people are prone to sleep disorders. Sleep disorders affect sleep quality, and good sleep quality plays a vital role in physical and mental health and can become a serious health problem for people. Sleep apnea syndrome is considered one of the major sleep disorders affecting at least 2% of women and 4% of men. Among people with sleep apnea syndrome, 80% are unaware of their condition. [0003] In the field of sleep disorder diagnosis, polysomnography (PSG) is a commonly used standard method. PSG is the monitoring of respiratory airflow, respiratory events, snoring, oxygen saturation (SpO2), electrocardiogram (EOG), electroencephalogram (EEG), and electrocardiogram (ECG)...

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
IPC IPC(8): A61B5/1455A61B5/00A61B5/0205
CPCA61B5/14551A61B5/14542A61B5/4806A61B5/4815A61B5/4818A61B5/7235A61B5/7267A61B5/0205A61B5/0816A61B5/08A61B5/02438A61B5/6802A61B5/0002
Inventor 马宾吴兆龙徐健王春鹏李健李宁宁李春晓
Owner QILU UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com