k-means Improvement by Dynamic Pre-aggregates

Nabil El malki, Franck Ravat, Olivier Teste

Abstract

The k-means algorithm is one well-known of clustering algorithms. k-means requires iterative and repetitive accesses to data up to performing the same calculations several times on the same data. However, intermediate results that are difficult to predict at the beginning of the k-means process are not recorded to avoid recalculating some data in subsequent iterations. These repeated calculations can be costly, especially when it comes to clustering massive data. In this article, we propose to extend the k-means algorithm by introducing pre-aggregates. These aggregates can then be reused to avoid redundant calculations during successive iterations. We show the interest of the approach by several experiments. These last ones show that the more the volume of data is important, the more the pre-aggregations speed up the algorithm.

Download


Paper Citation


in Harvard Style

El malki N., Ravat F. and Teste O. (2019). k-means Improvement by Dynamic Pre-aggregates.In Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-372-8, pages 133-140. DOI: 10.5220/0007675201330140


in Bibtex Style

@conference{iceis19,
author={Nabil El malki and Franck Ravat and Olivier Teste},
title={k-means Improvement by Dynamic Pre-aggregates},
booktitle={Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2019},
pages={133-140},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007675201330140},
isbn={978-989-758-372-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - k-means Improvement by Dynamic Pre-aggregates
SN - 978-989-758-372-8
AU - El malki N.
AU - Ravat F.
AU - Teste O.
PY - 2019
SP - 133
EP - 140
DO - 10.5220/0007675201330140