Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hemoglobin concentration prediction regression model training method, application method and training system

A technology of hemoglobin concentration and regression model, applied in the application method and system, the training field of hemoglobin concentration prediction regression model, can solve the problems of easy infection, inaccurate detection value, etc., and achieve the effect of improving detection accuracy and generalization ability

Pending Publication Date: 2021-11-12
SHANDONG INST OF ADVANCED TECH CHINESE ACAD OF SCI CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a training, application method and system of hemoglobin concentration prediction regression model, to solve the problems of traditional invasive detection which is accurate but easy to infection, and non-invasive detection without wound but inaccurate detection value

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
  • Hemoglobin concentration prediction regression model training method, application method and training system
  • Hemoglobin concentration prediction regression model training method, application method and training system
  • Hemoglobin concentration prediction regression model training method, application method and training system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] Such as figure 1 As shown, the present embodiment provides a training method for a hemoglobin concentration prediction regression model, comprising the following steps:

[0081] A1. Construct a hemoglobin concentration prediction regression model based on multiple machine learning algorithms.

[0082] A11, build the first layer of regressor, the first layer of regressor is Ada Boost, PCR, PLSR and SVR four parallel models;

[0083] A12. Construct a second-layer regressor, the second-layer regressor is an attention layer model.

[0084] A2. Obtain historical multi-channel PPG signals and historical hemoglobin concentration values.

[0085] A3. Preprocessing the historical multi-channel PPG signal to obtain the pre-processed historical multi-channel PPG signal data.

[0086] A4. Automatically extract feature information of the preprocessed historical multi-channel PPG signal data to obtain historical automatic feature information.

[0087] A41, build a convolutional n...

Embodiment 2

[0104] Obtained the well-trained hemoglobin concentration prediction regression model by embodiment 1, as figure 2 As shown, the model includes a first layer regressor and a second layer regressor; the first layer regressor includes four parallel models of Ada Boost, PCR, PLSR and SVR; the second layer regressor includes attention layer model; corresponding, such as image 3 As shown, this embodiment also provides a method for applying the hemoglobin concentration prediction regression model correspondingly, including the following steps:

[0105] B1. Obtain multi-channel PPG signals.

[0106] B2. Preprocessing the multi-channel PPG signal to obtain preprocessed multi-channel PPG signal data.

[0107] B3. Automatically extract feature information of the preprocessed multi-channel PPG signal to obtain automatic feature information.

[0108] B31, construct convolutional neural network model, described convolutional neural network model comprises 1 input layer, 2 convolutiona...

Embodiment 3

[0125] In addition, according to the method of embodiment 1 and embodiment 2 of the present invention, the method can also use Figure 4 The architecture of the application system 1 shown is implemented. Figure 4 The architecture of the application system 1 is shown. Such as Figure 4 As shown, the application system 1 can include a PPG information acquisition module 2, a historical concentration value acquisition module 3, a preprocessing module 4, an automatic feature extraction module 5, a manual feature extraction module 6, a feature fusion module 7, a regression model building module 8, Regression model training module 9 and regression prediction module 10; Some modules can also have subunits for realizing its function, such as automatic feature extraction module 5 can include convolutional neural network model construction unit 51 and convolutional neural network model training unit 52, The manual feature extraction module 6 may also include a mapping relationship est...

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 provides a hemoglobin concentration prediction regression model training and application method, and system, and the method comprises the steps of obtaining a multi-channel PPG signal, and carrying out the signal processing of the multi-channel PPG signal; performing manual and automatic feature information extraction on the acquired multi-channel PPG signals, and fusing the manual feature information and the automatic feature information through a feature information fusion mechanism to realize accurate extraction of the feature information; establishing a hemoglobin concentration prediction regression model integrated based on a multi-machine learning algorithm for noninvasive detection, and obtaining a more stable detection result by utilizing efficient integration of a plurality of regression models and multiple regression predictions. According to the method, under the condition that the model training speed is guaranteed, the detection precision and generalization ability of the model can be improved, the method has the advantages of a non-invasive detection method and an invasive detection method, and the technical problem that the hemoglobin concentration of the human body cannot be continuously detected in real time in the prior art is solved.

Description

technical field [0001] The invention relates to the technical field of non-invasive detection, in particular to a training and application method and system of a hemoglobin concentration prediction regression model. Background technique [0002] At present, the methods for detecting hemoglobin concentration can be divided into two types: invasive detection and non-invasive detection. Invasive hemoglobin concentration detection methods include cyanmethemoglobin detection method and instant detection method, both of which need to take blood samples from the subject first, and then analyze the hemoglobin concentration value by a blood cell analyzer. Although the accuracy of the results obtained by this type of detection method is high, there are some shortcomings: the detection time cannot achieve continuous and real-time results, and the situation of critically ill patients cannot be understood in time; it is easy to cause wound infection, and it may also cause the subject to ...

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): G06K9/62A61B5/145G06N3/04G06N3/08
CPCG06N3/08A61B5/145G06N3/045G06F18/213G06F18/25G06F18/214
Inventor 彭福来陈财张昔坤
Owner SHANDONG INST OF ADVANCED TECH CHINESE ACAD OF SCI CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com