CLASSIFICATION OF SUB-LEVELS IN TURKEY WITH GUSTAFSON-KESSEL METHOD
Abstract
The European Union paved the way for countries to be divided into sub-units and in a sense paved the way for the further elaboration of statistical calculations. Level-1 or Level-2 classifications, which are created not only by the cities but also with neighboring cities, are of great importance in the development calculations of countries. Fuzzy Clustering approach comes out as a suitable method if the clusters are not separated from each other prominently or if some of the members are indecisive about being a member of the cluster. Fuzzy clusters are functions that determine each unit between 0 and 1 defined as the membership of the unit. Units which are very similar take part in the same cluster according to high membership degree. The purpose here is to determine homogenous city groups that have the same characteristics in terms of these indicators. In this study, one of the well known fuzzy clustering methods Gustafson-Kessel is used for classification SCTU Level-2 regions through development indicators. The results obtained from the Level-2 classifications were also used to rank the regions according to their importance. Thus, priority regions can be determined in investments.
Keywords
Kaynakça
- BABAK, R. (2010), “A Cluster Validity İndex for Fuzzy Clustering”, Fuzzy Sets and Systems, 161, 3014–3025.
- BALASKO, B., ABONYI, J. and FEIL, B. (2005), “Fuzzy Clustering and Data Analysis Toolbox”, Univ. of Veszprem, Hungary.
- BEZDEK, J.C. and DUNN, J.C. (1975), “Optimal Fuzzy Partitions: A Heuristic for Estimating the Parameters in a Mixture of Normal Distributions”, IEEE Transactions on Computers, pages 835–838.
- DANİEL, G. and WİTOLD, P. (2007), “Fuzzy C-Means, Gustafson-Kessel FCM, and Kernel-Based FCM: A Comparative Study”, Anal. and Des. of Intel. Sys. using SC Tech., ASC 41, pp. 140–149.
- ERILLI, N.A. (2014), “Bulanık Kümeleme Analizi İle İstatistiki Bölge Birimlerinin (IBBS) Mali Değişkenlere Göre Sınıflandırılması”, Kırıkkale Üniversitesi, Sosyal Bilimler Dergisi, Cilt:4, Sayı:2.
- ERILLI, N.A. (2015), “Socioeconomic Development İndex Ranking Calculations of Cities with Fuzzy Clustering Method: Case of Turkey”, Theoretical and Applied Economics, Volume XXII, No. 1(602), pp. 233-244.
- ERILLI, N.A., YOLCU, U., EĞRIOĞLU, E., ALADAĞ, Ç.H. and ÖNER, Y. (2011), “Determining the Most Proper Number of Cluster in Fuzzy Clustering by Artificial Neural Networks”, Expert Systems with Applications, 38, pp. 2248-2252.
- GATH, I. and GEVA, A.B. (1989), “Unsupervised Optimal Fuzzy Clustering”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 7:773–781.
Ayrıntılar
Birincil Dil
İngilizce
Konular
-
Bölüm
Araştırma Makalesi
Yayımlanma Tarihi
30 Kasım 2019
Gönderilme Tarihi
6 Eylül 2019
Kabul Tarihi
1 Kasım 2019
Yayımlandığı Sayı
Yıl 1970 Cilt: 20 Sayı: 2