Shallow machine learning techniques have been analysized and applied for a data-driven Parkinson's disease diagnosis from patient voice measurements. In particular, the mathematical aspects of the underlying methods have been presented and deeply discussed, together with a brief introduction of machine learning theory.
For all the details on the project see the full project report
Useful resources:
[1] Shai Shalev-Shwartz, Shai Ben-David, ‘Understanding Machine Learning: From Theory to Algorithms’, published by Cambridge University Press (2014).
[2] Max A. Little, Patrick E. McSharry, Eric J. Hunter, Lorraine O. Ramig (2008), 'Suitability of dysphonia measurements for telemonitoring of Parkinson's disease', IEEE Transactions on Biomedical Engineering
[3] 'Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection', Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. BioMedical Engineering OnLine 2007 (2007)
[4] UCI Parkinson's dataset used available at https://archive.ics.uci.edu/ml/datasets/Parkinsons