A Data Mining Approach for Precise Diagnosis of Dengue Fever

Dengue is a eviscerate disease common in tropical countries. It is also known as break-bone fever. Dataset for dengue gives information about the patient suffering with the dengue disease. The Dataset consist of attribute like fever, bleeding, metallic taste, Fatigue. The main objective of this study is to calculate the performance of various classification Techniques and compare their performance. The classification techniques used in this study are REP Tree, J48, SMO, ZeroR and Random Tree. The performance of classification techniques were compared by plotting graphs and table. Weka the data mining tool is used for the classification. Keywords— Data mining, Dataset, Classification, break bone fever, Weka. A Data mining Approach for Precise Diagnosis of Dengue Fever 353 II. METHODOLOGY Weka (Waikato Environment for Knowledge Analysis) is a data mining tool written in java developed at Waikato. WEKA is a very good data mining tool for the users to classify the accuracy on the basis of datasets by applying different algorithmic approaches and compared in the field of bioinformatics [6].It is also well-suited for developing new machine learning schemes. Our main objective is to identify that whether the patient is affected by Dengue or not. Some of the parameter are used for predicting the fever and compare the performance of the various classification techniques. The Various result obtained from the dataset using Weka tool are given below. Figure-1 Weka. Figure-2.SMO classifier. Figure-3: REP Tree classifier. Figure-4.Random Tree classifier. Figure-5 J48 classifier. Figure-6 ZeroR classifier. M.Bhavani and S.Vinod kumar 354 The main objective of this study is dengue disease prediction using data mining tool. The main task carried out in this study are: 1. Various Data mining classification techniques are used for the Prediction the dengue fever. 2. Comparing different classification techniques. 3. Finding best algorithm for the disease prediction. A. Classification It is the organization of data in given classes. Classification uses given class labels to order the objects in the data collection. Classification approaches normally use a training set where all objects are already associated with known class labels. The classification algorithm learns from the training set and builds a model. The model is used to classify new objects. Five techniques have been used in this study. They are REP Tree, RT, J48, ZeroR and SMO. Their performance was analyzed using some measures such as Accuracy, TP Rate, FP Rate, and ROC Area. B. Dataset Dataset is a collection of data. The dataset is contained in database table. The dataset is created in the CSV format. The dataset contains the attribute such as fever, bleeding, myalgia, flu, fatigue, pain, metallic taste. The symptoms are used as Attribute. The dataset loaded in the Weka tool in ARRF format and the performance of the classification techniques are identified and tabulated. Table -1 ATTRIBUTE DESCRIPTION Attribute possible values EPID any alpha-numeric values Fever Yes or No Bleeding Yes or No Myalgia Yes or No Flu Yes or No Pain Yes or No Joint/Muscle pain Yes or No Metallic Taste Yes or No Result Positive or Negative Fatigue Yes or No A Data mining Approach for Precise Diagnosis of Dengue Fever 355