A similarity-guaranteed clustering algorithm and its search tree for handling an increased weight

Authors:
Kreadtisak Lappanitchayakul;Nualsawat Hiransakolwong
Affiliations:
Department of Mathematics and Computer Science, Faculty of Science, King Mongkut's Institute of Technology Ladkrabang, Thailand;Department of Mathematics and Computer Science, Faculty of Science, King Mongkut's Institute of Technology Ladkrabang, Thailand
Venue:
AIC'08 Proceedings of the 8th conference on Applied informatics and communications
Year:
2008

Citing 3
Cited 0

Chameleon: Hierarchical Clustering Using Dynamic Modeling

Computer
Algorithms for Mining Distance-Based Outliers in Large Datasets

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
WaveCluster: A Multi-Resolution Clustering Approach for Very Large Spatial Databases

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases

Quantified Score

Hi-index	0.00

Visualization

Abstract

A Clustering Tree, which is a kind of data structures, is not only used for clustering data but also a search tree for searching clusters number. Normally, it is constructed from a Minimum Spanning Tree (MST). In the case a connection line is later adjusted its weight: either increased or decreased weight. It is necessary to invoke the Clustering Tree constructing algorithm again. This situation affects the overall running time which can be greater. There was an algorithm for handling the decreased weight. In this paper, a new algorithm is presented. This new algorithm avoids reconstructing the Clustering Tree at each increased weight. Additionally, its running time is O(n) per weight adjustment where n is the number of nodes in the Clustering Tree.