By Topic

Effects of different data characteristics on classifier's performance

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Mehmood, Y. ; Nat. Univ. of Comput. & Emerging Sci., Islamabad, Pakistan ; Khadam, S. ; Hameed, K. ; Riaz, F.
more authors

It is worthwhile to point out the fact that nature of given data plays considerable role in classifying the data accurately. To select an appropriate classifier for certain type of data, we are required to understand the behavior of classifiers on different data characteristics. The varying dimensions, number of instances, class labels, data correlation, and data distribution on different data classes, might characterize the data. In this study, the performance and behavior of five different supervised machine learning classification techniques have been investigated using six real life datasets that are taken form UCI Machine Learning repository along with artificially generated data. In the end, we have come up with some conclusions and findings which will be very supportive for upcoming researchers to develop a better understanding about data characteristics in combination with classifier's performance.

Published in:

Emerging Technologies (ICET), 2010 6th International Conference on

Date of Conference:

18-19 Oct. 2010