Rough Set -Algorithm for Clustering Categorical Data Using Mean Attribute (MMA) Dependency Based Measure

Anazida, Zainul and Muftah, Mohamed Baroud and Siti Mariyam, Shamsuddin and Siti Zaiton, Mohd Hashim (2019) Rough Set -Algorithm for Clustering Categorical Data Using Mean Attribute (MMA) Dependency Based Measure. In: 8th International Conference on Advances in Computing, Electronics and Communication - ACEC, 12 -13 January 2019, Kuala Lumpur, Malaysia.

[img]
Preview
Text
20190123_074223.pdf - Published Version

Download (663kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/1...

Abstract

Different cluster techniques based on the Rough Set Theory (RST) have been used for attribute selection and grouping objects displaying similar characteristics. On the other hand, a majority of these clustering techniques cannot tackle uncertainty. Furthermore, these processes are computationally complicated and less accurate. In this study, the researchers have explored the limitations of the two rough set theory based techniques, i.e., the Maximum Dependency Attribute (MDA) and the Maximum Indiscernible Attribute (MIA). They also proposed a novel approach for selecting the clustering attributes, i.e., the Maximum Mean Attribute (MMA). They compared the performances of the MMA, MDA and the MIA techniques, using the UCI dataset. Their results validated the performance of the MMA with regards to its accuracy and computational complexity.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: clustering, rough set theory, categorical data, dependency of attribute, performance.
Depositing User: Mr. John Steve
Date Deposited: 06 Mar 2019 07:44
Last Modified: 06 Mar 2019 07:45
URI: http://publications.theired.org/id/eprint/36

Actions (login required)

View Item View Item