Identifying and exploiting ultrametricity

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We begin with pervasive ultrametricity due to high dimensionality and/or spatial sparsity. How extent or degree of ultrametricity can be quantified leads us to the discussion of varied practical cases when ultrametricity can be partially or locally present in data. We show how the ultrametricity can be assessed in text or document collections, and in time series signals. In our presentation we also discussed applications to chemical information retrieval and to astrophysics, in particular observational cosmology.

LanguageEnglish
Title of host publicationAdvances in Data Analysis
Subtitle of host publicationProceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation
EditorsReinhold Decker, Hans-J Lenz
PublisherSpringer Verlag
Pages263-272
Number of pages10
ISBN (Electronic)9783540709817
ISBN (Print)9783540709800
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event30th Annual Conference of the German Classification Society on Advances in Data Analysis - Berlin, Germany
Duration: 8 Mar 200610 Mar 2006
Conference number: 30

Conference

Conference30th Annual Conference of the German Classification Society on Advances in Data Analysis
Abbreviated titleGfKl 2006
CountryGermany
CityBerlin
Period8/03/0610/03/06

Fingerprint

Cosmology
Astrophysics
Information retrieval
Sparsity
Information Retrieval
Dimensionality
Time series
Presentation
Text

Cite this

Murtagh, F. (2007). Identifying and exploiting ultrametricity. In R. Decker, & H-J. Lenz (Eds.), Advances in Data Analysis: Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation (pp. 263-272). Springer Verlag. https://doi.org/10.1007/978-3-540-70981-7_30
Murtagh, Fionn. / Identifying and exploiting ultrametricity. Advances in Data Analysis: Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation . editor / Reinhold Decker ; Hans-J Lenz. Springer Verlag, 2007. pp. 263-272
@inproceedings{efe5f6efdba646e983111d94b902b355,
title = "Identifying and exploiting ultrametricity",
abstract = "We begin with pervasive ultrametricity due to high dimensionality and/or spatial sparsity. How extent or degree of ultrametricity can be quantified leads us to the discussion of varied practical cases when ultrametricity can be partially or locally present in data. We show how the ultrametricity can be assessed in text or document collections, and in time series signals. In our presentation we also discussed applications to chemical information retrieval and to astrophysics, in particular observational cosmology.",
keywords = "analysis, Clustering, multivariate statistics, time series, Classification, data analysis, data mining, statistics",
author = "Fionn Murtagh",
year = "2007",
month = "12",
day = "1",
doi = "10.1007/978-3-540-70981-7_30",
language = "English",
isbn = "9783540709800",
pages = "263--272",
editor = "Reinhold Decker and Hans-J Lenz",
booktitle = "Advances in Data Analysis",
publisher = "Springer Verlag",

}

Murtagh, F 2007, Identifying and exploiting ultrametricity. in R Decker & H-J Lenz (eds), Advances in Data Analysis: Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation . Springer Verlag, pp. 263-272, 30th Annual Conference of the German Classification Society on Advances in Data Analysis, Berlin, Germany, 8/03/06. https://doi.org/10.1007/978-3-540-70981-7_30

Identifying and exploiting ultrametricity. / Murtagh, Fionn.

Advances in Data Analysis: Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation . ed. / Reinhold Decker; Hans-J Lenz. Springer Verlag, 2007. p. 263-272.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Identifying and exploiting ultrametricity

AU - Murtagh, Fionn

PY - 2007/12/1

Y1 - 2007/12/1

N2 - We begin with pervasive ultrametricity due to high dimensionality and/or spatial sparsity. How extent or degree of ultrametricity can be quantified leads us to the discussion of varied practical cases when ultrametricity can be partially or locally present in data. We show how the ultrametricity can be assessed in text or document collections, and in time series signals. In our presentation we also discussed applications to chemical information retrieval and to astrophysics, in particular observational cosmology.

AB - We begin with pervasive ultrametricity due to high dimensionality and/or spatial sparsity. How extent or degree of ultrametricity can be quantified leads us to the discussion of varied practical cases when ultrametricity can be partially or locally present in data. We show how the ultrametricity can be assessed in text or document collections, and in time series signals. In our presentation we also discussed applications to chemical information retrieval and to astrophysics, in particular observational cosmology.

KW - analysis

KW - Clustering

KW - multivariate statistics

KW - time series

KW - Classification

KW - data analysis

KW - data mining

KW - statistics

UR - http://www.scopus.com/inward/record.url?scp=84879581168&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-70981-7_30

DO - 10.1007/978-3-540-70981-7_30

M3 - Conference contribution

SN - 9783540709800

SP - 263

EP - 272

BT - Advances in Data Analysis

A2 - Decker, Reinhold

A2 - Lenz, Hans-J

PB - Springer Verlag

ER -

Murtagh F. Identifying and exploiting ultrametricity. In Decker R, Lenz H-J, editors, Advances in Data Analysis: Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation . Springer Verlag. 2007. p. 263-272 https://doi.org/10.1007/978-3-540-70981-7_30