Comparison of Classification Techniques on Dermatological Dataset

KEMAL, TUTUNCU and MURAT, KOKLU (2015) Comparison of Classification Techniques on Dermatological Dataset. In: Third International Conference on Advances in Bio-Informatics and Environmental Engineering - ICABEE 2015, 10-11 December, 2015, Rome, Italy.

[img]
Preview
Text
20151223_094034.pdf - Published Version

Download (592kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/7...

Abstract

Data mining is the process of analysing data and summarizing it into useful information. One of main problem in the field of data mining is classification. Having done in this study, Simple Logistic Regression, Bayes Net, Naïve Bayes, Radial Basis Function Network (RBF), Multilayer Perceptron (MLP), Naïve Bayes Tree (NB Tree), Sequential Minimal Optimization (SMO), J48, Random Tree and ZeroR classification methods were applied on dermatology data set by UCI Machine Learning Repository. When comparing the performances of algorithms it’s been found that Simple Logistic Regression and Bayes Net have highest accuracies whereas ZeroR had the worst accuracy. The results were also compared with previous studies in the literature. It has been seen that Simple Logistic Regression and Bayes Net had promising results when they compared with the methods used in literature.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: data mining, classification, j48, bayes net, smo, zeror
Depositing User: Mr. John Steve
Date Deposited: 04 Apr 2019 11:58
Last Modified: 04 Apr 2019 11:58
URI: http://publications.theired.org/id/eprint/1146

Actions (login required)

View Item View Item