SOCEN-CLUSTER: A new rapid clustering technique

Author

Baccari, Farouk ; Sayadi, Mounir

Author_Institution

ESSTT, Univ. of Tunis, Tunis, Tunisia

fYear

2013

fDate

21-23 March 2013

Firstpage

1

Lastpage

6

Abstract

In this paper, we present a novel clustering technique for unindexed, randomized, multidimensional, datasets. The main advantage of the proposed technique is the time and space complexity that were reduced to linear cardinality dependency. The algorithmic implementation shown in this paper uses some heuristics to enhance the overall execution time and space required making them fully scalable. This particularity makes it easier for ASICS / FPGA architects to implement such a technique in a constrained environment.

Keywords

computational complexity; pattern clustering; ASICS architect; FPGA architect; SOCEN-CLUSTER technique; field programmable gate array; linear cardinality dependency; rapid clustering technique; space complexity; time complexity; Classification algorithms; Clustering algorithms; Containers; Filtering; Merging; Noise; Time complexity; algorithmic hurisitcs; classification; clustering; herarchical clustering; incremental clustering; linear time complexity; scalable clustering technique;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering and Software Applications (ICEESA), 2013 International Conference on

Conference_Location

Hammamet

Print_ISBN

978-1-4673-6302-0

Type

conf

DOI

10.1109/ICEESA.2013.6578367

Filename

6578367