Fuzzy clustering of time series using extremes

Pierpaolo D'Urso, Elizabeth Ann Maharaj, Andres Modesto Alonso

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this study we explore the grouping together of time series with similar seasonal patterns using extreme value analysis with fuzzy clustering. Input features into the fuzzy clustering methods are parameter estimates of time varying location, scale and shape obtained from fitting the generalised extreme value (GEV) distribution to annual maxima or the r-largest order statistics per year of the time series. An innovative contribution of the study is the development of new generalised fuzzy clustering procedures taking into account weights, and the derivation of iterative solutions based on the GEV parameter estimators. Simulation studies conducted to evaluate the methods, reveal good performance. An application is made to a set of daily sea-level time series from around the coast of Australia where the identified clusters are well validated and they can be meaningfully interpreted.
Original languageEnglish
Pages (from-to)56-79
Number of pages24
JournalFuzzy Sets and Systems
Volume318
DOIs
Publication statusPublished - Jul 2017

Keywords

  • Fuzzy c-means clustering
  • Fuzzy c-medoids clustering
  • Time series data
  • r-largest order statistics
  • Generalised extreme value distribution

Cite this

D'Urso, Pierpaolo ; Maharaj, Elizabeth Ann ; Alonso, Andres Modesto. / Fuzzy clustering of time series using extremes. In: Fuzzy Sets and Systems. 2017 ; Vol. 318. pp. 56-79.
@article{91bbb8e5f4f1431c9b2c42fb2e26707c,
title = "Fuzzy clustering of time series using extremes",
abstract = "In this study we explore the grouping together of time series with similar seasonal patterns using extreme value analysis with fuzzy clustering. Input features into the fuzzy clustering methods are parameter estimates of time varying location, scale and shape obtained from fitting the generalised extreme value (GEV) distribution to annual maxima or the r-largest order statistics per year of the time series. An innovative contribution of the study is the development of new generalised fuzzy clustering procedures taking into account weights, and the derivation of iterative solutions based on the GEV parameter estimators. Simulation studies conducted to evaluate the methods, reveal good performance. An application is made to a set of daily sea-level time series from around the coast of Australia where the identified clusters are well validated and they can be meaningfully interpreted.",
keywords = "Fuzzy c-means clustering, Fuzzy c-medoids clustering, Time series data, r-largest order statistics, Generalised extreme value distribution",
author = "Pierpaolo D'Urso and Maharaj, {Elizabeth Ann} and Alonso, {Andres Modesto}",
year = "2017",
month = "7",
doi = "10.1016/j.fss.2016.10.006",
language = "English",
volume = "318",
pages = "56--79",
journal = "Fuzzy Sets and Systems",
issn = "0165-0114",
publisher = "Elsevier",

}

Fuzzy clustering of time series using extremes. / D'Urso, Pierpaolo; Maharaj, Elizabeth Ann; Alonso, Andres Modesto.

In: Fuzzy Sets and Systems, Vol. 318, 07.2017, p. 56-79.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Fuzzy clustering of time series using extremes

AU - D'Urso, Pierpaolo

AU - Maharaj, Elizabeth Ann

AU - Alonso, Andres Modesto

PY - 2017/7

Y1 - 2017/7

N2 - In this study we explore the grouping together of time series with similar seasonal patterns using extreme value analysis with fuzzy clustering. Input features into the fuzzy clustering methods are parameter estimates of time varying location, scale and shape obtained from fitting the generalised extreme value (GEV) distribution to annual maxima or the r-largest order statistics per year of the time series. An innovative contribution of the study is the development of new generalised fuzzy clustering procedures taking into account weights, and the derivation of iterative solutions based on the GEV parameter estimators. Simulation studies conducted to evaluate the methods, reveal good performance. An application is made to a set of daily sea-level time series from around the coast of Australia where the identified clusters are well validated and they can be meaningfully interpreted.

AB - In this study we explore the grouping together of time series with similar seasonal patterns using extreme value analysis with fuzzy clustering. Input features into the fuzzy clustering methods are parameter estimates of time varying location, scale and shape obtained from fitting the generalised extreme value (GEV) distribution to annual maxima or the r-largest order statistics per year of the time series. An innovative contribution of the study is the development of new generalised fuzzy clustering procedures taking into account weights, and the derivation of iterative solutions based on the GEV parameter estimators. Simulation studies conducted to evaluate the methods, reveal good performance. An application is made to a set of daily sea-level time series from around the coast of Australia where the identified clusters are well validated and they can be meaningfully interpreted.

KW - Fuzzy c-means clustering

KW - Fuzzy c-medoids clustering

KW - Time series data

KW - r-largest order statistics

KW - Generalised extreme value distribution

U2 - 10.1016/j.fss.2016.10.006

DO - 10.1016/j.fss.2016.10.006

M3 - Article

VL - 318

SP - 56

EP - 79

JO - Fuzzy Sets and Systems

JF - Fuzzy Sets and Systems

SN - 0165-0114

ER -