Parkinson’s Disease Classification from Speech Data using multiple Machine Learning methods. This was implemented using scikit-learn Python package on a Jupyter Notebook.
In this project, multiple modern machine learning and pattern recognition methods have been used in order to classify or predict the risk of Parkinson’s disease based on speech signal data. The methods discussed in this project consist of a number of classification methods (i.e. Naïve Bayes, K-NN, Decision Trees, and Neural Networks), as well as some “Ensemble” learning techniques where we attempt to improve the accuracy by combining several models. The performance of the methods has been assessed with a reliable dataset from UCI repository. An ensemble method outperformed other individual models including more complex ones like neural networks.
- Jupyter Notebook
scikit-learn
library
- Add an adaptive implementation of maximum entropy thresholding
- Jupyter Notebook
scikit-learn
- Machine Learning library
[1] Scitech Europa. (2019, April 24th). A breakthrough for chronic Parkinson’s disease: patients have been given movement using electrical stimulation [Blog post]. Retrieved from https://www.scitecheuropa.eu/chronic-parkinsons-disease/94524/
**Parkinson's Disease Classification Data Set - **http://archive.ics.uci.edu/ml/datasets/Parkinson%27s+Disease+Classification
Sakar, C.O., Serbes, G., Gunduz, A., Tunc, H.C., Nizam, H., Sakar, B.E., Tutuncu, M., Aydin, T., Isenkul, M.E. and Apaydin, H., 2018. A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform. Applied Soft Computing, DOI: [Web Link]
- Imad Eddine Toubal - Initial work - imadtoubal
This project is licensed under the MIT License - see the LICENSE file for details
Happy coding!