On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)

Tony Bagnall; Michael Flynn; James Large; Matthew Middlehurst

doi:10.1007/978-3-030-65742-0_1

On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)

Tony Bagnall, Michael Flynn, James Large, Matthew Middlehurst

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

50 Citations (Scopus)

Abstract

The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. Since it was first proposed in 2016, the algorithm has undergone some minor changes and there is now a configurable, scalable and easy to use version available in two open source repositories. We present an overview of the latest stable HIVE-COTE, version 1.0, and describe how it differs to the original. We provide a walkthrough guide of how to use the classifier, and conduct extensive experimental evaluation of its predictive performance and resource usage. We compare the performance of HIVE-COTE to three recently proposed algorithms.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Subtitle of host publication	Advanced Analytics and Learning on Temporal Data (AALTD)
Editors	Vincent Lemaire, Simon Malinowski, Anthony Bagnall, Thomas Guyet, Romain Tavenard, Georgiana Ifrim
Publisher	Springer
Chapter	1
Pages	3-18
Number of pages	16
Volume	12588
ISBN (Electronic)	978-3-030-65742-0
ISBN (Print)	978-3-030-65741-3
DOIs	https://doi.org/10.1007/978-3-030-65742-0_1
Publication status	Published - 16 Dec 2020

Keywords

Classification
HIVE-COTE
Heterogeneous ensembles
Time series

Access to Document

10.1007/978-3-030-65742-0_1

Cite this

Bagnall, T., Flynn, M., Large, J., & Middlehurst, M. (2020). On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0). In V. Lemaire, S. Malinowski, A. Bagnall, T. Guyet, R. Tavenard, & G. Ifrim (Eds.), Lecture Notes in Computer Science: Advanced Analytics and Learning on Temporal Data (AALTD) (Vol. 12588, pp. 3-18). Springer. https://doi.org/10.1007/978-3-030-65742-0_1

Bagnall, Tony ; Flynn, Michael ; Large, James et al. / On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0). Lecture Notes in Computer Science: Advanced Analytics and Learning on Temporal Data (AALTD) . editor / Vincent Lemaire ; Simon Malinowski ; Anthony Bagnall ; Thomas Guyet ; Romain Tavenard ; Georgiana Ifrim. Vol. 12588 Springer, 2020. pp. 3-18

@inbook{33b57209446b4218b9bca5db9bcf6cb1,

title = "On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)",

abstract = "The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. Since it was first proposed in 2016, the algorithm has undergone some minor changes and there is now a configurable, scalable and easy to use version available in two open source repositories. We present an overview of the latest stable HIVE-COTE, version 1.0, and describe how it differs to the original. We provide a walkthrough guide of how to use the classifier, and conduct extensive experimental evaluation of its predictive performance and resource usage. We compare the performance of HIVE-COTE to three recently proposed algorithms.",

keywords = "Classification, HIVE-COTE, Heterogeneous ensembles, Time series",

author = "Tony Bagnall and Michael Flynn and James Large and Matthew Middlehurst",

year = "2020",

month = dec,

day = "16",

doi = "10.1007/978-3-030-65742-0_1",

language = "English",

isbn = "978-3-030-65741-3",

volume = "12588",

pages = "3--18",

editor = "Vincent Lemaire and Simon Malinowski and Anthony Bagnall and Thomas Guyet and Romain Tavenard and Georgiana Ifrim",

booktitle = "Lecture Notes in Computer Science",

publisher = "Springer",

address = "Germany",

}

Bagnall, T, Flynn, M, Large, J & Middlehurst, M 2020, On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0). in V Lemaire, S Malinowski, A Bagnall, T Guyet, R Tavenard & G Ifrim (eds), Lecture Notes in Computer Science: Advanced Analytics and Learning on Temporal Data (AALTD) . vol. 12588, Springer, pp. 3-18. https://doi.org/10.1007/978-3-030-65742-0_1

On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0). / Bagnall, Tony; Flynn, Michael; Large, James et al.
Lecture Notes in Computer Science: Advanced Analytics and Learning on Temporal Data (AALTD) . ed. / Vincent Lemaire; Simon Malinowski; Anthony Bagnall; Thomas Guyet; Romain Tavenard; Georgiana Ifrim. Vol. 12588 Springer, 2020. p. 3-18.

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)

AU - Bagnall, Tony

AU - Flynn, Michael

AU - Large, James

AU - Middlehurst, Matthew

PY - 2020/12/16

Y1 - 2020/12/16

N2 - The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. Since it was first proposed in 2016, the algorithm has undergone some minor changes and there is now a configurable, scalable and easy to use version available in two open source repositories. We present an overview of the latest stable HIVE-COTE, version 1.0, and describe how it differs to the original. We provide a walkthrough guide of how to use the classifier, and conduct extensive experimental evaluation of its predictive performance and resource usage. We compare the performance of HIVE-COTE to three recently proposed algorithms.

AB - The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. Since it was first proposed in 2016, the algorithm has undergone some minor changes and there is now a configurable, scalable and easy to use version available in two open source repositories. We present an overview of the latest stable HIVE-COTE, version 1.0, and describe how it differs to the original. We provide a walkthrough guide of how to use the classifier, and conduct extensive experimental evaluation of its predictive performance and resource usage. We compare the performance of HIVE-COTE to three recently proposed algorithms.

KW - Classification

KW - HIVE-COTE

KW - Heterogeneous ensembles

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=85094170718&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-65742-0_1

DO - 10.1007/978-3-030-65742-0_1

M3 - Chapter (peer-reviewed)

SN - 978-3-030-65741-3

VL - 12588

SP - 3

EP - 18

BT - Lecture Notes in Computer Science

A2 - Lemaire, Vincent

A2 - Malinowski, Simon

A2 - Bagnall, Anthony

A2 - Guyet, Thomas

A2 - Tavenard, Romain

A2 - Ifrim, Georgiana

PB - Springer

ER -

Bagnall T, Flynn M, Large J, Middlehurst M. On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0). In Lemaire V, Malinowski S, Bagnall A, Guyet T, Tavenard R, Ifrim G, editors, Lecture Notes in Computer Science: Advanced Analytics and Learning on Temporal Data (AALTD) . Vol. 12588. Springer. 2020. p. 3-18 doi: 10.1007/978-3-030-65742-0_1

On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)

Abstract

Keywords

Access to Document

Other files and links

Profiles

Tony Bagnall

Cite this