Skip to main content

Local modes-based free-shape data partitioning

Angelov, Plamen, Gu, Xiaowei (2016) Local modes-based free-shape data partitioning. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI). . pp. 1-8. IEEE ISBN 978-1-5090-4241-8. (doi:10.1109/SSCI.2016.7850117) (KAR id:90135)

PDF Author's Accepted Manuscript
Language: English
Download (933kB) Preview
[thumbnail of Datacloud_localmode_v3.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
https://doi.org/10.1109/SSCI.2016.7850117

Abstract

In this paper, a new data partitioning algorithm, named “local modes-based data partitioning”, is proposed. This algorithm is entirely data-driven and free from any user input and prior assumptions. It automatically derives the modes of the empirically observed density of the data samples and results in forming parameter-free data clouds. The identified focal points resemble Voronoi tessellations. The proposed algorithm has two versions, namely, offline and evolving. The two versions are both able to work separately and start “from scratch”, they can also perform a hybrid. Numerical experiments demonstrate the validity of the proposed algorithm as a fully autonomous partitioning technique, and achieve better performance compared with alternative algorithms.

Item Type: Conference or workshop item (Paper)
DOI/Identification number: 10.1109/SSCI.2016.7850117
Uncontrolled keywords: Partitioning algorithms; Clustering algorithms; Chebyshev approximation; Machine learning algorithms; Filtering; Algorithm design and analysis; Standards; data partitioning; evolving clustering; parameterfree; data cloud; data- driven
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Amy Boaler
Date Deposited: 10 Sep 2021 12:07 UTC
Last Modified: 13 Sep 2021 10:27 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/90135 (The current URI for this page, for reference purposes)
  • Depositors only (login required):