Back to Search
Start Over
K-boyutlu ağaç ve uyarlanabilir yarıçap (KD-AR Stream) tabanlı gerçek zamanlı akan veri kümeleme.
- Source :
-
Journal of the Faculty of Engineering & Architecture of Gazi University / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, . 2020, Vol. 35 Issue 1, p337-354. 18p. - Publication Year :
- 2020
-
Abstract
- Data stream clustering is one of the most popular topics of today's world where the amount of data reaches incredible levels in parallel with technological developments. The most important problems encountered in data stream clustering approaches are the fact that most of the approaches consists of an online and offline phases, the definition of the number of cluster, or the need to set a limitation to this number, the problems encountered in determining optimum radius value, and the problems encountered in concept evolution. The present study proposes an evolutionary based solution method, which is based on Kd-Tree and adaptive radius (KD-AR Stream) to perform real-time clustering on the streaming data. The proposed approach has been compared with SE-Stream, DPStream and CEDAS algorithms in terms of both cluster quality and execution time. The results showed that KD-AR Stream algorithm has a good clustering performance within a reasonable time by comparison with the other algorithms. [ABSTRACT FROM AUTHOR]
- Subjects :
- *RIVERS
*ALGORITHMS
*DEFINITIONS
*RADIUS (Geometry)
*CONCEPTS
Subjects
Details
- Language :
- Turkish
- ISSN :
- 13001884
- Volume :
- 35
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Journal of the Faculty of Engineering & Architecture of Gazi University / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi,
- Publication Type :
- Academic Journal
- Accession number :
- 139597967
- Full Text :
- https://doi.org/10.17341/gazimmfd.467226