A Comparison of Decision Tree Algorithms For UCI Repository Classification

  ijett-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2013 by IJETT Journal
Volume-4 Issue-8                      
Year of Publication : 2013
Authors : Kittipol Wisaeng

MLA 

Kittipol Wisaeng. "A Comparison of Decision Tree Algorithms For UCI Repository Classification". International Journal of Engineering Trends and Technology (IJETT). V4(8):3393-3397 Jul 2013. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group.

Abstract

The development of decision tree algorithms have been used for industrial, commercial and scientific purpose. However, the choice of the most suitable algorithm becomes increasingly difficult. In this paper, we present the comparison of decision tree algorithms using Waikato environment for knowledge analysis. The aim is to investigate the performance of data classification for a set of a large data. The algorithms tested are functional tree algorithm , logistic model tre es algorithm, REP tree algorithm and best - first decision tree algorithm . The UCI repository will be used to test and justify the performance of decision tree algorithms. Subsequently, the classification algorithm that has the optimal potential will be suggested for use in large scale data.

References

[1] University of Waikato, New Zealand: WEKA version 3.6.10 (2013) Website: http://www.cs. Waikato.ac.nz/ml/ weka.html
[2] P . Bhargavi , and S . Jyoth , “ Soil Classification using data mining techniques: A comparative study ,” In ternational Journal of Engineering Trends and Technology , pp. 55 – 59 , July . 2011 .
[3] M.C. Storrie - Lombardi, A.A. Suchkov and E.L. Winter, “Morphological cla ssification of galaxies by artificial neural network” MNRAS, pp. 8 - 12, 1992.
[4] Y. Zhang, and Y. Zhao, “Automated clustering algorithm for classification of astronomical objects,” pp. 1113 - 1121, 2004.
[5] M. Qu, Y. Frank, and J. Jing, “Automated solar flare dete ction using MLP, RBF, and SVM,” Solar Physics, pp. 157 - 172, 2003.
[6] S.J. Williams, P.R. Wozniak, and W.T. Vestrand, “Identifying Red Variable in the Northern Sky Variability Survey” pp. 2965 - 2976, 2004. A CKNOWLEDGMENT This paper was supporte d by the Mahasakham Business School (MBS), Mahasahakham University, Thailand. We also would like to thank UCI repository for the data set used in this experiment.
[7] S.J. Williams, P.R. Wozniak, and W.T. Vestrand, “Identifying Red Variable in the Northern Sk y Variability Survey” pp. 2965 - 2976, 2004.
[8] Y. Wadadekar, “Estimating photometric redshifts using support vector machine,” pp.79 - 85, 2009.
[9] D.J. Newman, S. Hettich, C.L. Blake and C.J. Merz, UCI repository of machine leaning databases, University of Californ ia, Department of Computer Science, Website: http://www.ics.usi.edu
[10] R. Tina, and S.S. Sherekar, “Performance Analysis of Naïve Bayes and J48 Classification Algorithm for Data Classification,” pp. 256 - 261, April. 2013.
[11] Joao Gama , “Functional Tree,” Machine Learning, pp. 219 – 250, 2004 .
[12] N. Landwehr, M. Hall, and E. Frank , “Logistic Model Trees,” Machine Learning, pp. 161 - 205, 2005 .
[13] J. Park, T. Hsiao - Rong and C. - C.J. Kuo, “GA - Based Internet Traffic Classificaton Technique for QoS Provisioning,” pp. 251 - 254, 2006.
[14] J . Friedman, T . Hastie, and R . Tibshirani , “Additive logistic regression : A statistical view of boosting,” Annals of statistics, pp. 337 - 407, 2000 .

Keywords
Functional tree algorithm , logistic model trees algorithm , REP tree algorithm , best - first decision tree algorithm