Comparative Study of Diabetic Patient Data’s Using Classification Algorithm in WEKA Tool

Abstract

Data mining refers to extracting knowledge from large amount of data. Real life data mining approaches are interesting because they often present a different set of problems for diabetic patient's data. The research area to solve various problems and classification is one of main problem in the field. The research describes algorithmic discussion of J48, J48 Graft, Random tree, REP, LAD. Here used to compare the performance of computing time, correctly classified instances, kappa statistics, MAE, RMSE, RAE, RRSE and to find the error rate measurement for different classifiers in weka .In this paper the data classification is diabetic patients data set is developed by collecting data from hospital repository consists of 1865 instances with different attributes. The instances in the dataset are two categories of blood tests, urine tests. Weka tool is used to classify the data is evaluated using 10 fold cross validation and the results are compared. When the performance of algorithms, we found J48 is better algorithm in most of the cases.

Various Data Mining Techniques for Diabetes Prognosis: A Review

“…Classification shows better accuracy when the k value is increased to a large value. P.Yasodha et al[5] The objective of this study is to evaluate and investigate FIVE selected classification algorithms based on WEKA. The best algorithm in WEKA is J48 classifier with an accuracy of 70.59%International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456-6470 They are used in various healthcare units all over the world.…”

Rule-Based Recommendation Model for Selecting Classifiers in Weka Based on User Specifications

“…There are different techniques used in hyperparameters optimization problems such as grid search [10], random search [11], evolutionary techniques [12], and Bayesian optimization [13], however, in this work does not consider the problem of hyperparameters optimization. The decision was to use the default hyperparameters during the training phase, this because the intention of this work is to build a recommendation model that selects a learning algorithm with minimizing the training time.…”

“…RandomTree does not prune the tree. RandomTree allows us to approximately estimate the class probability [12].…”