A NEW ITJ METHOD WITH COMBINED SAMPLE SELECTION TECHNIQUE TO PREDICT THE DIABETES MELLITUS

N.Aswin Vignesh, Dr.D.I.George Amalarethinam

Abstract


The purpose of this study was to generate more concise rule extraction from the ITJ method. The proposed algorithm replacing the c4.5 program currently employed in ITJ method. The algorithms that can provide further insight are needed. Rule extraction can provide such explanations. The research was consequently operated to determine twelve rules with data sets having discrete and continuous aspect. The rule derivation method recommended for strengthen ITJ method to carry out deeply classification rules. The J48 scion decision tree algorithm is generated and used for classification. ITJ method is combined with sample selection technique which is used to substantially better accuracy and provided a considerably fewer average number of rules and antecedents. The proposed method is suitable for decision making medical accept including the diagnosis of all type of diabetes mellitus. The conventional input scooping approach for the forecast of diabetes uses single classifier method for anticipate the disease, which have documented approximately high rate of efficiency. Thus the theoretical hybrid classifier capability is recommended to predict diabetes through feature relevance analysis with high accuracy rate.

Keywords


Classification rule, Data scooping, selection technique, Antecedents.

Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v8i9.4914

Refbacks

  • There are currently no refbacks.




Copyright (c) 2017 International Journal of Advanced Research in Computer Science