ACADSTAFF UGM

CREATION
Title : ACCELERATING THE OUTLIER DETECTION METHODS FOR CATEGORICAL DATA BY USING MATRIX OF ATTRIBUTE VALUE FREQUENCY
Author :

Dr. Nur Rokhman, S.Si., M.Kom. (1) Prof. Drs. Subanar, Ph.D. (2) Drs. Edi Winarko, M.Sc.,Ph.D. (3)
Date : 0 2017
Keyword : Categorical Data Entropy Outlier Detection Weighting Function Categorical Data Entropy Outlier Detection Weighting Function
Abstract : Based on the data, outlier detection methods can be classified into three classes. Those are the methods which work on numerical data, work on categorical data, and work on mixed type data. Most of the outlier detection method works on numerical data. Only few method works on categorical data or work on mixed type data. In this paper, a new method for detecting outlier in categorical data called Weighted Matrix Entropy Value Frequency (WMEVF) has been proposed. This method uses weighting function to improve the precision and uses a matrix of attribute value frequency to reduce the complexity. There are four weighting functions used in the experiments namely: range, variations, deviation standard, and square function. The performance of WMEVF is observed based on the detected outlier of UCI Machine Learning datasets and the time needed to detect the outlier. The experiments show the fact that square function improved the precision and the matrix of attribute value frequency reduced the complexcity from O(m*n²) to O(m*n). [ABSTRACT FROM AUTHOR] Copyright of Journal of Theoretical & Applied Information Technology is the property of Journal of Theoretical & Applied Information Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Group of Knowledge : Ilmu Komputer
Original Language : English
Level : Internasional
Status :
Published
Document
No Title Document Type Action
1 ACCELERATING THE OUTLIER DETECTION METHODS FOR CATEGORICAL DATA BY USING MATRIX OF ATTRIBUTE VALUE FREQUENCY.pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
2 Accelerating the outlier detection methods for cat data by using matrix of attri value frequency-turnitin.pdf
Document Type : [PAK] Cek Similarity
[PAK] Cek Similarity View