Multi-features Extraction for Automating Covid-19 Detection from Cough Sound using Deep Neural Networks

This research paper proposed a smart system based on deep learning to detect COVID-19 patient's using the cough sound. The deep neural networks are used to distinguish between different types of cough COVID-19 positive or negative coughs. The proposed system is segmented into three stages: Audio pre-processing by noise reduction, segmentation, feature extraction, classification, and model deployment. Eight features have been extracted from 1635 sound subjects: 573 COVID-19 positive and 1062 negative coughs. The feature's extracted data have trained using two models; first model Cough detection based on ANN used to distinguish if there is cough or not, the second model to detect the covid-19 using Convolutional Neural Network. The overall accuracy for both models is 98.1% for the Cough model and 98.5% for the Covid-19 model. The models were compiled after deployment to work together as a web service based on flask. Cough model receives cough sound from the mobile app or web interface and discriminates if there is cough then passe it coivd1-9 model that will analyze if cough is positive or negative. and send the result back to the mobile app.