Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data

Dan Hudson; Travis Wiltshire; Martin Atzmueller

doi:10.1007/978-3-030-88942-5_34

Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data

Dan Hudson, Travis Wiltshire, Martin Atzmueller

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. As an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we discuss the results and showcase the presented novel analysis options. In addition, we outline possible implications of the results in terms of understanding teamwork.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on Discovery Science
Publisher	Springer Nature Switzerland AG
Pages	435-445
Number of pages	11
Volume	12986
ISBN (Electronic)	978-3-030-88942-5
ISBN (Print)	978-3-030-88941-8
DOIs	https://doi.org/10.1007/978-3-030-88942-5_34
Publication status	Published - 2021
Event	24th International Conference on Discovery Science - Halifax, Canada Duration: 11 Oct 2021 → 13 Oct 2021 https://ds2021.cs.dal.ca/

Conference

Conference	24th International Conference on Discovery Science
Country/Territory	Canada
City	Halifax
Period	11/10/21 → 13/10/21
Internet address	https://ds2021.cs.dal.ca/

Keywords

subgroup discovery
exceptional model mining
time series
teamwork
multimodal

Access to Document

10.1007/978-3-030-88942-5_34Licence: CC BY-ND

https://link.springer.com/chapter/10.1007/978-3-030-88942-5_34Licence: CC BY-ND

Cite this

@inproceedings{863bea3d3d7d453aaf832b5b43c78dca,

title = "Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data",

abstract = "In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. As an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we discuss the results and showcase the presented novel analysis options. In addition, we outline possible implications of the results in terms of understanding teamwork.",

keywords = "subgroup discovery, exceptional model mining, time series, teamwork, multimodal",

author = "Dan Hudson and Travis Wiltshire and Martin Atzmueller",

year = "2021",

doi = "10.1007/978-3-030-88942-5_34",

language = "English",

isbn = "978-3-030-88941-8",

volume = "12986",

pages = "435--445",

booktitle = "Proceedings of the 24th International Conference on Discovery Science",

publisher = "Springer Nature Switzerland AG",

address = "Switzerland",

note = "24th International Conference on Discovery Science ; Conference date: 11-10-2021 Through 13-10-2021",

url = "https://ds2021.cs.dal.ca/",

}

Hudson, D, Wiltshire, T & Atzmueller, M 2021, Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data. in Proceedings of the 24th International Conference on Discovery Science. vol. 12986, Springer Nature Switzerland AG, pp. 435-445, 24th International Conference on Discovery Science, Halifax, Canada, 11/10/21. https://doi.org/10.1007/978-3-030-88942-5_34

Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data. / Hudson, Dan; Wiltshire, Travis; Atzmueller, Martin.
Proceedings of the 24th International Conference on Discovery Science. Vol. 12986 Springer Nature Switzerland AG, 2021. p. 435-445.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Local Exceptionality Detection in Time Series using Subgroup Discovery

T2 - 24th International Conference on Discovery Science

AU - Hudson, Dan

AU - Wiltshire, Travis

AU - Atzmueller, Martin

PY - 2021

Y1 - 2021

N2 - In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. As an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we discuss the results and showcase the presented novel analysis options. In addition, we outline possible implications of the results in terms of understanding teamwork.

AB - In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. As an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we discuss the results and showcase the presented novel analysis options. In addition, we outline possible implications of the results in terms of understanding teamwork.

KW - subgroup discovery

KW - exceptional model mining

KW - time series

KW - teamwork

KW - multimodal

U2 - 10.1007/978-3-030-88942-5_34

DO - 10.1007/978-3-030-88942-5_34

M3 - Conference contribution

SN - 978-3-030-88941-8

VL - 12986

SP - 435

EP - 445

BT - Proceedings of the 24th International Conference on Discovery Science

PB - Springer Nature Switzerland AG

Y2 - 11 October 2021 through 13 October 2021

ER -

Local Exceptionality Detection in Time Series using Subgroup Discovery: An Approach Exemplified on Team Interaction Data

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this