Asian Journal of Research in Social Sciences and Humanities
Year : 2016, Volume : 6, Issue : 8
First page : ( 1026) Last page : ( 1038)
Online ISSN : 2249-7315.
Article DOI : 10.5958/2249-7315.2016.00668.7

Soft Computing based Classifier Models and Comparing its Predictive Ability through Statistical Validation

Dr. Parvathi B. Thanga*, Dr. Shalinie S. Mercy**

*Bannariamman Institute of Technology, Tamilnadu, India

**Thiagarajar College of Engineering, Madurai, Tamil Nadu, India

Online published on 2 August, 2016.

Abstract

This work aims to develop a systematic architecture and procedure of Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) for data mining classification model to predict the 11 data sets taken from UCI repository. The classification accuracy of ANN model is compared with the model errors of two different membership functions of ANFIS model. The results reveal that the performance of ANFIS model has the potential in classifying the numerical, categorical and mixed class value dataset. Further, the validation of the models has been made through statistical analysis to check the predictive ability of each model.

Top

Keywords

Data classification, ANN, ANFIS, Statistical validation.

Top