Classification of Pulmonary Diseases Using Cough Sounds

Pulmonary diseases include Asthma, Chronic Obstructive Pulmonary Disease (COPD), Pneumonia and Bronchiolitis are the pose significant health risks worldwide. Early detection and accurate classification of these diseases are critical for timely treatment and improved patient outcomes. Traditional diagnostic methods such as imaging and lung function tests are often resource-intensive and time-consuming. Alternatively, recent research has explored the use of non-invasive methods, such as analysing cough sounds for pulmonary disease classification. Cough sounds contain valuable information that reflects the underlying respiratory condition and approaches for disease detection. Existing system contains limited dataset, influence of background noise and variability in cough sounds. The proposed framework consists of three main stages: pre-processing, feature extraction, and classification. Using the deep learning model Convolutional Neural Network (CNN) for extracting features and predicting the respiratory disease based on the cough sound. Future work will focus on expanding the dataset, improving feature extraction methods, and incorporating real-time analysis to develop a practical diagnostic tool for clinical use.