TY - GEN
T1 - Deep Learning with hyper-parameter tuning for COVID-19 Cough Detection
AU - Rao, Sunil
AU - Narayanaswamy, Vivek
AU - Esposito, Michael
AU - Thiagarajan, Jayaraman
AU - Spanias, Andreas
N1 - Funding Information:
This work was funded by the REU supplement NSF NCSS/SenSIP I/UCRC Award number 1540040. We would also like to thank the authors in [41] for their insightful suggestions on model development.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/12
Y1 - 2021/7/12
N2 - As the COVID-19 pandemic continues, rapid non-invasive testing has become essential. Recent studies and benchmarks motivates the use of modern artificial intelligence (AI) tools that utilize audio waveform spectral features of coughing for COVID-19 diagnosis. In this paper, we describe the system we developed for COVID-19 cough detection. We utilize features directly extracted from the coughing audio and use deep learning algorithms to develop automated diagnostic tools for COVID-19. In particular, we develop a unique modification of the VGG13 deep learning architecture for audio analysis that uses log-mel spectrograms and a combination of binary cross entropy and focal losses. This unique modification enabled the model to achieve highly robust classification of the DiCOVA 2021 COVID-19 data. We also explore the use of data augmentation and an ensembling strategy to further improve the performance on the validation and the blind test datasets. Our model achieved an average validation AUROC of 82.23% and a test AUROC of 78.3% at a sensitivity of 80.49%.
AB - As the COVID-19 pandemic continues, rapid non-invasive testing has become essential. Recent studies and benchmarks motivates the use of modern artificial intelligence (AI) tools that utilize audio waveform spectral features of coughing for COVID-19 diagnosis. In this paper, we describe the system we developed for COVID-19 cough detection. We utilize features directly extracted from the coughing audio and use deep learning algorithms to develop automated diagnostic tools for COVID-19. In particular, we develop a unique modification of the VGG13 deep learning architecture for audio analysis that uses log-mel spectrograms and a combination of binary cross entropy and focal losses. This unique modification enabled the model to achieve highly robust classification of the DiCOVA 2021 COVID-19 data. We also explore the use of data augmentation and an ensembling strategy to further improve the performance on the validation and the blind test datasets. Our model achieved an average validation AUROC of 82.23% and a test AUROC of 78.3% at a sensitivity of 80.49%.
KW - COVID-19
KW - acoustics
KW - healthcare
KW - machine learning
KW - respiratory diagnosis
UR - http://www.scopus.com/inward/record.url?scp=85117452624&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117452624&partnerID=8YFLogxK
U2 - 10.1109/IISA52424.2021.9555564
DO - 10.1109/IISA52424.2021.9555564
M3 - Conference contribution
AN - SCOPUS:85117452624
T3 - IISA 2021 - 12th International Conference on Information, Intelligence, Systems and Applications
BT - IISA 2021 - 12th International Conference on Information, Intelligence, Systems and Applications
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Conference on Information, Intelligence, Systems and Applications, IISA 2021
Y2 - 12 July 2021 through 14 July 2021
ER -