@article{37134c349f414d6fb64a8f97e86a036a,
title = "Graph clustering-based discretization of splitting and merging methods (GraphS and GraphM)",
abstract = "Discretization plays a major role as a data preprocessing technique used in machine learning and data mining. Recent studies have focused on multivariate discretization that considers relations among attributes. The general goal of this method is to obtain the discrete data, which preserves most of the semantics exhibited by original continuous data. However, many techniques generate the final discrete data that may be less useful with natural groups of data not being maintained. This paper presents a novel graph clustering-based discretization algorithm that encodes different similarity measures into a graph representation of the examined data. The intuition allows more refined data-wise relations to be obtained and used with the effective graph clustering technique based on normalized association to discover nature graphs accurately. The goodness of this approach is empirically demonstrated over 30 standard datasets and 20 imbalanced datasets, compared with 11 well-known discretization algorithms using 4 classifiers. The results suggest the new approach is able to preserve the natural groups and usually achieve the efficiency in terms of classifier performance, and the desired number of intervals than the comparative methods.",
keywords = "Data mining, Graph clustering, Multivariate discretization, Normalized association, Normalized cuts",
author = "Kittakorn Sriwanna and Tossapon Boongoen and Natthakan Iam-On",
note = "Funding Information: KS is a lecturer at the School of Computer and Information Technology, Chiang Rai Rajabhat University (CRRU), Thailand, since 2009. He received the BEng degree in computer engineering (first class honors) from Naresuan University (NU) in 2008 and MEng degree in computer engineering from Kasetsart University (KU) in 2012. Currently, he is a Ph.D. candidate in computer engineering at Mae Fah Luang University (MFU). His primary research interests are in the area of machine learning, data mining, data preprocessing, and data reduction. TB is a Lecturer at the School of Information Technology, Mae Fah Luang University, Chiang Rai, Thailand. He obtained Ph.D. in Artificial Intelligence from Cranfield University in 2003, and worked as Post-Doctoral Research Associate (PDRA) at Aberystwyth University, during 2007-2010. His PDRA work focused on anti-terrorism using data analytical and decision support synthesizes. He has been the leader of research projects in exploiting biometrics technology for anti-terrorism in southern-provinces of Thailand, funded by Ministry of Defense. He also serves as a committee and reviewer of several venues, IEEE SMC, IEEE TKDE, Knowledge Based Systems, International Journal of Intelligent Systems Technologies and Applications, for instance. NI is an Assistant Professor at the School of Information Technology, Mae Fah Luang University. She received Ph.D. in Computer Science from Aberystwyth University in 2010, funded by Royal Thai Government. Her Ph.D. work won the Thesis Prize of 2012 by Thai National Research Council. Her present research of improving face classification for anti-terrorism and crime protection has been funded by Ministry of Science and Technology. She serves as an editor for International Journal of Data Analysis Techniques and Strategies; as a committee and reviewer of several venues, IEEE SMC, IEEE TKDE, Machine Learning, for instance. Publisher Copyright: {\textcopyright} 2017, The Author(s).",
year = "2017",
month = dec,
day = "1",
doi = "10.1186/s13673-017-0103-8",
language = "English",
volume = "7",
journal = "Human-centric Computing and Information Sciences",
issn = "2192-1962",
publisher = "Korea Information Processing Society",
number = "1",
}