In another study, 477 hand-crafted features, including zero-crossing, spectral centroid, and Mel frequency Cepstral Portions (MFCCs), were used to correctly classify healthy and COVID-19 sounds from a crowdsourced dataset of respiratory sounds. Using Origianal double Patterns (LBPs) and Haralick's system as the point birth styles, an audio texture analysis was carried out on three distinct signal modalities of COVID-19 sounds—cough, breath, and speech signal. Another study used biomedical data (body temperature, heart rate, and SpO2) from 1085 quarantined healthy and unhealthy individuals collected through a wearable device to infer COVID- 19 infections, in contrast to cough sounds [5].