Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure

Fatma-Ezzahra  Gmati; Salem Chakhar; Wided Lejouad Chaari; Mark Xu

doi:10.23919/ICAC50006.2021.9594127

Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure

Fatma-Ezzahra Gmati, Salem Chakhar, Wided Lejouad Chaari, Mark Xu

University of Manouba

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

90 Downloads (Pure)

Abstract

This paper proposes a Time Series Shape (TSS) based framework for time series representation and abstraction. The paper also introduces a Dynamic Time Shape Wrapping (DTSW), which is a shape extension of the well-known Dynamic Time Wrapping (DTW) dissimilarity measure. By jointly supporting representation and abstraction, TSS and its related dissimilarity measure DTSW can be applied in hybrid time series data mining tasks, especially those involving both rule induction and classification. The paper also compares the capabilities of TSS and Piecewise Linear Approximation (PAA) representation in a classification task. Results show that TSS has the same dimensionality reduction power as PAA. This means that TSS is able to maintain the same classification accuracy as PAA, with an additional time series abstraction capability. The results also indicate that DTSW is able to successfully quantify the comparison between TSS abstractions.

Original language	English
Title of host publication	System Intelligence through Automation & Computing
Subtitle of host publication	2021 26th International Conference on Automation and Computing (ICAC)
Editors	Chenguang Yang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-8
Number of pages	8
ISBN (Electronic)	9781860435577
ISBN (Print)	9781665443524
DOIs	https://doi.org/10.23919/ICAC50006.2021.9594127
Publication status	Published - 15 Nov 2021
Event	26th IEEE International Conference on Automation and Computing (ICAC'21) - Portsmouth, United Kingdom Duration: 2 Sept 2021 → 4 Sept 2021

Conference

Conference	26th IEEE International Conference on Automation and Computing (ICAC'21)
Country/Territory	United Kingdom
City	Portsmouth
Period	2/09/21 → 4/09/21

Keywords

Time Series Representation
Time Series Abstraction
dissimilarity measure
Dynamic Time Shape Wrapping

Access to Document

10.23919/ICAC50006.2021.9594127

Shape_based_Representation_and_Abstraction_of_Time_Series_Data_along_with_a_Dynamic_Time_Shape_Wrapping_as_a_Dissimilarity_Measure(3)
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 506 KB

Cite this

Gmati, F.-E., Chakhar, S., Lejouad Chaari, W., & Xu, M. (2021). Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure. In C. Yang (Ed.), System Intelligence through Automation & Computing: 2021 26th International Conference on Automation and Computing (ICAC) (pp. 1-8). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ICAC50006.2021.9594127

Gmati, Fatma-Ezzahra ; Chakhar, Salem ; Lejouad Chaari, Wided et al. / Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure. System Intelligence through Automation & Computing: 2021 26th International Conference on Automation and Computing (ICAC). editor / Chenguang Yang. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 1-8

@inproceedings{11c3c7a04aea45e59717a51bf453208d,

title = "Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure",

abstract = "This paper proposes a Time Series Shape (TSS) based framework for time series representation and abstraction. The paper also introduces a Dynamic Time Shape Wrapping (DTSW), which is a shape extension of the well-known Dynamic Time Wrapping (DTW) dissimilarity measure. By jointly supporting representation and abstraction, TSS and its related dissimilarity measure DTSW can be applied in hybrid time series data mining tasks, especially those involving both rule induction and classification. The paper also compares the capabilities of TSS and Piecewise Linear Approximation (PAA) representation in a classification task. Results show that TSS has the same dimensionality reduction power as PAA. This means that TSS is able to maintain the same classification accuracy as PAA, with an additional time series abstraction capability. The results also indicate that DTSW is able to successfully quantify the comparison between TSS abstractions.",

keywords = "Time Series Representation, Time Series Abstraction, dissimilarity measure, Dynamic Time Shape Wrapping",

author = "Fatma-Ezzahra Gmati and Salem Chakhar and {Lejouad Chaari}, Wided and Mark Xu",

year = "2021",

month = nov,

day = "15",

doi = "10.23919/ICAC50006.2021.9594127",

language = "English",

isbn = "9781665443524",

pages = "1--8",

editor = "Chenguang Yang",

booktitle = "System Intelligence through Automation & Computing",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "26th IEEE International Conference on Automation and Computing (ICAC'21) ; Conference date: 02-09-2021 Through 04-09-2021",

}

Gmati, F-E, Chakhar, S, Lejouad Chaari, W & Xu, M 2021, Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure. in C Yang (ed.), System Intelligence through Automation & Computing: 2021 26th International Conference on Automation and Computing (ICAC). Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 26th IEEE International Conference on Automation and Computing (ICAC'21), Portsmouth, United Kingdom, 2/09/21. https://doi.org/10.23919/ICAC50006.2021.9594127

Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure. / Gmati, Fatma-Ezzahra ; Chakhar, Salem; Lejouad Chaari, Wided et al.
System Intelligence through Automation & Computing: 2021 26th International Conference on Automation and Computing (ICAC). ed. / Chenguang Yang. Institute of Electrical and Electronics Engineers Inc., 2021. p. 1-8.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure

AU - Gmati, Fatma-Ezzahra

AU - Chakhar, Salem

AU - Lejouad Chaari, Wided

AU - Xu, Mark

PY - 2021/11/15

Y1 - 2021/11/15

N2 - This paper proposes a Time Series Shape (TSS) based framework for time series representation and abstraction. The paper also introduces a Dynamic Time Shape Wrapping (DTSW), which is a shape extension of the well-known Dynamic Time Wrapping (DTW) dissimilarity measure. By jointly supporting representation and abstraction, TSS and its related dissimilarity measure DTSW can be applied in hybrid time series data mining tasks, especially those involving both rule induction and classification. The paper also compares the capabilities of TSS and Piecewise Linear Approximation (PAA) representation in a classification task. Results show that TSS has the same dimensionality reduction power as PAA. This means that TSS is able to maintain the same classification accuracy as PAA, with an additional time series abstraction capability. The results also indicate that DTSW is able to successfully quantify the comparison between TSS abstractions.

AB - This paper proposes a Time Series Shape (TSS) based framework for time series representation and abstraction. The paper also introduces a Dynamic Time Shape Wrapping (DTSW), which is a shape extension of the well-known Dynamic Time Wrapping (DTW) dissimilarity measure. By jointly supporting representation and abstraction, TSS and its related dissimilarity measure DTSW can be applied in hybrid time series data mining tasks, especially those involving both rule induction and classification. The paper also compares the capabilities of TSS and Piecewise Linear Approximation (PAA) representation in a classification task. Results show that TSS has the same dimensionality reduction power as PAA. This means that TSS is able to maintain the same classification accuracy as PAA, with an additional time series abstraction capability. The results also indicate that DTSW is able to successfully quantify the comparison between TSS abstractions.

KW - Time Series Representation

KW - Time Series Abstraction

KW - dissimilarity measure

KW - Dynamic Time Shape Wrapping

U2 - 10.23919/ICAC50006.2021.9594127

DO - 10.23919/ICAC50006.2021.9594127

M3 - Conference contribution

SN - 9781665443524

SP - 1

EP - 8

BT - System Intelligence through Automation & Computing

A2 - Yang, Chenguang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE International Conference on Automation and Computing (ICAC'21)

Y2 - 2 September 2021 through 4 September 2021

ER -

Gmati FE, Chakhar S, Lejouad Chaari W, Xu M. Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure. In Yang C, editor, System Intelligence through Automation & Computing: 2021 26th International Conference on Automation and Computing (ICAC). Institute of Electrical and Electronics Engineers Inc. 2021. p. 1-8 doi: 10.23919/ICAC50006.2021.9594127

Shape-based representation and abstraction of Time Series Data along with a Dynamic Time Shape Wrapping as a dissimilarity measure

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this