Parkinson’s Disease Data Classification Using Evolvable Wavelet Neural Networks
Parkinson’s Disease is the second most common neurological condition in Australia. This paper develops and compares a new type of Wavelet Neural Network that is evolved via Cartesian Genetic Programming for classifying Parkinson’s Disease data based on speech signals. The classifier is trained using 10-fold and leave-one-subject-out cross validation testing strategies. The results indicate that the proposed algorithm can find high quality solutions and the associated features without requiring a separate feature pruning pre-processing step. The technique aims to become part of a future support tool for specialists in the early diagnosis of the disease reducing misdiagnosis and cost of treatment.
KeywordsParkinson’s Disease Neuroevolution Wavelet neuralnetwork Cartesian genetic programming Artificial neural network
We acknowledge Max Little, from the University of Oxford, UK, who created the database in collaboration with the National Center for Voice and Speech, Denver, Colorado, USA, who recorded the speech signals.
- 1.Parkinson’s Australia, Living with Parkinson’s disease; Deloitte Access Economics Pty Ltd, update - October 2011. http://www.parkinsonsnsw.org.au/. Accessed August 2014
- 3.Khan, M.M., Chalup, S.K., Mendes, A.: Evolving wavelet neural networks for breast cancer classification. In: 12th Australasian Data Mining Conference, Brisbane, Australia, 27th-28th November 2014Google Scholar
- 4.Lichman, M.: UCI machine learning repositry. http://archive.ics.uci.edu/ml
- 5.UCI machine learning repositry - Parkinsons data set. http://archive.ics.uci.edu/ml/datasets/Parkinsons.html. Accessed May 2014
- 9.Caglar, M.F., Cetisli, B., Toprak, I.B.: Automatic recognition of Parkinson’s disease from sustained phonation tests using ann and adaptive neuro-fuzzy classifier. J. Eng. Sci. Des. 2, 59–64 (2010)Google Scholar
- 15.Spadoto, A.A., Guido, R.C., Carnevali, F.L., Pagnin, A.F., Falcao, A.X., Papa, J.P.: Improving parkinson’s disease identification through evolutionary-based feature selection. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pp. 7857–7860, August 2011Google Scholar
- 19.Miller, J.: What bloat? cartesian genetic programming on boolean problems. In: Genetic and Evolutionary computation Conference Late Breaking Papers, pp. 295–302. Morgan Kaufmann (2001)Google Scholar
- 23.Khan, M.M., Khan, G.M., Miller, J.F.: Efficient representation of recurrent neural networks for markovian/non-markovian non-linear control problems. In: International Conference on System Design and Applications (ISDA), pp. 615–620 (2010)Google Scholar
- 24.Walker, A., Miller, J.F.: Solving real-valued optimisation problems using cartesian genetic programming. In: Proceedings of the Genetic and Evolutionary Computation Conference GECCO, pp. 1724–1730. ACM Press (2007)Google Scholar