Investigating Feature Selection and Explainability for COVID-19 Diagnostics from Cough Sounds
Abstrak
In this paper, we propose an approach to automatically classify COVID-19 and non-COVID-19 cough samples based on the combination of both feature engineering and deep learning models. In the feature engineering approach, we develop a support vector machine classifier over high dimensional (6373D) space of acoustic features. In the deep learning-based approach, on the other hand, we apply a convolutional neural network trained on the log-mel spectrograms. These two methodologically diverse models are then combined by fusing the probability scores of the models. The proposed system, which ranked 9th on the 2021 Diagnosing COVID-19 using Acoustics (Di- COVA) challenge leaderboard, obtained an area under the receiver operating characteristic curve (AUC) of 0:81 on the blind test data set, which is a 10:9% absolute improvement compared to the baseline. Moreover, we analyze the explainability of the deep learning-based model when detecting COVID-19 from cough signals. Copyright © 2021 ISCA.
Topik & Kata Kunci
Penulis (9)
F. Avila
A. H. Poorjam
Deepak Mittal
Charles Dognin
Ananya Muguli
Rohit Kumar
Srikanth Raj Chetupalli
Sriram Ganapathy
M. Singh
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2021
- Bahasa
- en
- Total Sitasi
- 10×
- Sumber Database
- Semantic Scholar
- DOI
- 10.21437/interspeech.2021-2197
- Akses
- Open Access ✓