An Efficient Data Partitioning Method Based Cell Partitioning Parallel Hierarchical Agglomerative Clustering 


Vol. 44,  No. 11, pp. 2167-2173, Nov.  2019
10.7840/kics.2019.44.11.2167


PDF
  Abstract

In today’s growth in CPU-based parallel and distributed computing fields, general-purpose graphics processing unit(GPGPU) has shown tremendous success in computing speeds. Data partitioning is a very important task in applications in the field of data mining with various domains. In addition, hierarchical agglomerative clustering is a useful method of identifying the number and pattern of clusters using the clustering hierarchy. The traditional hierarchical agglomerative clustering repeatedly searches for the closest cluster pair until all clusters belong to a single cluster. This task increases complexity of time and memory, to solve this problem, Shalom et al. described and implemented an efficient cell partitioning partially overlapping hierarchical agglomerative clustering. In this paper, we propose a cell partitioning parallel hierarchical agglomerative method by improving the cell partitioning partially overlapping hierarchical agglomerative clustering method proposed by Shalom et al. Experimental results show that the proposed method improves about 2~10 times than traditional hierarchical agglomerative clustering.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

B. Seo, "An Efficient Data Partitioning Method Based Cell Partitioning Parallel Hierarchical Agglomerative Clustering," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 11, pp. 2167-2173, 2019. DOI: 10.7840/kics.2019.44.11.2167.

[ACM Style]

Byung-suk Seo. 2019. An Efficient Data Partitioning Method Based Cell Partitioning Parallel Hierarchical Agglomerative Clustering. The Journal of Korean Institute of Communications and Information Sciences, 44, 11, (2019), 2167-2173. DOI: 10.7840/kics.2019.44.11.2167.

[KICS Style]

Byung-suk Seo, "An Efficient Data Partitioning Method Based Cell Partitioning Parallel Hierarchical Agglomerative Clustering," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 11, pp. 2167-2173, 11. 2019. (https://doi.org/10.7840/kics.2019.44.11.2167)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880