REPOSITORY APPLICATIONS
SEARCH OBJECTS
basic search
advanced search
search on lom fields
fulltext search
ADD OBJECTS
add an object
upload metadata file
BROWSE OBJECTS
by disciplines
by title of objects
by date of entry
by popularity (hits)
by editorial scores
on disciplines directory
on category map
OAI-PMH DATA PROVIDER
ABOUT TRAGLOR
About TrAgLor
Invitation
Project Team
Users Feedbacks
Communication
Site Map
TrAgLor Stats
Terms of Use
Signup to be member
HELP
how to add objects
review process
Plugins and Viewers
REPOSITORY GUIDE
select a language
|
Repository Login
|
Signup to be member
|
TrAgLor - Turkish Agricultural Learning Objects Repository
Object Details
Comparison of K-Means and Fuzzy C-Means Algorithms on Different Cluster Structures
view object
object summary
metadata(xml)
GENERAL
LIFE CYCLE
METAMETADATA
TECHNICAL
EDUCATIONAL
RIGHTS
RELATION
ANNOTATION
CLASSIFICATION
Identifier :
Catalog
: URI
Entry
: http://journal.magisz.org/index.php/jai/article/download/196/pdf_196
Title :
Comparison of K-Means and Fuzzy C-Means Algorithms on Different Cluster Structures
K-Ortalamalar ve Bulanık C-Ortalamalar Algoritmalarının Farklı Küme Yapıları İçin Karşılaştırılması
Language :
English
Descriptions :
In this paper the K-means (KM) and the Fuzzy C-means (FCM) algorithms were compared for their computing performance and clustering accuracy on different shaped cluster structures which are regularly and irregularly scattered in two dimensional space. While the accuracy of the KM with single pass was lower than those of the FCM, the KM with multiple starts showed nearly the same clustering accuracy with the FCM. Moreover the KM with multiple starts was extremely superior to the FCM in computing time in all datasets analyzed. Therefore, when well separated cluster structures spreading with regular patterns do exist in datasets the KM with multiple starts was recommended for cluster analysis because of its comparable accuracy and runtime performances.
Bu makalede K-Ortalamalar (KO) ve Bulanık C-Ortalamalar (BCO) algoritmalarının düzenli ve düzensiz olarak iki boyutlu uzayda dağılış gösteren farklı şekillerde küme yapılarında hesaplama performansı ve kümeleme geçerliliği açısından karşılaştırılması yapılmıştır. Tek geçişli KO'nun kümeleme geçerliliği BCO'dan daha düşük olmasına karşın çoklu geçişle KO'nun BCO'nunkiyle yaklaşık olarak aynı düzeyde bulunmuştur. Ayruca çok geçişli KO'nun analiz edilen tüm veri setlerinde BCO'dan çok fazla yüksek saptanmıştır. Bu nedenle, düzenli dağılış gösteren veri setlerinde BCO'ya göre kümeleme geçerliliği ve hesaplama performansı açısından çok geçişli KO'nun kullanılması önerilmiştir.
Keywords :
fuzzy c-means
k-means
soft clustering
hard clustering
bulanık c-ortalamalar
k-ortalamalar
yumuşak kümeleme
sert kümeleme
Coverage :
World
Structure :
Atomic
Aggregation Level :
Level 1
Version :
JAI, 2015
Status :
Final
Contribute :
Role :
Publisher
Date :
2015-10-12
name :
Journal of Agricultural Informatics
e-mail :
JAI-L@agr.unideb.hu
organization :
Hungarian Association of Agricultural Informatics
Identifier :
Catalog
: URI
Entry
: http://traglor.cu.edu.tr/common/object_xml.aspx?id=1948
Contribute :
Role :
Initiator
Date :
2015-10-15
name :
Zeynel Cebeci
e-mail :
cebeciz@gmail.com
organization :
Çukurova Üniversitesi Ziraat Fakültesi Biyometri ve Genetik Anabilim Dalı
Metadata Schema :
TrAgLor LOM AP
Language :
Turkish
Format :
Text
Requirements :
Operating System: Multios
Min ver :
Max ver :
Browser: Any
Min ver :
Max ver :
Installation Remarks :
Other Platform Requirements :
Duration :
Year :
0
Month :
0
Day :
0
Hour :
0
Minutes :
0
Size :
1363968 bytes
Location :
http://journal.magisz.org/index.php/jai/article/download/196/pdf_196
Interactivity Type :
Expositive
Learning Resource Type :
Research
Interactivity Level :
Low
Semantic Density :
High
Intended End User Role :
Other
Context :
University Postgraduate
Typical Age Range :
18Ü
Difficulty Level :
Difficult
Duration :
Year :
0
Month :
0
Day :
2
Hour :
0
Minutes :
0
Description :
Cost :
No
Copyright and Other Restrictions :
Yes
Description :
This resource is licensed under the license(CC-BY-NC-ND)
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported
Kind :
IsPartOf
Resource :
Catalog
: URI
Entry
: http://journal.magisz.org/index.php/jai/article/view/196
Description :
Journal of Agricultural Informatics (ISSN 2061-862X) 2015 Vol. 6, No. 3:13-23
Entity :
name :
e-mail :
organization :
Date :
Description :
Purpose :
Discipline
Source :
AGRICOLA
Entry :
Mathematics and Statistics
Description :
Keywords :
cluster analysis
data mining
Share in the Social Networks
QR Code