Cough Sound Identification: An Approach Based on Ensemble Learning

Christian Salamea-Palacios; Javier Guaña-Moya; Tarquino Sanchez; Xavier Calderón; David Naranjo

doi:10.1007/978-981-16-9268-0_22

Cough Sound Identification: An Approach Based on Ensemble Learning

Christian Salamea-Palacios^*, Javier Guaña-Moya, Tarquino Sanchez, Xavier Calderón, David Naranjo

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Cough identification using DSP techniques in an audio signal is a complex task; thus, an artificial intelligence approach is proposed by applying machine learning, deep learning, and HMMs algorithms. Later, an ensemble learning model has been used to differentiate cough from other environmental sounds, putting those algorithms together and choosing the best result as the performance of the system. The final system consists of a preprocessing stage where the audio signals are adjusted through data augmentation, normalization, removal of silent fragments, and the transformation to Mel spectrograms, while, on back-end stage, three models have been evaluated: a convolutional neural network, a random forest, and a classifier based on hidden Markov models. We assembled a hard voting classifier (VC) model from the three models to obtain a more robust and reliable model. The VC model reached the highest precision and F1-score values without false-negative and up to 75% of true-positive values.

Original language	English
Title of host publication	Smart Innovation, Systems and Technologies
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	269-278
Number of pages	10
DOIs	https://doi.org/10.1007/978-981-16-9268-0_22
State	Published - 2022

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	279
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Funding

To the Corporación Ecuatoriana para el Desarrollo de la Investigación y Academia, CEDIA, for the financing provided to research, development, and innovation through the CEPRA projects, especially the project CEPRA-XV-2021-011: Caracterización de la tos provocada por el COVID-19 en pacientes con diagnóstico positivo. The authors thank Escuela Politécnica Nacional, Universidad Politécnica Salesiana, and Pontificia Universidad Católica del Ecuador.

Funders	Funder number
Universidad Politécnica Salesiana del Ecuador
Corporación Ecuatoriana para el Desarrollo de la Investigación y la Academia	CEPRA-XV-2021-011
Pontifical Catholic University of Ecuador
Escuela Politécnica Nacional

Keywords

Convolutional neural network
Cough identification
Ensemble learning
Hidden Markov model
Random forest
Voting classifier

Access to Document

10.1007/978-981-16-9268-0_22

Cite this

Salamea-Palacios, C., Guaña-Moya, J., Sanchez, T., Calderón, X., & Naranjo, D. (2022). Cough Sound Identification: An Approach Based on Ensemble Learning. In Smart Innovation, Systems and Technologies (pp. 269-278). (Smart Innovation, Systems and Technologies; Vol. 279). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-9268-0_22

@inbook{de21be4c556246ca9f65f0acf062756a,

title = "Cough Sound Identification: An Approach Based on Ensemble Learning",

abstract = "Cough identification using DSP techniques in an audio signal is a complex task; thus, an artificial intelligence approach is proposed by applying machine learning, deep learning, and HMMs algorithms. Later, an ensemble learning model has been used to differentiate cough from other environmental sounds, putting those algorithms together and choosing the best result as the performance of the system. The final system consists of a preprocessing stage where the audio signals are adjusted through data augmentation, normalization, removal of silent fragments, and the transformation to Mel spectrograms, while, on back-end stage, three models have been evaluated: a convolutional neural network, a random forest, and a classifier based on hidden Markov models. We assembled a hard voting classifier (VC) model from the three models to obtain a more robust and reliable model. The VC model reached the highest precision and F1-score values without false-negative and up to 75% of true-positive values.",

keywords = "Convolutional neural network, Cough identification, Ensemble learning, Hidden Markov model, Random forest, Voting classifier",

author = "Christian Salamea-Palacios and Javier Gua{\~n}a-Moya and Tarquino Sanchez and Xavier Calder{\'o}n and David Naranjo",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.",

year = "2022",

doi = "10.1007/978-981-16-9268-0_22",

language = "English",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "269--278",

booktitle = "Smart Innovation, Systems and Technologies",

}

Cough Sound Identification: An Approach Based on Ensemble Learning. / Salamea-Palacios, Christian; Guaña-Moya, Javier; Sanchez, Tarquino et al.
Smart Innovation, Systems and Technologies. Springer Science and Business Media Deutschland GmbH, 2022. p. 269-278 (Smart Innovation, Systems and Technologies; Vol. 279).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Cough Sound Identification

T2 - An Approach Based on Ensemble Learning

AU - Salamea-Palacios, Christian

AU - Guaña-Moya, Javier

AU - Sanchez, Tarquino

AU - Calderón, Xavier

AU - Naranjo, David

PY - 2022

Y1 - 2022

N2 - Cough identification using DSP techniques in an audio signal is a complex task; thus, an artificial intelligence approach is proposed by applying machine learning, deep learning, and HMMs algorithms. Later, an ensemble learning model has been used to differentiate cough from other environmental sounds, putting those algorithms together and choosing the best result as the performance of the system. The final system consists of a preprocessing stage where the audio signals are adjusted through data augmentation, normalization, removal of silent fragments, and the transformation to Mel spectrograms, while, on back-end stage, three models have been evaluated: a convolutional neural network, a random forest, and a classifier based on hidden Markov models. We assembled a hard voting classifier (VC) model from the three models to obtain a more robust and reliable model. The VC model reached the highest precision and F1-score values without false-negative and up to 75% of true-positive values.

AB - Cough identification using DSP techniques in an audio signal is a complex task; thus, an artificial intelligence approach is proposed by applying machine learning, deep learning, and HMMs algorithms. Later, an ensemble learning model has been used to differentiate cough from other environmental sounds, putting those algorithms together and choosing the best result as the performance of the system. The final system consists of a preprocessing stage where the audio signals are adjusted through data augmentation, normalization, removal of silent fragments, and the transformation to Mel spectrograms, while, on back-end stage, three models have been evaluated: a convolutional neural network, a random forest, and a classifier based on hidden Markov models. We assembled a hard voting classifier (VC) model from the three models to obtain a more robust and reliable model. The VC model reached the highest precision and F1-score values without false-negative and up to 75% of true-positive values.

KW - Convolutional neural network

KW - Cough identification

KW - Ensemble learning

KW - Hidden Markov model

KW - Random forest

KW - Voting classifier

UR - http://www.scopus.com/inward/record.url?scp=85127647897&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-9268-0_22

DO - 10.1007/978-981-16-9268-0_22

M3 - Chapter

AN - SCOPUS:85127647897

T3 - Smart Innovation, Systems and Technologies

SP - 269

EP - 278

BT - Smart Innovation, Systems and Technologies

PB - Springer Science and Business Media Deutschland GmbH

ER -

Cough Sound Identification: An Approach Based on Ensemble Learning

Abstract

Publication series

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this