Detecting Stress from Multivariate Time Series Data Using Topological Data Analysis

Tran, HV; McGregor, C; Kennedy, PJ

Detecting Stress from Multivariate Time Series Data Using Topological Data Analysis

Tran, HV McGregor, C

Kennedy, PJ

Permalink

Publisher:: SPRINGER-VERLAG SINGAPORE PTE LTD
Publication Type:: Chapter
Citation:: AI 2023: Advances in Artificial Intelligence, 2024, 14471 LNAI, pp. 341-353
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	Stress.pdf	Published version	899.29 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Tran, HV
dc.contributor.author	McGregor, C https://orcid.org/0000-0002-0491-4403
dc.contributor.author	Kennedy, PJ
dc.contributor.editor	Liu, T
dc.contributor.editor	Yue, L
dc.contributor.editor	Webb, G
dc.contributor.editor	Wang, D
dc.date.accessioned	2024-08-23T00:32:15Z
dc.date.available	2024-08-23T00:32:15Z
dc.date.issued	2024-01-01
dc.identifier.citation	AI 2023: Advances in Artificial Intelligence, 2024, 14471 LNAI, pp. 341-353
dc.identifier.isbn	978-981-99-8387-2
dc.identifier.uri	http://hdl.handle.net/10453/180541
dc.description.abstract	Stress can have dangerous effects to human mental and physical health. Statistics, machine learning and novel data analytics approaches have been used to detect stress from physiological time series data. However such data is noisy which can limit the effectiveness of algorithms. Topological Data Analysis (TDA) is a novel approach that can handle noisy data and may be promising for physiological time series data analysis. However, TDA is currently in the early stages of development, with researchers still grappling with the problem of feature extraction from TDA signatures for machine learning. Current state-of-the-art in TDA handles only small computer vision or univariate time series data analysis due to its computational expense. We present a TDA method for stress detection and validate it on the public Wearable Stress and Affect Detection (WESAD) dataset. We contribute a complete TDA method to classify long multivariate physiological time series data that overcomes some of the computational expensive and demonstrate its effectiveness compared to state of the art methods.
dc.language	en
dc.publisher	SPRINGER-VERLAG SINGAPORE PTE LTD
dc.relation.ispartof	AI 2023: Advances in Artificial Intelligence
dc.relation.ispartofseries	Lecture Notes in Artificial Intelligence
dc.relation.isbasedon	10.1007/978-981-99-8388-9_28
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	46 Information and computing sciences
dc.title	Detecting Stress from Multivariate Time Series Data Using Topological Data Analysis
dc.type	Chapter
utslib.citation.volume	14471 LNAI
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - CHT - Health Technologies
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2024-08-23T00:32:13Z
pubs.publication-status	Published
pubs.volume	14471 LNAI

Abstract:

Stress can have dangerous effects to human mental and physical health. Statistics, machine learning and novel data analytics approaches have been used to detect stress from physiological time series data. However such data is noisy which can limit the effectiveness of algorithms. Topological Data Analysis (TDA) is a novel approach that can handle noisy data and may be promising for physiological time series data analysis. However, TDA is currently in the early stages of development, with researchers still grappling with the problem of feature extraction from TDA signatures for machine learning. Current state-of-the-art in TDA handles only small computer vision or univariate time series data analysis due to its computational expense. We present a TDA method for stress detection and validate it on the public Wearable Stress and Affect Detection (WESAD) dataset. We contribute a complete TDA method to classify long multivariate physiological time series data that overcomes some of the computational expensive and demonstrate its effectiveness compared to state of the art methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/180541