Early Detection of COVID-19 Patients using Chromagram Features of Cough Sound Recordings with Machine Learning Algorithms
Rumana Islam, Esam Abdel‐Raheem, Mohammed Tarique
Abstract
This paper presents a cough sound-based fast, automated, and noninvasive COVID-19 detection system to discriminate the cough sounds of the COVID-19 patients from the healthy individuals. The proposed system extracts an acoustic feature called chromagram from the cough sound samples and applies it to the input of a classifier algorithm. Two artificial neural network (ANN) based classifiers namely convolutional neural network (CNN) and deep neural network (DNN) are modeled for this purpose. The simulation results show that the proposed system achieves an accuracy of 92.9% and 91.7% with CNN and DNN respectively. The performance comparison of the proposed system with two popular machine learning algorithms namely support vector machine (SVM) and k-nearest neighbor (kNN) are also presented in this work.