ON FUZZY NEIGHBORHOOD BASED CLUSTERING ALGORITHM WITH LOW COMPLEXITY
IRANIAN JOURNAL OF FUZZY SYSTEMS, cilt.10, sa.3, ss.1-20, 2013 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 10 Sayı: 3
- Basım Tarihi: 2013
- Dergi Adı: IRANIAN JOURNAL OF FUZZY SYSTEMS
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Sayfa Sayıları: ss.1-20
- Anahtar Kelimeler: Clustering, Fuzzy neighborhood relation, Complexity, Modified FJP
- Dokuz Eylül Üniversitesi Adresli: Evet
Özet
The main purpose of this paper is to achieve improvement in the speed of Fuzzy Joint Points (FJP) algorithm. Since FJP approach is a basis for fuzzy neighborhood based clustering algorithms such as Noise-Robust FJP (NRFJP) and Fuzzy Neighborhood DBSCAN (FN-DBSCAN), improving FJP algorithm would an important achievement in terms of these FJP-based methods. Although FJP has many advantages such as robustness, auto detection of the optimal number of clusters by using cluster validity, independency from scale, etc., it is a little bit slow. In order to eliminate this disadvantage, by improving the FJP algorithm, we propose a novel Modified FJP algorithm, which theoretically runs approximately n/log(2) n times faster and which is less complex than the FJP algorithm. We evaluated the performance of the Modified FJP algorithm both analytically and experimentally.