Date of Award


Document Type


Degree Name

Master of Science in Computer Science


School of Computer Science and Engineering

First Reader/Committee Chair

Dr.Jennifer Jin


Auscultation plays a role, in diagnosing and identifying diseases during examinations. However, it requires training and expertise, for application. This study aims to tackle this challenge by introducing a model that categorizes respiratory sounds into eight groups: URTI, Healthy, Asthma, COPD, LRTI, Bronchiectasis, Pneumonia, and Bronchiolitis. To achieve this categorization the study utilizes a Convolutional Neural Network (CNN) model that has been optimized using techniques. The dataset used in the study consists of 920 audio samples obtained from 126 patients with durations ranging from 10 to 90 seconds. Impressively, the model demonstrates a noteworthy 83% validation accuracy and an impressive 86% training accuracy, highlighting its robust and effective performance. To enhance user interaction and facilitate result visualization, the research team has developed a user-friendly interface using Flask, HTML, and CSS. This interface provides healthcare professionals and other stakeholders with the means to access and interpret the results of the experimental analysis. Overall, this research marks a significant stride in making respiratory sound analysis more accessible and accurate, thus contributing to improved disease diagnosis and patient care.