CovidCoughNet: A new method based on convolutional neural networks and deep feature extraction using pitch-shifting data augmentation for covid-19 detection from cough, breath, and voice signals.
Gaffari ÇelikPublished in: Comput. Biol. Medicine (2023)
Keyphrases
- synthetic data
- detection method
- noisy data
- fundamental frequency
- data sets
- input data
- missing data
- feature extraction
- statistical methods
- preprocessing
- pairwise
- clustering method
- extracted features
- test data
- prior knowledge
- detection algorithm
- missing values
- dynamic programming
- training data
- hilbert huang transform
- training samples
- data sources
- manifold learning
- similarity measure