AI-powered COVID-19 detection via cough sounds (available)

Starting Date: June 2024
Prerequisites: Having good knowledge of Python programming is essential. Having some basic knowledge of Machine Learning is beneficial (but not mandatory)
Will results be assigned to University: No

Respiratory diseases such as COVID-19 are known to physically damage our airway and lungs, which in turn alters the produced respiratory sounds (e.g., cough, breadth).

During the pandemic, cough classification has emerged as an accessible, low-cost, and environmentally friendly COVID-19 screening alternative, needing only a smartphone to collect and process cough samples. However, audio processing of recordings collected in such uncontrolled environments posed significant challenges for Machine Learning algorithms to classify.

This project will apply Machine Learning techniques on two large-scale >100 GB datasets of anonymised sounds from COVID-19 patients, to evaluate how well the models could identify COVID-19 infections from sound features.

Students are welcome to email ( for informal discussions.


  • Ashby, A.E., Meister, J.A., Nguyen, K.A., Luo, Z. and Gentzke, W., (2022). Cough-based COVID-19 detection with audio quality clustering and confidence measure based learning. In Conformal and Probabilistic Prediction with Applications (pp. 129-148). PMLR.
  • Meister, J.A., Nguyen, K.A. and Luo, Z., (2022). Audio feature ranking for sound-based COVID-19 patient detection. In EPIA Conference on Artificial Intelligence (pp. 146-158). Springer.