Applying cybernetic technology to diagnose human pulmonary sounds topical collection on education & training

Mei Yung Chen, Cheng Han Chou

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.

Original languageEnglish
Article number58
JournalJournal of Medical Systems
Volume38
Issue number6
DOIs
Publication statusPublished - 2014 Jun

Fingerprint

Cybernetics
Respiratory Sounds
Education
Acoustic waves
Technology
Auscultation
Neural networks
Heart Sounds
Wavelet Analysis
Aptitude
Haploidy
ROC Curve
Lung Diseases
Ear
Pulmonary diseases
Thorax
Vector quantization
Learning

Keywords

  • 2-stage classifier
  • Artificial neural network (ANN)
  • Pulmonary sounds (PSs)
  • Receiver operating characteristic curve
  • Wavelet transform

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Information Systems
  • Health Informatics
  • Health Information Management

Cite this

Applying cybernetic technology to diagnose human pulmonary sounds topical collection on education & training. / Chen, Mei Yung; Chou, Cheng Han.

In: Journal of Medical Systems, Vol. 38, No. 6, 58, 06.2014.

Research output: Contribution to journalArticle

@article{dca1b3581f1b4de9a9e75ca91f237eb9,
title = "Applying cybernetic technology to diagnose human pulmonary sounds topical collection on education & training",
abstract = "Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.",
keywords = "2-stage classifier, Artificial neural network (ANN), Pulmonary sounds (PSs), Receiver operating characteristic curve, Wavelet transform",
author = "Chen, {Mei Yung} and Chou, {Cheng Han}",
year = "2014",
month = "6",
doi = "10.1007/s10916-014-0058-5",
language = "English",
volume = "38",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "6",

}

TY - JOUR

T1 - Applying cybernetic technology to diagnose human pulmonary sounds topical collection on education & training

AU - Chen, Mei Yung

AU - Chou, Cheng Han

PY - 2014/6

Y1 - 2014/6

N2 - Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.

AB - Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.

KW - 2-stage classifier

KW - Artificial neural network (ANN)

KW - Pulmonary sounds (PSs)

KW - Receiver operating characteristic curve

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=84904043208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904043208&partnerID=8YFLogxK

U2 - 10.1007/s10916-014-0058-5

DO - 10.1007/s10916-014-0058-5

M3 - Article

AN - SCOPUS:84904043208

VL - 38

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 6

M1 - 58

ER -