EEG-based tonic cold pain recognition system using wavelet transform

Alazrai, R; Momani, M; Khudair, HA; Daoud, MI

EEG-based tonic cold pain recognition system using wavelet transform

Alazrai, R Momani, M Khudair, HA Daoud, MI

Permalink

Publisher:: Springer (part of Springer Nature)
Publication Type:: Journal Article
Citation:: Neural Computing and Applications, 2019, 31, (7), pp. 3187-3200
Issue Date:: 2019-07-01

Closed Access

	Filename	Description	Size
	Alazrai2019_Article_EEG-basedTonicColdPainRecognit.pdf	Published version	1.02 MB	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	Alazrai, R
dc.contributor.author	Momani, M
dc.contributor.author	Khudair, HA
dc.contributor.author	Daoud, MI
dc.date.accessioned	2020-05-20T23:45:17Z
dc.date.available	2020-05-20T23:45:17Z
dc.date.issued	2019-07-01
dc.identifier.citation	Neural Computing and Applications, 2019, 31, (7), pp. 3187-3200
dc.identifier.issn	0941-0643
dc.identifier.issn	1433-3058
dc.identifier.uri	http://hdl.handle.net/10453/140855
dc.description.abstract	© 2017, The Natural Computing Applications Forum. Developing an objective pain identification system can provide caregivers with a second opinion to improve the treatment of patients who are unable to verbally communicate their pain. In this study, we present a new EEG-based approach for pain recognition. The proposed approach is employed to identify four different states that a human can feel during tonic cold pain stimulation. These states are the relax state, relax-to-pain state (RPS), pain state (PS), and pain-to-relax state (PRS). A sliding window has been used to decompose the EEG signals into overlapping segments. Each EEG segment is analyzed using the discrete wavelet transform to construct a time–frequency representation of the EEG signals and extract a set of nonlinear features. These features are used to construct a two-layer hierarchical classification framework that can identify the aforementioned four pain states. The first layer identifies whether an EEG segment is relax or pain segment. In the second layer, the pain segments are classified into one of the three pain states (i.e., RPS, PS, and PRS). To evaluate the performance of the proposed approach, we recorded EEG data for 24 healthy subjects who were exposed to tonic cold pain stimulation. Three procedures were employed to evaluate the capability of the approach to detect the four states associated with tonic cold pain stimulation. The experimental results demonstrate the efficacy of our approach for accurate tonic cold pain identification. Moreover, these promising results suggest the feasibility of expanding the proposed approach to characterize clinical pain, such as cancer-related pain.
dc.language	en
dc.publisher	Springer (part of Springer Nature)
dc.relation.ispartof	Neural Computing and Applications
dc.relation.isbasedon	10.1007/s00521-017-3263-6
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 1702 Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	EEG-based tonic cold pain recognition system using wavelet transform
dc.type	Journal Article
utslib.citation.volume	31
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1702 Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true
dc.date.updated	2020-05-20T23:45:10Z
pubs.issue	7
pubs.publication-status	Published
pubs.volume	31
utslib.start-page	3187
utslib.citation.issue	7

Abstract:

© 2017, The Natural Computing Applications Forum. Developing an objective pain identification system can provide caregivers with a second opinion to improve the treatment of patients who are unable to verbally communicate their pain. In this study, we present a new EEG-based approach for pain recognition. The proposed approach is employed to identify four different states that a human can feel during tonic cold pain stimulation. These states are the relax state, relax-to-pain state (RPS), pain state (PS), and pain-to-relax state (PRS). A sliding window has been used to decompose the EEG signals into overlapping segments. Each EEG segment is analyzed using the discrete wavelet transform to construct a time–frequency representation of the EEG signals and extract a set of nonlinear features. These features are used to construct a two-layer hierarchical classification framework that can identify the aforementioned four pain states. The first layer identifies whether an EEG segment is relax or pain segment. In the second layer, the pain segments are classified into one of the three pain states (i.e., RPS, PS, and PRS). To evaluate the performance of the proposed approach, we recorded EEG data for 24 healthy subjects who were exposed to tonic cold pain stimulation. Three procedures were employed to evaluate the capability of the approach to detect the four states associated with tonic cold pain stimulation. The experimental results demonstrate the efficacy of our approach for accurate tonic cold pain identification. Moreover, these promising results suggest the feasibility of expanding the proposed approach to characterize clinical pain, such as cancer-related pain.

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

http://hdl.handle.net/10453/140855