Incremental Hessian Locally Linear Embedding algorithm

In this paper we propose an incremental version of Hessian locally linear embedding (HLLE) on the basis of incremental locally linear embedding (LLE) generalizations. The main idea behind our algorithm is to produce a lower dimension representation of a high-dimensional manifold such that the signif...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2007 9th International Symposium on Signal Processing and Its Applications : Sharjah, United Arab Emirates, 12-15 February 2007 S. 1 - 4
Hauptverfasser: Abdel-Mannan, O., Ben Hamza, A., Youssef, A.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.02.2007
Schlagworte:
Data engineering
Data mining
Data structures
Data visualization
Eigenvalues and eigenfunctions
Information systems
Laplace equations
Manifolds
Pattern recognition
Systems engineering and theory
ISBN:9781424407781, 1424407788
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper we propose an incremental version of Hessian locally linear embedding (HLLE) on the basis of incremental locally linear embedding (LLE) generalizations. The main idea behind our algorithm is to produce a lower dimension representation of a high-dimensional manifold such that the significant characteristics of the dataset are preserved while adapting to newly added points arriving to the dataset. Our experimental results verify how the new projection of points, along with the additional points, produces a good fit to the original manifold.
ISBN:9781424407781
1424407788
DOI:10.1109/ISSPA.2007.4555395