Explainable attention ResNet18-based model for asthma detection using stethoscope lung sounds

Topaloglu, I; Barua, PD; Yildiz, AM; Keles, T; Dogan, S; Baygin, M; Gul, HF; Tuncer, T; Tan, RS; Acharya, UR

Explainable attention ResNet18-based model for asthma detection using stethoscope lung sounds

Topaloglu, I Barua, PD Yildiz, AM Keles, T Dogan, S Baygin, M Gul, HF Tuncer, T Tan, RS Acharya, UR

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Engineering Applications of Artificial Intelligence, 2023, 126, pp. 106887
Issue Date:: 2023-11-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0952197623010710-main.pdf	Published version	6.79 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	Topaloglu, I
dc.contributor.author	Barua, PD
dc.contributor.author	Yildiz, AM
dc.contributor.author	Keles, T
dc.contributor.author	Dogan, S
dc.contributor.author	Baygin, M
dc.contributor.author	Gul, HF
dc.contributor.author	Tuncer, T
dc.contributor.author	Tan, RS
dc.contributor.author	Acharya, UR
dc.date.accessioned	2024-04-23T03:03:46Z
dc.date.available	2024-04-23T03:03:46Z
dc.date.issued	2023-11-01
dc.identifier.citation	Engineering Applications of Artificial Intelligence, 2023, 126, pp. 106887
dc.identifier.issn	0952-1976
dc.identifier.uri	http://hdl.handle.net/10453/178268
dc.description.abstract	This study proposes an accurate asthma detection model using an attention network and machine learning technique. The objective of this study is the automated detection of asthma using an attention network. The lung sounds from 203 subjects involving 767 segments from asthma and 722 segments from healthy subjects were collected using a stethoscope. A novel Attention ResNet18-based deep feature engineering model has been developed in five phases: preprocessing, training the Attention ResNet18 network, extracting deep features, iterative feature selection, and classification using k-nearest neighbor (kNN) or support vector machine (SVM). Gradient-weighted class activation mapping (Grad-CAM) was used to generate heat maps, effectively distinguishing asthma lung sounds from those of normal individuals. By using Grad-CAM, explainable results have been presented. Our proposed model obtained an accuracy of 99.73% using SVM with 10-fold cross-validation, surpassing the performance obtained by previous models. Hence, the developed model has the potential to detect asthma in the real-world scenario. scenario to detect.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Engineering Applications of Artificial Intelligence
dc.relation.isbasedon	10.1016/j.engappai.2023.106887
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Explainable attention ResNet18-based model for asthma detection using stethoscope lung sounds
dc.type	Journal Article
utslib.citation.volume	126
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
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/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-04-23T03:03:44Z
pubs.publication-status	Published
pubs.volume	126

Abstract:

This study proposes an accurate asthma detection model using an attention network and machine learning technique. The objective of this study is the automated detection of asthma using an attention network. The lung sounds from 203 subjects involving 767 segments from asthma and 722 segments from healthy subjects were collected using a stethoscope. A novel Attention ResNet18-based deep feature engineering model has been developed in five phases: preprocessing, training the Attention ResNet18 network, extracting deep features, iterative feature selection, and classification using k-nearest neighbor (kNN) or support vector machine (SVM). Gradient-weighted class activation mapping (Grad-CAM) was used to generate heat maps, effectively distinguishing asthma lung sounds from those of normal individuals. By using Grad-CAM, explainable results have been presented. Our proposed model obtained an accuracy of 99.73% using SVM with 10-fold cross-validation, surpassing the performance obtained by previous models. Hence, the developed model has the potential to detect asthma in the real-world scenario. scenario to detect.

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

http://hdl.handle.net/10453/178268