TY - GEN
T1 - Harnessing the Power of Vocal Signals in COVID-19 Detection Utilizing Machine Learning
AU - Mann, Aleesa
AU - Jadhav, Ajinkya P.
AU - Matovu, Richard
AU - Gupta, Vibhuti
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The global COVID-19 pandemic has strained health-care systems and highlighted the need for accessible and efficient diagnostic methods. Traditional diagnostic tools, such as nasal swabs and biosensors, while accurate, pose significant logistical challenges and high costs, limiting their scalability. This paper explores an alternative, non-invasive approach to COVID-19 detection using machine learning algorithms to analyze vocal patterns, particularly cough and breathing sounds. Leveraging a publicly available dataset, we developed machine learning models capable of classifying audio samples as COVID-19 positive or negative. Our models achieve an AUC of up to 85% and an F1-score of 81%, demonstrating the potential of machine learning in enabling rapid, cost-effective COVID-19 diagnosis. These findings suggest that audio-based diagnostics could be a practical and scalable solution, particularly in resource-limited settings where traditional methods are less feasible.
AB - The global COVID-19 pandemic has strained health-care systems and highlighted the need for accessible and efficient diagnostic methods. Traditional diagnostic tools, such as nasal swabs and biosensors, while accurate, pose significant logistical challenges and high costs, limiting their scalability. This paper explores an alternative, non-invasive approach to COVID-19 detection using machine learning algorithms to analyze vocal patterns, particularly cough and breathing sounds. Leveraging a publicly available dataset, we developed machine learning models capable of classifying audio samples as COVID-19 positive or negative. Our models achieve an AUC of up to 85% and an F1-score of 81%, demonstrating the potential of machine learning in enabling rapid, cost-effective COVID-19 diagnosis. These findings suggest that audio-based diagnostics could be a practical and scalable solution, particularly in resource-limited settings where traditional methods are less feasible.
KW - breathing
KW - Coronavirus
KW - coughs
KW - COVID-19
KW - COVID-19 detection
KW - machine learning
KW - vocal signal analysis
UR - https://www.scopus.com/pages/publications/85218022771
UR - https://www.scopus.com/pages/publications/85218022771#tab=citedBy
U2 - 10.1109/BigData62323.2024.10825050
DO - 10.1109/BigData62323.2024.10825050
M3 - Conference contribution
AN - SCOPUS:85218022771
T3 - Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024
SP - 4564
EP - 4570
BT - Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024
A2 - Ding, Wei
A2 - Lu, Chang-Tien
A2 - Wang, Fusheng
A2 - Di, Liping
A2 - Wu, Kesheng
A2 - Huan, Jun
A2 - Nambiar, Raghu
A2 - Li, Jundong
A2 - Ilievski, Filip
A2 - Baeza-Yates, Ricardo
A2 - Hu, Xiaohua
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Big Data, BigData 2024
Y2 - 15 December 2024 through 18 December 2024
ER -