Comparison of classification techniques-SVM and naives bayes to predict the Arboviral disease-Dengue

In this paper we present the performance analysis of different data mining techniques to predict the Arboviral disease-Dengue. Data set used for the analysis is real time data taken from super specialty hospitals and diagnostic laboratories where the blood samples were collected for diagnostic investigations at study enrolment and again at hospital discharge. This data set consists of 5000 records with 29 parameters. In this paper we have investigated the data mining techniques: SVM and Naive Bayes Classifier. A proficient methodology - randomforest classifier with its associated Gini feature importance allows to identify small sets of parameters to be used for diagnostic purposes in clinical practice; this involves obtaining the smallest possible set of symptoms that can still achieve decent predictive performance for the dengue disease. We combine both the approaches, and evaluate the classifiers performance. The result of the comparison between the methods showed that SVM outperforms the Naïve Bayes in Dengue disease diagnosis.