Classification du son contre la toux fondée sur des méthodes explicables : étude de cas Covid 19

Abstract

This project aims to develop a computer-aided diagnostic tool for the early detection of COVID-19 through voice analysis. The proposed system operates in two main stages: sound feature extraction and classification. For feature extraction, we utilized Mel-Frequency Cepstral Coefficients (MFCCs), a common technique in voice-based disease detection. The disease classification task employs three supervised machine learning algorithms: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree (DT). We will evaluate our proposed system using a publicly available dataset (TOS). The performance of the system will be measured using metrics such as accuracy, sensitivity, specificity, F1 score, and Receiver Operating Characteristic (ROC) curves. These metrics provide insights into the system's ability to correctly identify positive and negative cases.