Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients

Charleston-Villalobos, S.; Martínez-Hernández, Gabriela Belen; González-Camarena, R.; Chi-Lem, G.; Carrillo, Julio Manuel Afonso

doi:10.1016/j.compbiomed.2011.04.009

Cited by 65 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Percentile frequencies [4], eigenvalues of covariance matrices [4], and cepstral coefficients [5] were also used. The multivariate version of the AR model, namely, vector auto-regressive (VAR) model, has been used in two recent studies [4], [6]. For classification, k-nearest neighbor [2], [3] and artificial neural network [4], [5] algorithms were adopted.…”

Section: A Comparison Of Svm and Gmm-based Classifiermentioning

confidence: 99%

“…Most of the pulmonary diseases belong to one of two main categories, namely, obstructive (e.g., asthma, emphysema, bronchiectasis) and restrictive (e.g., interstitial lung disease (ILD), the term referring to a broad group of diseases including pneumonia). In the majority of studies [2]- [4], the binary case of healthy versus pathological classification was considered, where the pathological classes were composed of several diseases from both obstructive and restrictive categories [2], [3] or of a group of diseases from a single category [4]. Only two of the studies adopted a three-class structure, where the obstructive and restrictive classes are considered separately, in addition to the healthy class [5], [6].…”

Section: A Comparison Of Svm and Gmm-based Classifiermentioning

confidence: 99%

See 1 more Smart Citation

A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds

Şen

Saraçlar

Kahya

2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

Section: A Comparison Of Svm and Gmm-based Classifiermentioning

confidence: 99%

Section: A Comparison Of Svm and Gmm-based Classifiermentioning

confidence: 99%

A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds

Şen

Saraçlar

Kahya

2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…Therefore, their accuracy results were either very high when there was a very distinct set of audio data or very low when the audio data was similar [16,[25][26][27][28][29][30][31][32][33][34][35][36][37]. This is a major problem as these systems deal with a critical decision in patient's diagnosis.…”

Section: Resultsmentioning

confidence: 99%

Classification of lung sounds using convolutional neural networks

Aykanat

Kılıç

Kurt

et al. 2017

J Image Video Proc.

205

110

View full text Add to dashboard Cite

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms. In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects. We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively. As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

show abstract

“…The activation function used in this work is sigmoidal (sig) activation function as shown in Eq. (11).…”

Section: Classificationmentioning

confidence: 95%

A telemedicine tool to detect pulmonary pathology using computerized pulmonary acoustic signal analysis

Palaniappan

Sundaraj

et al. 2015

Applied Soft Computing

View full text Add to dashboard Cite

Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients

Cited by 65 publications

References 22 publications

A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds

A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds

Classification of lung sounds using convolutional neural networks

A telemedicine tool to detect pulmonary pathology using computerized pulmonary acoustic signal analysis

Contact Info

Product

Resources

About