Predication of Parkinson's disease using data mining methods: A comparative analysis of tree, statistical and support vector machine classifiers

作者: Geeta Yadav , Yugal Kumar , G. Sahoo

DOI: 10.1109/NCCCS.2012.6413034

关键词:

摘要: The prediction of Parkinson's disease in early age has been challenging task among researchers because the symptoms come into existence middle and late age. There is lot that leads to disease. But this paper focus on speech articulation difficulty PD affected people try formulate model behalf three data mining methods. These methods are taken from different domains i.e. tree classifier, statistical classifier support vector machine classifier. Performance these classifiers measured with performance matrices accuracy, sensitivity specificity. So, main tried find out which identified more accurately.

参考文章(70)
Fiona Thomson, Parkinson's Disease Neuron. ,vol. 39, pp. 889- 909 ,(2003) , 10.1016/S0896-6273(03)00568-3
Björn Falck, Steen Andreassen, Stig K. Andersen, Marianne Woldbye, MUNIN: a causal probabilistic network for interpretation of electromyographic findings international joint conference on artificial intelligence. pp. 366- 372 ,(1987)
James Parkinson, An essay on the shaking palsy. 1817 Journal of Neuropsychiatry and Clinical Neurosciences. ,vol. 14, pp. 223- ,(2002) , 10.1176/JNP.14.2.223
Robert Tibshirani, Trevor Hastie, Jerome H. Friedman, The Elements of Statistical Learning ,(2001)
Domenic V Cicchetti, Neural networks and diagnosis in the clinical laboratory: state of the art. Clinical Chemistry. ,vol. 38, pp. 9- 10 ,(1992) , 10.1093/CLINCHEM/38.1.9
Steven L. Salzberg, Alberto Segre, Programs for Machine Learning ,(1994)
Bernhard Schölkopf, Koji Tsuda, Jean-Philippe Vert, Kernel Methods in Computational Biology MIT Press. ,(2004)
A. Maghbouleh, A logistic regression model for detecting prominences international conference on spoken language processing. ,vol. 4, pp. 2443- 2445 ,(1996) , 10.1109/ICSLP.1996.607303
Thorsten Joachims, Text categorization with support vector machines Universität Dortmund. ,(1999) , 10.17877/DE290R-5097