Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article


Master of Science


Computer Science

Collaborative Specialization

Artificial Intelligence


Haque, Anwar


Corona Virus (COVID-19) is a highly contagious respiratory disease that the World Health Organization (WHO) has declared a worldwide epidemic. This virus has spread worldwide, affecting various countries until now, causing millions of deaths globally. To tackle this public health crisis, medical professionals and researchers are working relentlessly, applying different techniques and methods. In terms of diagnosis, respiratory sound has been recognized as an indicator of one’s health condition. Our work is based on cough sound analysis. This study has included an in-depth analysis of the diagnosis of COVID-19 based on human cough sound. Based on cough audio samples from crowdsourced COVID data, we develop an audio-based framework, deploying traditional Machine Learning (ML), Resampling multiclass ML approach, Cost-Sensitive Multiclass ML, and Multiclass Deep Learning (DL) approaches for COVID-19 digital screening. Our experimental results indicate that the resampling Multiclass ML approach shows the best result for COVID-19 digital prescreening with an AUC of 78.77%. To the best of our knowledge, this is the first COVID-19 detection tool that uses such diverse crowdsourced and largest physician annotated COVID data that uses patients’ cough sound data to predict the presence of COVID-19 in those patients by applying multiple multiclass data balance techniques for AI algorithms. Our proposed novel framework and the developed tool will assist in a) automating COVID-19 digital pre-screening, b) making the COVID test more accessible and cost-effective, c) helping to detect an infected individual before a physical COVID test, and d) reducing the risk of infecting others.

Summary for Lay Audience

The COVID-19 epidemic has nearly brought the world to a halt since February 2020. Countries were placed on lockdown, millions of people died, healthcare facilities were overburdened, and the global economy saw one of its worst periods as a result of the epidemic. To address this issue, researchers throughout the world are investing in the development of a rapid, reliable, non-invasive diagnostic process. One of the most essential research initiatives is to employ coughs and their accompanying vocal biomarkers to diagnose COVID-19. In this thesis, we proposed a novel Artificial Intelligence (AI) based COVID-19 digital screening technique based on cough audio data from COVID patients. The proposed framework will aid in the promotion of contactless self-screening. Our model demonstrates promising results in detecting COVID-19 in real time. This will make the COVID test more accessible and cost-effective and reduce the spread of COVID-19 by alerting patients, who will be able to self-isolate and help the public health authorities curb the spread.

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License