A Dynamic Linkage Clustering using KD-Tree

Shadi Abudalfa1 and Mohammad Mikki2
1The University Collage of Applied Sciences, Palestine
2The Islamic University of Gaza, Palestine

 
Abstract: Some clustering algorithms calculate connectivity of each data point to its cluster by depending on density reachability. These algorithms can find arbitrarily shaped clusters, but they require parameters that are mostly sensitive to clustering performance. We develop a new dynamic linkage clustering algorithm using kd-tree. The proposed algorithm does not require any parameters and does not have a worst-case bound on running time that exists in many similar algorithms in the literature. Experimental results are shown in this paper to demonstrate the effectiveness of the proposed algorithm. We compare the proposed algorithm with other famous similar algorithm that is shown in literature. We present the proposed algorithm and its performance in detail along with promising avenues of future research.

Keywords: Data clustering, density-based clustering Algorithm, KD-tree, dynamic linkage clustering, DBSCAN.

 

Received February 26, 2011; accepted July 28, 2011

  

Full Text