DiCOVA-Net: Diagnosing COVID-19 using Acoustics based on Deep Residual Network for the DiCOVA Challenge 2021. (arXiv:2107.06126v2 [cs.SD] UPDATED)

Web: http://arxiv.org/abs/2107.06126

In this paper, we propose a deep residual network-based method, namely the
DiCOVA-Net, to identify COVID-19 infected patients based on the acoustic
recording of their coughs. Since there are far more healthy people than
infected patients, this classification problem faces the challenge of
imbalanced data. To improve the model's ability to recognize minority class
(the infected patients), we introduce data augmentation and cost-sensitive
methods into our model. Besides, considering the particularity of this task, we
deploy some fine-tuning techniques to …

2021 arxiv challenge covid covid-19 deep network on