Detection method of blood sugar concentration based on neural network algorithm

A technology of blood sugar concentration and neural network, which is applied in the field of microwave nondestructive testing, can solve the problems of insufficient understanding of the optical characteristics of human tissue and the inability to eliminate the influence of blood pressure measurement accuracy, etc.

Inactive Publication Date: 2018-05-11
TIANJIN UNIV
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The common problem with optical methods is that the understanding of the optical properties of human tissue is not deep enough, and it is impos...

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
  • Detection method of blood sugar concentration based on neural network algorithm
  • Detection method of blood sugar concentration based on neural network algorithm
  • Detection method of blood sugar concentration based on neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Firstly, the feasibility of the present invention will be described below in conjunction with the earlobe tissue model. Then the technical scheme of the present invention is described in conjunction with the examples.

[0017] Due to the simple tissue structure in the earlobe, the distribution of capillaries can be equivalent to a layer of blood, and there are different electromagnetic characteristic parameters at different blood sugar concentrations. When the ultra-broadband microwave emitted by one antenna passes through the earlobe and is received by the antenna on the other side, the neural network input can be obtained by extracting the characteristic pole value of the received signal, and the neural network is used to analyze the characteristics of the received signal with known blood sugar concentration Extreme training. After the training is over, the characteristic poles of the received signal of unknown blood sugar concentration are input into the neural netw...

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 relates to a detection method of blood sugar concentration based on a neural network algorithm. The method includes the following steps that a human body earlobe model is made; test blood with different blood sugar concentrations is prepared; a first antenna is used to transmit an ultra wide band microwave signal, a second antenna receives the signal which penetrates the earlobe model; the obtained received signal is processed, signal characteristic poles including resonant frequencies and attenuation factors are extracted by a Prony method, eighteen characteristic poles of the received signal are extracted, wherein the number of the resonant frequencies is nine, the number of the attenuation factors is nine, a total of eighteen signal characteristic poles is as a group; anda BP neural network is selected to train.

Description

technical field [0001] The invention belongs to the technical field of microwave nondestructive testing, and relates to a blood sugar concentration testing method. Background technique [0002] The changes in the content of various chemical components in human blood can truly reflect the health status of the human body, which is important information necessary for clinical diagnosis and daily monitoring. Finding a method that can conveniently, continuously, effectively, accurately and non-invasively measure blood components has been a long-awaited ideal in the process of fighting diseases. Since the real-time detection of blood glucose concentration is of great value in the prevention and treatment of diabetes, current research mainly focuses on the non-invasive detection of blood glucose. The feasible non-invasive detection methods of blood glucose that are being studied can be divided into two categories: one is optical methods, mainly including near-infrared spectroscopy...

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): G01N22/00G06N3/00
CPCG01N22/00G06N3/084
Inventor 肖夏李钦伟
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap