Open AccessEarly prediction of systemic lupus erythematosus using hybrid K-Means J48 decision tree algorithm
Author(s) -
S. Gomathi,
V. Narayani
Publication year - 2017
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i1.3.8982
Subject(s) - c4.5 algorithm , decision tree , naive bayes classifier , computer science , cluster analysis , algorithm , statistical classification , tree (set theory) , random forest , machine learning , decision tree learning , data mining , mathematics , support vector machine , mathematical analysis
The objective of the paper is to propose an enhanced algorithm for the prediction of chronic, autoimmune disease called Systemic Lupus Erythematosus (SLE). The Hybrid K-means J48 Decision Tree algorithm (HKMJDT) has been proposed for the effective and early prediction of the SLE. The reason for combining both the clustering and classification algorithms is to obtain the best accuracy and to predict the disease in the early stage. The performance of algorithms such as Naïve Bayes, decision tree, random forest, J48 and Hoeffding tree has been combined with K-means clustering algorithm and compared in an effort to find the best algorithm for diagnosing SLE disease. The results of the statistical evaluation with the comparative study show that the effectiveness of different classification techniques depends on the nature and intricacy of the dataset used. K-means combined with J48 algorithm shows the best accuracy rate of 82.14% on the pre-processed data. The work-flow has been proposed to show the execution of the algorithm.