Vector quantisation and topology based graph representation

Ágnes Vathy-Fogarassy, J. Abonyi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Compact graph based representation of complex data can be used for clustering and visualisation. In this chapter we introduce basic concepts of graph theory and present approaches which may generate graphs from data. Computational complexity of clustering and visualisation algorithms can be reduced replacing original objects with their representative elements (code vectors or fingerprints) by vector quantisation. We introduce widespread vector quantisation methods, the k -means and the neural gas algorithms. Topology representing networks obtained by the modification of neural gas algorithm create graphs useful for the low-dimensional visualisation of data set. In this chapter the basic algorithm of the topology representing networks and its variants (Dynamic Topology Representing Network and Weighted Incremental Neural Network) are presented in details.

Original languageEnglish
Title of host publicationSpringerBriefs in Computer Science
PublisherSpringer
Pages1-16
Number of pages16
Edition9781447151579
DOIs
Publication statusPublished - Jan 1 2013

Publication series

NameSpringerBriefs in Computer Science
Number9781447151579
ISSN (Print)2191-5768
ISSN (Electronic)2191-5776

Fingerprint

Vector quantization
Topology
Visualization
Graph theory
Gases
Computational complexity
Neural networks

Keywords

  • Cluster centre
  • Delaunay triangulation
  • Minimal span tree
  • Vector quantisation
  • Voronoi diagram

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Vathy-Fogarassy, Á., & Abonyi, J. (2013). Vector quantisation and topology based graph representation. In SpringerBriefs in Computer Science (9781447151579 ed., pp. 1-16). (SpringerBriefs in Computer Science; No. 9781447151579). Springer. https://doi.org/10.1007/978-1-4471-5158-6_1

Vector quantisation and topology based graph representation. / Vathy-Fogarassy, Ágnes; Abonyi, J.

SpringerBriefs in Computer Science. 9781447151579. ed. Springer, 2013. p. 1-16 (SpringerBriefs in Computer Science; No. 9781447151579).

Research output: Chapter in Book/Report/Conference proceedingChapter

Vathy-Fogarassy, Á & Abonyi, J 2013, Vector quantisation and topology based graph representation. in SpringerBriefs in Computer Science. 9781447151579 edn, SpringerBriefs in Computer Science, no. 9781447151579, Springer, pp. 1-16. https://doi.org/10.1007/978-1-4471-5158-6_1
Vathy-Fogarassy Á, Abonyi J. Vector quantisation and topology based graph representation. In SpringerBriefs in Computer Science. 9781447151579 ed. Springer. 2013. p. 1-16. (SpringerBriefs in Computer Science; 9781447151579). https://doi.org/10.1007/978-1-4471-5158-6_1
Vathy-Fogarassy, Ágnes ; Abonyi, J. / Vector quantisation and topology based graph representation. SpringerBriefs in Computer Science. 9781447151579. ed. Springer, 2013. pp. 1-16 (SpringerBriefs in Computer Science; 9781447151579).
@inbook{22e6feccbfdb435f9dfe4570920eaa3c,
title = "Vector quantisation and topology based graph representation",
abstract = "Compact graph based representation of complex data can be used for clustering and visualisation. In this chapter we introduce basic concepts of graph theory and present approaches which may generate graphs from data. Computational complexity of clustering and visualisation algorithms can be reduced replacing original objects with their representative elements (code vectors or fingerprints) by vector quantisation. We introduce widespread vector quantisation methods, the k -means and the neural gas algorithms. Topology representing networks obtained by the modification of neural gas algorithm create graphs useful for the low-dimensional visualisation of data set. In this chapter the basic algorithm of the topology representing networks and its variants (Dynamic Topology Representing Network and Weighted Incremental Neural Network) are presented in details.",
keywords = "Cluster centre, Delaunay triangulation, Minimal span tree, Vector quantisation, Voronoi diagram",
author = "{\'A}gnes Vathy-Fogarassy and J. Abonyi",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/978-1-4471-5158-6_1",
language = "English",
series = "SpringerBriefs in Computer Science",
publisher = "Springer",
number = "9781447151579",
pages = "1--16",
booktitle = "SpringerBriefs in Computer Science",
edition = "9781447151579",

}

TY - CHAP

T1 - Vector quantisation and topology based graph representation

AU - Vathy-Fogarassy, Ágnes

AU - Abonyi, J.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Compact graph based representation of complex data can be used for clustering and visualisation. In this chapter we introduce basic concepts of graph theory and present approaches which may generate graphs from data. Computational complexity of clustering and visualisation algorithms can be reduced replacing original objects with their representative elements (code vectors or fingerprints) by vector quantisation. We introduce widespread vector quantisation methods, the k -means and the neural gas algorithms. Topology representing networks obtained by the modification of neural gas algorithm create graphs useful for the low-dimensional visualisation of data set. In this chapter the basic algorithm of the topology representing networks and its variants (Dynamic Topology Representing Network and Weighted Incremental Neural Network) are presented in details.

AB - Compact graph based representation of complex data can be used for clustering and visualisation. In this chapter we introduce basic concepts of graph theory and present approaches which may generate graphs from data. Computational complexity of clustering and visualisation algorithms can be reduced replacing original objects with their representative elements (code vectors or fingerprints) by vector quantisation. We introduce widespread vector quantisation methods, the k -means and the neural gas algorithms. Topology representing networks obtained by the modification of neural gas algorithm create graphs useful for the low-dimensional visualisation of data set. In this chapter the basic algorithm of the topology representing networks and its variants (Dynamic Topology Representing Network and Weighted Incremental Neural Network) are presented in details.

KW - Cluster centre

KW - Delaunay triangulation

KW - Minimal span tree

KW - Vector quantisation

KW - Voronoi diagram

UR - http://www.scopus.com/inward/record.url?scp=85044988863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044988863&partnerID=8YFLogxK

U2 - 10.1007/978-1-4471-5158-6_1

DO - 10.1007/978-1-4471-5158-6_1

M3 - Chapter

T3 - SpringerBriefs in Computer Science

SP - 1

EP - 16

BT - SpringerBriefs in Computer Science

PB - Springer

ER -