Classification of Respiratory Sounds with Convolutional Neural Network

A. A. Francisco, A. A. Saraiva, D. B. S. Santos, A. A. Francisco, Jose Vigno Moura Sousa, Jose Vigno Moura Sousa, N. M. Fonseca Ferreira, N. M. Fonseca Ferreira, Salviano Soares, Antonio Valente, Antonio Valente

2020

Abstract

Noting recent advances in the field of image classification, where convolutional neural networks (CNNs) are used to classify images with high precision. This paper proposes a method of classifying breathing sounds using CNN, where it is trained and tested. To do this, a visual representation of each audio sample was made that allows identifying resources for classification, using the same techniques used to classify images with high precision.For this we used the technique known as Mel Frequency Cepstral Coefficients (MFCCs). For each audio file in the dataset, we extracted resources with MFCC which means we have an image representation for each audio sample. The method proposed in this article obtained results above 74%, in the classification of respiratory sounds used in the four classes available in the database used (Normal, crackles, wheezes, Both).

Paper Citation

in Harvard Style

Saraiva A., B. S. Santos D., Francisco A., Sousa J., Ferreira N., Soares S. and Valente A. (2020). Classification of Respiratory Sounds with Convolutional Neural Network. In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 3: BIOINFORMATICS; ISBN 978-989-758-398-8, SciTePress, pages 138-144. DOI: 10.5220/0008965101380144

in Bibtex Style

@conference{bioinformatics20,
author={A. A. Saraiva and D. B. S. B. S. Santos and A. A. Francisco and Jose Vigno Moura Sousa and N. M. Fonseca Ferreira and Salviano Soares and Antonio Valente},
title={Classification of Respiratory Sounds with Convolutional Neural Network},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 3: BIOINFORMATICS},
year={2020},
pages={138-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008965101380144},
isbn={978-989-758-398-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 3: BIOINFORMATICS
TI - Classification of Respiratory Sounds with Convolutional Neural Network
SN - 978-989-758-398-8
AU - Saraiva A.
AU - B. S. Santos D.
AU - Francisco A.
AU - Sousa J.
AU - Ferreira N.
AU - Soares S.
AU - Valente A.
PY - 2020
SP - 138
EP - 144
DO - 10.5220/0008965101380144
PB - SciTePress