MCOKE: Multi-Cluster Overlapping K-Means Extension Algorithm

Said Baadel, Fadi Thabtah, Zhongyu Lu

Research output: Contribution to journalArticle

Abstract

Clustering involves the partitioning of n objects into k clusters. Many clustering algorithms use hard-partitioning techniques where each object is assigned to one cluster. In this paper we propose an overlapping algorithm MCOKE which allows objects to belong to one or more clusters. The algorithm is different from fuzzy clustering techniques because objects that overlap are assigned a membership value of 1 (one) as opposed to a fuzzy membership degree. The algorithm is also different from other overlapping algorithms that require a similarity threshold be defined a priori which can be difficult to determine by novice users.
LanguageEnglish
Article number104
Pages427-430
Number of pages4
JournalInternational Journal of Computer, Electrical, Automation, Control and Information Engineering
Volume9
Issue number2
Publication statusPublished - 2015

Fingerprint

Fuzzy clustering
Clustering algorithms

Cite this

@article{791b82267dcf45f28d995b8527285dcb,
title = "MCOKE: Multi-Cluster Overlapping K-Means Extension Algorithm",
abstract = "Clustering involves the partitioning of n objects into k clusters. Many clustering algorithms use hard-partitioning techniques where each object is assigned to one cluster. In this paper we propose an overlapping algorithm MCOKE which allows objects to belong to one or more clusters. The algorithm is different from fuzzy clustering techniques because objects that overlap are assigned a membership value of 1 (one) as opposed to a fuzzy membership degree. The algorithm is also different from other overlapping algorithms that require a similarity threshold be defined a priori which can be difficult to determine by novice users.",
keywords = "data mining, k-means, MCOKE, over-lapping",
author = "Said Baadel and Fadi Thabtah and Zhongyu Lu",
year = "2015",
language = "English",
volume = "9",
pages = "427--430",
journal = "International Journal of Computer, Electrical, Automation, Control and Information Engineering",
number = "2",

}

MCOKE : Multi-Cluster Overlapping K-Means Extension Algorithm. / Baadel, Said; Thabtah, Fadi; Lu, Zhongyu.

In: International Journal of Computer, Electrical, Automation, Control and Information Engineering, Vol. 9, No. 2, 104, 2015, p. 427-430.

Research output: Contribution to journalArticle

TY - JOUR

T1 - MCOKE

T2 - International Journal of Computer, Electrical, Automation, Control and Information Engineering

AU - Baadel, Said

AU - Thabtah, Fadi

AU - Lu, Zhongyu

PY - 2015

Y1 - 2015

N2 - Clustering involves the partitioning of n objects into k clusters. Many clustering algorithms use hard-partitioning techniques where each object is assigned to one cluster. In this paper we propose an overlapping algorithm MCOKE which allows objects to belong to one or more clusters. The algorithm is different from fuzzy clustering techniques because objects that overlap are assigned a membership value of 1 (one) as opposed to a fuzzy membership degree. The algorithm is also different from other overlapping algorithms that require a similarity threshold be defined a priori which can be difficult to determine by novice users.

AB - Clustering involves the partitioning of n objects into k clusters. Many clustering algorithms use hard-partitioning techniques where each object is assigned to one cluster. In this paper we propose an overlapping algorithm MCOKE which allows objects to belong to one or more clusters. The algorithm is different from fuzzy clustering techniques because objects that overlap are assigned a membership value of 1 (one) as opposed to a fuzzy membership degree. The algorithm is also different from other overlapping algorithms that require a similarity threshold be defined a priori which can be difficult to determine by novice users.

KW - data mining

KW - k-means

KW - MCOKE

KW - over-lapping

UR - https://www.waset.org/Publications?p=98

M3 - Article

VL - 9

SP - 427

EP - 430

JO - International Journal of Computer, Electrical, Automation, Control and Information Engineering

JF - International Journal of Computer, Electrical, Automation, Control and Information Engineering

IS - 2

M1 - 104

ER -