Application of time-frequency analysis and back-propagation neural network in the lung sound signal recognition

Mei-Yung Chen, Chien Chou Huang

Research output: Contribution to journalConference article

Abstract

In the diagnosis of the respiratory diseases, auscultation is a non-invasive and convenient diagnostic method. In the digital auscultation analysis, what method we use to analyze the lung signals which microphone recorded will affect the results of the experiment greatly. The purpose of this study is to use frequency analysis and time-frequency analysis to analyze the six lung sound signals, which are vesicular breath sounds, bronchial breath sounds, crackle, and wheeze. Finally, the study transformed the analysis results into the characteristic images, and put them to the back propagation neural network for training. After that, the study compares the results of the two methods. We also analyze the realistic lung sound signals and simulated lung sound signals, and compare the results finally. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire LS signals, and signals preprocessing. Then we use Visual Signal to analyze the lung sound signals by time-frequency analysis. We also analyze the lung sound signals which are from the auscultation teaching website. Finally we compare the result of two kinds of signals, and assess their similarity and accuracy by the test of back-propagation neural network. According to the result of this study, we found that time-frequency analysis provide much information about the lung signals, and are more suitable as a basis of diagnosis, and increase the recognition rate of the back-propagation neural network.

Original languageEnglish
Pages (from-to)927-930
Number of pages4
JournalApplied Mechanics and Materials
Volume190-191
DOIs
Publication statusPublished - 2012 Oct 16
Event3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012 - Guangxi, China
Duration: 2012 Aug 12012 Aug 2

Fingerprint

Backpropagation
Acoustic waves
Neural networks
Microphones
Pulmonary diseases
Websites
Data acquisition
Teaching
Experiments

Keywords

  • Back-propagation neural network
  • Lung sound signal
  • Time-frequency analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Application of time-frequency analysis and back-propagation neural network in the lung sound signal recognition. / Chen, Mei-Yung; Huang, Chien Chou.

In: Applied Mechanics and Materials, Vol. 190-191, 16.10.2012, p. 927-930.

Research output: Contribution to journalConference article

@article{06d4b4bbee7549f980ac6e2240ea2bcd,
title = "Application of time-frequency analysis and back-propagation neural network in the lung sound signal recognition",
abstract = "In the diagnosis of the respiratory diseases, auscultation is a non-invasive and convenient diagnostic method. In the digital auscultation analysis, what method we use to analyze the lung signals which microphone recorded will affect the results of the experiment greatly. The purpose of this study is to use frequency analysis and time-frequency analysis to analyze the six lung sound signals, which are vesicular breath sounds, bronchial breath sounds, crackle, and wheeze. Finally, the study transformed the analysis results into the characteristic images, and put them to the back propagation neural network for training. After that, the study compares the results of the two methods. We also analyze the realistic lung sound signals and simulated lung sound signals, and compare the results finally. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire LS signals, and signals preprocessing. Then we use Visual Signal to analyze the lung sound signals by time-frequency analysis. We also analyze the lung sound signals which are from the auscultation teaching website. Finally we compare the result of two kinds of signals, and assess their similarity and accuracy by the test of back-propagation neural network. According to the result of this study, we found that time-frequency analysis provide much information about the lung signals, and are more suitable as a basis of diagnosis, and increase the recognition rate of the back-propagation neural network.",
keywords = "Back-propagation neural network, Lung sound signal, Time-frequency analysis",
author = "Mei-Yung Chen and Huang, {Chien Chou}",
year = "2012",
month = "10",
day = "16",
doi = "10.4028/www.scientific.net/AMM.190-191.927",
language = "English",
volume = "190-191",
pages = "927--930",
journal = "Applied Mechanics and Materials",
issn = "1660-9336",
publisher = "Trans Tech Publications",

}

TY - JOUR

T1 - Application of time-frequency analysis and back-propagation neural network in the lung sound signal recognition

AU - Chen, Mei-Yung

AU - Huang, Chien Chou

PY - 2012/10/16

Y1 - 2012/10/16

N2 - In the diagnosis of the respiratory diseases, auscultation is a non-invasive and convenient diagnostic method. In the digital auscultation analysis, what method we use to analyze the lung signals which microphone recorded will affect the results of the experiment greatly. The purpose of this study is to use frequency analysis and time-frequency analysis to analyze the six lung sound signals, which are vesicular breath sounds, bronchial breath sounds, crackle, and wheeze. Finally, the study transformed the analysis results into the characteristic images, and put them to the back propagation neural network for training. After that, the study compares the results of the two methods. We also analyze the realistic lung sound signals and simulated lung sound signals, and compare the results finally. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire LS signals, and signals preprocessing. Then we use Visual Signal to analyze the lung sound signals by time-frequency analysis. We also analyze the lung sound signals which are from the auscultation teaching website. Finally we compare the result of two kinds of signals, and assess their similarity and accuracy by the test of back-propagation neural network. According to the result of this study, we found that time-frequency analysis provide much information about the lung signals, and are more suitable as a basis of diagnosis, and increase the recognition rate of the back-propagation neural network.

AB - In the diagnosis of the respiratory diseases, auscultation is a non-invasive and convenient diagnostic method. In the digital auscultation analysis, what method we use to analyze the lung signals which microphone recorded will affect the results of the experiment greatly. The purpose of this study is to use frequency analysis and time-frequency analysis to analyze the six lung sound signals, which are vesicular breath sounds, bronchial breath sounds, crackle, and wheeze. Finally, the study transformed the analysis results into the characteristic images, and put them to the back propagation neural network for training. After that, the study compares the results of the two methods. We also analyze the realistic lung sound signals and simulated lung sound signals, and compare the results finally. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire LS signals, and signals preprocessing. Then we use Visual Signal to analyze the lung sound signals by time-frequency analysis. We also analyze the lung sound signals which are from the auscultation teaching website. Finally we compare the result of two kinds of signals, and assess their similarity and accuracy by the test of back-propagation neural network. According to the result of this study, we found that time-frequency analysis provide much information about the lung signals, and are more suitable as a basis of diagnosis, and increase the recognition rate of the back-propagation neural network.

KW - Back-propagation neural network

KW - Lung sound signal

KW - Time-frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=84867304110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867304110&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMM.190-191.927

DO - 10.4028/www.scientific.net/AMM.190-191.927

M3 - Conference article

AN - SCOPUS:84867304110

VL - 190-191

SP - 927

EP - 930

JO - Applied Mechanics and Materials

JF - Applied Mechanics and Materials

SN - 1660-9336

ER -