Performance of Classification Techniques on Parkinson's Disease
Nowadays, many methods and algorithms have been developed that may influence the decision-making process
and are used to extract meaningful information. One of the well know methods or approaches in information extraction is
data mining. Data mining tries to establish the best model to support decision system, to extract information and to
categorize, to summarize and etc. according to given data set. The Parkinson’s disease-related data obtained from UCI
Machine Learning Database is used to try several data mining techniques and methods to see the successes of techniques
regarding to diagnosis accuracy ratio to support the expert. So far, Parkinson’s disease can actually be diagnosed after
medical examinations. However, diagnosis with computer has been the subject of many researches due to demand to help
physician. In this study, a research is conducted using 16 different data mining techniques and methods to support the
doctors in the decision-making process. The results of the applied methods for the study regarding to diagnosis accuracy
ratesare as follows; IB1 (96.4103%), RotationForest (92.3077%) RandomForest (91.7949%), MultilayerPerceptron
(90.7692%), ClassificationViaRegression (88.2051%), Bagging (87.6923%), JRip (87.6923%) SMO (87.1795%), OneR
(86.1538%), NBTree (86.1538%), Dagging (85.6410%), DTNB (85.1282%), DecisionTable (81.0256%), J48 (80.5128%),
BayesNet (80.0000%) and Naïve Bayes (69.2308%).
Keywords- Data Mining, Classification, Parkinson Disease.