BIRCH: an efficient data clustering method for very large databases
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
OPTICS: ordering points to identify the clustering structure
SIGMOD '99 Proceedings of the 1999 ACM SIGMOD international conference on Management of data
A local search approximation algorithm for k-means clustering
Computational Geometry: Theory and Applications - Special issue on the 18th annual symposium on computational geometry—SoCG2002
Enabling real time data analysis
Proceedings of the VLDB Endowment
| Hi-index | 0.00 |
Building and maintaining a reliable, high performance network infrastructure requires the ability of accurately visualizing, rapidly navigating and effectively resolving performance impacting issues. With the growing number of network entities and services, exploratory monitoring of a large-scale telecommunication network is becoming increasingly difficult. This paper presents a density hierarchy clustering algorithm, designed for real-time visualization of large telecommunications networks. The density histogram is calculated, which replaces the original dataset in further processing. The elements (cells) of the density histogram are compared to their neighbors in order to assign them to density hierarchies, which in turn identify the clusters. The experimental results have shown that the proposed algorithm provides high accuracy in visualizing node clusters, while significantly outperforming k-means in terms of clustering speed. This makes the algorithm a practical exploratory monitoring solution.