Hemoglobin dynamic spectrum analytical prediction method based on deep learning technology

A technology of deep learning and dynamic spectrum, which is applied in the field of hemoglobin dynamic spectrum analysis and prediction based on deep learning technology, can solve the problems of automatic comprehensive analysis of hemoglobin concentration, etc.

Inactive Publication Date: 2018-04-13
TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the defect that the hemoglobin concentration cannot be automatically comprehensively analyzed in the prior art, and to provide a hemoglobin dynamic spectrum analysis and prediction method based on deep learning technology to solve the above problems

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 dynamic spectrum analytical prediction method based on deep learning technology
  • Hemoglobin dynamic spectrum analytical prediction method based on deep learning technology
  • Hemoglobin dynamic spectrum analytical prediction method based on deep learning technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Such as figure 1 As shown, a hemoglobin dynamic spectrum analysis prediction method based on deep learning technology includes the following steps:

[0034] 1. Acquisition and preprocessing of deep learning training data, using a spectrometer to obtain dynamic spectral data of patients, preprocessing the acquired dynamic spectral data, obtaining several training samples, and marking the samples according to the diagnosis of the hospital. Specifically include the following steps:

[0035] (1) The patient puts his finger into the spectrometer to measure the patient's photoplethysmography.

[0036] (2) Perform low-pass filtering on the obtained photoplethysmogram to remove high-frequency noise.

[0037] (3) Use wavelet analysis or EMD to remove baseline drift, while retaining the data without baseline drift. That is, wavelet analysis or EMD is used to remove lo...

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 hemoglobin dynamic spectrum analytical prediction method based on deep learning technology. Compared with the prior art, the defect that the hemoglobin concentration and thecorresponding disease thereof cannot be comprehensively analyzed in real time in batch is solved, the error caused by performing regression analysis is artificially avoided, and the accuracy of the measurement is increased. The method comprises the following steps: acquiring and preprocessing deep learning training data: constructing a deep learning model; acquiring deep learning testing data; inputting the preprocessed training data, the testing data and the corresponding labels into the deep learning model to accomplish the training and the evaluation on the deep learning model; inputting the to-be-tested data into the trained deep learning model to perform the prediction. The hemoglobin dynamic spectrum analytical prediction is performed based on a structure model of the ResNet, the prediction accuracy of the hemoglobin concentration and the robustness of the model are improved.

Description

technical field [0001] The invention belongs to the technical field of data analysis and processing, and relates to a hemoglobin dynamic spectrum analysis and prediction method based on deep learning technology. Background technique [0002] Human hemoglobin concentration is one of the reliable basis for diagnosing anemia (low Hb) and polyhemoglobinemia vera (high Hb). Anemia occurs when the body's hemoglobin concentration falls below the normal range. According to the statistics of the World Health Organization, there are currently about 2 billion people in the world suffering from anemia in varying degrees. Factors causing anemia mainly include bone marrow hematopoietic dysfunction, hematopoietic substance deficiency or utilization disorder, hemolytic anemia, excessive blood loss caused by trauma, and some physiological reasons. On the other hand, when the hemoglobin level is higher than the normal range, it also reflects the existence of some diseases, such as cardiopul...

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): G06F19/24A61B5/00G06K9/62G06N3/08
CPCA61B5/0075G06N3/084G16B40/00G06F18/214
Inventor 刘玉良张全
Owner TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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