Detection of Hepatitis Viruses Based on J48, KStar and Naïve Bayes Classifier

In this paper, the target is to detect hepatitis according to symptoms, mode of transmission and relevant tests. Hepatitis is not only the diseases of liver but also infect other sites of the body. It can attack people of any age. Many viruses cause hepatitis. From there mainly five viruses are mentioned as hepatitis viruses because they are mainly tainted in the liver. They are HAV, HBV, HCV, HDV, and HEV. The Naive Bayes, KStar and J48 classifiers are used in WEKA software to calculate the result. Naïve Bayes is the algorithm used for solving text classification problems. Basically, it is used for text classification that includes high dimensional training data sets. KStar is an instance-based learner. It conducts an entropy-based distance function. J48 classifier in weka is actually an algorithm generally known as C4.5 algorithm. This algorithm is often called a statistical classifier. In Naive Bayes the accuracy of result 93.8% stands for 10 fold cross-validation. In J48 classifier the accuracy is 98.6% by using 10 fold cross-validation and in KStar it is 97.2% by using 10 fold cross-validation.