Lung sound signal processing method for electronic auscultation

A signal processing and lung sound technology, applied in stethoscopes, auscultation instruments, pattern recognition in signals, etc., can solve problems such as the accuracy of cumbersome processing results and the impact on the results of lung sound type judgment, so as to alleviate gradient disappearance or gradient explosion, and protect Integrity, the effect of reducing the difficulty of learning

Pending Publication Date: 2020-07-31
HARBIN INST OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the existing signal processing process of lung sound auscultation recording is cumbersome, which makes the processing result poor i

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
  • Lung sound signal processing method for electronic auscultation
  • Lung sound signal processing method for electronic auscultation
  • Lung sound signal processing method for electronic auscultation

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0053] Specific implementation mode 1. Combination Figure 1 to Figure 3 As shown, the invention provides a kind of lung sound signal processing method of electronic auscultation, comprising:

[0054] Perform band-pass filtering, down-sampling and normalization processing on the collected original lung sound signal in order to obtain the lung sound signal to be trained;

[0055] Using a plurality of convolution units to process the lung sound signal to be trained to obtain a feature vector of the lung sound signal; the connection mode of the plurality of convolution units includes sequential connection and skip connection;

[0056] A fully connected layer is used to process the lung sound signal feature vector finally output by the convolution unit to obtain a classification result.

[0057] After the original lung sound signal is band-pass filtered, fine noise can also be filtered out, for example, the fine noise can be directly cut off.

[0058] Further, the performing bandp...

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 lung sound signal processing method for electronic auscultation, and belongs to the field of signal classification of machine learning. The problems are solved that since anexisting processing process of lung sound auscultation recording signals is cumbersome, the processing result has poor accuracy, and the final judgment result of the types of lung sounds is affected.The method includes the steps: performing band-pass filtering on the collected original lung sound signals, performing downsampling and normalization processing sequentially so as to obtain to-be-trained lung sound signals, and adopting multiple convolution units to process the to-be-trained lung sound signals so as to obtain lung sound signal feature vectors, wherein the connection mode of the multiple convolution units includes sequential connection and skip connection; and adopting a full-connection layer to process the lung sound signal feature vectors which are finally output by the convolution units so as to obtain classification results. The method can be applied to classification of the lung sound signals.

Description

technical field [0001] The invention relates to a lung sound signal processing method of electronic auscultation, and belongs to the field of signal classification of machine learning. Background technique [0002] The electronic stethoscope is composed of three parts. The first part is the radio equipment. Its structure is similar to the stethoscope head of the ordinary stethoscope. It can collect the breathing sound signal of the lungs and connect to the second part through the transfer device connected at the end; the second part The second part is the recording pen, which is responsible for recording and saving the sound collected by the radio equipment; the third part is the listening device, that is, the mechanical earphone. In the process of sampling the lung sound signal of the patient, the doctor needs to ensure that he listens and records at the same time to determine the type of lung sound and record it; the result of the judgment of the lung sound type is used 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): A61B7/04G06K9/00G06K9/62G06N3/04
CPCA61B7/04A61B7/003G06N3/045G06F2218/04G06F2218/08G06F2218/12G06F18/214
Inventor 路程李鑫慧刘国栋侯代玉许梓艺刘炳国林春红包智慧王晓辉
Owner HARBIN INST OF TECH
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