A4 Conference proceedings

Outlier Robust Geodesic K-means Algorithm for High Dimensional Data


LUT Authors / Editors

Publication Details
Authors: Hassanzadeh Aidin, Kaarna Arto, Kauranne Tuomo
Publication year: 2016
Language: English
Related Journal or Series Information: Lecture Notes in Computer Science
Title of parent publication: Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop, S+SSPR 2016 Proceedings
Volume number: 10029
Start page: 252
End page: 262
ISBN: 978-3-319-49054-0
eISBN: 978-3-319-49055-7
ISSN: 0302-9743
JUFO-Level of this publication: 1
Open Access: Not an Open Access publication

Abstract
This paper proposes an outlier robust geodesic K-mean algorithm for high dimensional data. The proposed algorithm features three novel contributions. First, it employs a shared nearest neighbour (SNN) based distance metric to construct the nearest neighbour data model. Second, it combines the notion of geodesic distance to the well-known local outlier factor (LOF) model to distinguish outliers from inlier data. Third, it introduces a new ad-hoc strategy to integrate outlier scores into geodesic distances. Numerical experiments with synthetic and real world remote sensing spectral data show the efficiency of the proposed algorithm in clustering of high-dimensional data in terms of the overall clustering accuracy and the average precision.

Last updated on 2018-19-10 at 08:49