Predicting Respiratory Diseases from Lung Sounds using Ensemble Model

Abstract

The paper introduces an ensemble model combined with CNN and data augmentation to predict respiratory diseases. Respiratory diseases are one of the top causes of death around the world, according to WHO there are about three million people die each year from respiratory diseases, an estimated 6% of all deaths worldwide. The goal of the paper is to be able to diagnose the respiratory disease from lung sound using ensemble model and applying data augmentation. This technique may help healthcare professionals to save people's life. The aim was to classify two classes from a dataset of respiratory sounds. The model used in this paper was a combination between CNN and Random Forest to classify the respiratory disease with accuracy of 93%.