Kümeleme Yöntemlerinde BCO, OCO, BOCO ve OBCO Algoritmalarının Karşılaştırılması
Kümeleme, nesneleri özelliklerine göre kümelere bölme işlemidir, böylece aynı veri kümesi benzerdir, farklı kümelerin verileri farklıdır. Bulanık kümeleme algoritmalarının temeli C- ortalamalar aileleridir ve en güçlü algoritma Bulanık C- ortalamalar (BCO) algoritmasıdır. Bu çalışmada; BCO, Olabilirlikli Bulanık C-ortalamalar (OBCO), Bulanık Olabilirlikli C-ortalamalar (BOCO) ve Olabilirlikli C- ortalamalar (OCO) algoritmaları, E.koli, şarap ve tohum veri setleri olarak ifade edilen birkaç gerçek veri setini farklı kümeler halinde sınıflandırmak için MATLAB programı vasıtasıyla kullanılmıştır. Ayrıca, OBCO, BOCO ve OCO ve BCO algoritmaları sonuçları sınıflandırma doğruluğuna, hata kareler ortalamasının karekökü (HKOK) ve ortalama mutlak hata (OMH) değerlerine göre karşılaştırılmıştır. Deney sonuçları, performans karşılaştırmada kullanılan kriterlere göre OBCO ve BOCO algoritmalarının BCO ve OCO algoritmalarından daha iyi performansa sahip olduğunu göstermektedir.
Comparison of FCM, PCM, FPCM and PFCM Algorithms in Clustering Methods
Clustering is a process of dividing the objects into subgroups so that the same set of data is similar, butthe data of different clusters is different. The basis of the fuzzy clustering algorithms is the C- Meansfamilies and the strongest algorithm is the Fuzzy C-means (FCM) algorithm. In this study; FCM,Possibilistic Fuzzy C-means (PFCM), Fuzzy Possibilistic C-means (FPCM) and Possibilistic C- means (PCM)algorithms are used to classify the several real data sets which are E.coli, wine and seed data sets intodifferent clusters by MATLAB program. Also, the results of PFCM, FPCM, PCM and FCM algorithms arecompared according to the classification accuracy, root mean squared error (RMSE) and mean absoluteerror (MAE). The results show that the PFCM and FPCM algorithms have better performance than FCMand PCM according to criteria for comparing the performances.
___
- Anderson, D. T., Zare, A. and Price, S., 2013. Comparing
fuzzy, probabilistic and possibilistic partitions using
the earth mover’s distance. IEEE Transactions on
Fuzzy Systems, 21, 766-775.
- Asuncion, A. and Newman, D. J., 2007. UCI Machine
Learning Repository. Irvine, CA: University of
California, School of Information and Computer
Science.
- Berry, M. W., 2004. Survey of Text Mining. SpringerVerlag,
New York, USA.
- Bezdek, J. C., 1981. Pattern Recognition with Fuzzy
Objective Function Algorithms. New York: Plenum.
- Bora, D. J. and Gupta, A. K., 2014. A comparative study
between fuzzy clustering algorithm and hard
clustering algorithm. International Journal of
Computer Trends and Technology, 10, 108-113.
- Cebeci, Z. and Yildiz, F., 2015. Comparison of k-means and
fuzzy c-means algorithms on different cluster
structures. Journal of Agricultural Informatics, 6, 13-
23.
- Cebeci, Z., Kavlak, A.T. and Yıldız, F., 2017. Validation of
fuzzy and possibilistic clustering results. International
Artificial Intelligence and Data Processing Symposium,
IEEE.
- Charytanowicz, M., Niewczas, J., Kulczycki, P., Kowalski,
P.A., Lukasik, S. and Zak, S., 2010. A complete gradient
clustering algorithm for features analysis of x-ray
images. Information Technologies in Biomedicine,
Springer-Verlag, Berlin-Heidelberg.
- Correa, C., Valero, C., Barreiro, P., Diago, M. P. and
Tardaguila, J., 2011. A comparison of fuzzy clustering
algorithms applied to feature extraction on vineyard.
International Conference in Advances in Artificial
Intelligence, 234-239.
- Ganbold, G. and Chasia, S., 2017. Comparison between
possibilistic c-means and artificial neural network
classification algorithms in land use/ land cover
classification. International Journal of Knowledge
Content Development and Technology, 7, 57-78.
- Jafar, M. O. A. and Sivakumar, R., 2012. A study on
possibilistic and fuzzy possibilistic c- means clustering
algorithms for data clustering. International
Conference on Emerging Trends in Science,
Engineering and technology, 90-95.
- Krishnapuram, R. and Keller, J., 1993. A possibilistic
approach to clustering. IEEE Transactions on Fuzzy
Systems, 1, 98-110.
- Nakai, K. and Kanehisa, M., 1991. Expert system for
predicting protein localization sites in gram-negative
bacteria. Proteins: Structure, Function, and Genetics,
11, 95-110.
- Nefti, S. and Oussalah, M., 2004. Probabilistic-fuzzy
clustering algorithm. IEEE international Conference
on Systems, Man and Cybernetics, 4786-4791.
- Ozdemir, O. and Kaya, A., 2018. Effect of parameter
selection on fuzzy clustering. Mehmet Akif Ersoy
Üniversitesi Uygulamalı Bilimler Dergisi, 2, 22-33.
- Ozdemir, O. and Kaya, A., 2018. K-medoids and fuzzy cmeans
algorithms for clustering CO2 emissions of Turkey and other OECD
countries. Applied Ecology
and Environmental Research, 16, 2513-2526.
- Pal, N. R., Pal, K. and Bezdek, J. C., 1997. A mixed c-means
clustering model. IEEE International Conference Fuzzy
Systems, 11 -21.
- Pal, N. R., Pal, K., Keller, J. M. and Bezdek, J. C., 2005. A
possibilistic fuzzy c-means clustering algorithm. IEEE
Transactions on Fuzzy Systems, 13, 517-530.
- Saad, M. F. and Alimi, A.M., 2012. Validity index and
number of cluster. International Journal of Computer
Science Issues, 9, 52-56.
- Saad, M. F. and Alimi, A.M., 2016. Selecting parameters
of the fuzzy possibilistic clustering algorithm.
Communications on Applied Electronics, 5, 42-52.
- Singhal, R. and Deepika, N., 2016. Classification of words:
using PFCM clustering. International Journal of
Computer Science and Mobile Computing, 5, 114-117.
- Şahinli, F., 1999. Kümeleme analizine fuzzy set teorisi
yaklaşımı. Yüksek Lisans Tezi, Gazi Üniversitesi Fen
Bilimleri Enstitüsü, Ankara, 119.
- Şanlı, K. and Apaydın, A., 2006. Robust kümeleme
yöntemleri. Anadolu Üniversitesi Bilim ve Teknoloji
Dergisi, 7, 33-39.
- Timm, H, Borgelt, C., Doring, C. and Kruse, R., 2004. An
extension to possibilistic fuzzy cluster analysis. Fuzzy
Sets and Systems, 147, 3-16.
- Zadeh, L., 1965. Fuzzy sets. Information and Control, 8,
338-353.
- https://archive.ics.uci.edu/ml/index.php (07.03.2019)