An ensemble learning approach to digital corona virus preliminary screening from cough sounds

Abstract This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound da...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Emad A. Mohammed, Mohammad Keyhani, Amir Sanati-Nezhad, S. Hossein Hejazi, Behrouz H. Far
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/a8c423bfccc843dab31a04987be2c16c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a8c423bfccc843dab31a04987be2c16c
record_format dspace
spelling oai:doaj.org-article:a8c423bfccc843dab31a04987be2c16c2021-12-02T16:06:44ZAn ensemble learning approach to digital corona virus preliminary screening from cough sounds10.1038/s41598-021-95042-22045-2322https://doaj.org/article/a8c423bfccc843dab31a04987be2c16c2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95042-2https://doaj.org/toc/2045-2322Abstract This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.Emad A. MohammedMohammad KeyhaniAmir Sanati-NezhadS. Hossein HejaziBehrouz H. FarNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Emad A. Mohammed
Mohammad Keyhani
Amir Sanati-Nezhad
S. Hossein Hejazi
Behrouz H. Far
An ensemble learning approach to digital corona virus preliminary screening from cough sounds
description Abstract This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.
format article
author Emad A. Mohammed
Mohammad Keyhani
Amir Sanati-Nezhad
S. Hossein Hejazi
Behrouz H. Far
author_facet Emad A. Mohammed
Mohammad Keyhani
Amir Sanati-Nezhad
S. Hossein Hejazi
Behrouz H. Far
author_sort Emad A. Mohammed
title An ensemble learning approach to digital corona virus preliminary screening from cough sounds
title_short An ensemble learning approach to digital corona virus preliminary screening from cough sounds
title_full An ensemble learning approach to digital corona virus preliminary screening from cough sounds
title_fullStr An ensemble learning approach to digital corona virus preliminary screening from cough sounds
title_full_unstemmed An ensemble learning approach to digital corona virus preliminary screening from cough sounds
title_sort ensemble learning approach to digital corona virus preliminary screening from cough sounds
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/a8c423bfccc843dab31a04987be2c16c
work_keys_str_mv AT emadamohammed anensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT mohammadkeyhani anensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT amirsanatinezhad anensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT shosseinhejazi anensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT behrouzhfar anensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT emadamohammed ensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT mohammadkeyhani ensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT amirsanatinezhad ensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT shosseinhejazi ensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
AT behrouzhfar ensemblelearningapproachtodigitalcoronaviruspreliminaryscreeningfromcoughsounds
_version_ 1718384862143971328