A new lateral geniculate nucleus pattern-based environmental sound classification using a new large sound dataset

Taşcı, B; Acharya, MR; Datta Barua, P; Metehan Yildiz, A; Veysel Gun, M; Keles, T; Dogan, S; Tuncer, T

A new lateral geniculate nucleus pattern-based environmental sound classification using a new large sound dataset

Taşcı, B Acharya, MR Datta Barua, P Metehan Yildiz, A Veysel Gun, M Keles, T Dogan, S Tuncer, T

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Applied Acoustics, 2022, 196, pp. 108897
Issue Date:: 2022-07-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0003682X22002717-main.pdf		1.93 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	Taşcı, B
dc.contributor.author	Acharya, MR
dc.contributor.author	Datta Barua, P
dc.contributor.author	Metehan Yildiz, A
dc.contributor.author	Veysel Gun, M
dc.contributor.author	Keles, T
dc.contributor.author	Dogan, S
dc.contributor.author	Tuncer, T
dc.date.accessioned	2023-06-27T05:42:42Z
dc.date.available	2023-06-27T05:42:42Z
dc.date.issued	2022-07-01
dc.identifier.citation	Applied Acoustics, 2022, 196, pp. 108897
dc.identifier.issn	0003-682X
dc.identifier.issn	1872-910X
dc.identifier.uri	http://hdl.handle.net/10453/170896
dc.description.abstract	Background and purpose: One of the essential purposes of sound classification is to achieve similar/over classification ability of the human auditory system (HAS). A new dataset and a biologically inspired feature extraction function have been proposed to realize this aim. We have developed a highly accurate sound classification architecture using the proposed biological-inspired feature extraction function. Materials and methods: In this research, a new environmental sound classification (ESC) dataset has been collected as a testbed, and this dataset contains 5000 sounds with 50 classes. Moreover, the collected ESC sound dataset is balanced. A new hand-modeled sound classification model has been proposed to classify sounds of this dataset. This model consists of (i) feature generation using a new lateral geniculate nucleus pattern (LGNPat), statistical moments and discrete wavelet transform (DWT), (ii) loop-based (iterative) neighborhood component analysis (INCA) based feature selection, (iii) classification using the selected features by k nearest neighbors (kNN) with 10-fold cross-validation. The proposed sound classification architecture is an extendable model. In this aspect, a new generation of hand-modeled sound/one-dimensional signal classification methods can be proposed. Results: The presented hand-modeled learning method was applied to the ESC dataset acquired, and our LGNPat-based model attained 93.34% classification. Conclusions: The computed 93.34% on the collected ESC dataset has demonstrated the success of our model. Moreover, the collected dataset has been publicly published. In this aspect, the published dataset can be used to improve advanced sound classification models.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Applied Acoustics
dc.relation.isbasedon	10.1016/j.apacoust.2022.108897
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0203 Classical Physics, 0913 Mechanical Engineering, 1201 Architecture
dc.subject.classification	Acoustics
dc.title	A new lateral geniculate nucleus pattern-based environmental sound classification using a new large sound dataset
dc.type	Journal Article
utslib.citation.volume	196
utslib.for	0203 Classical Physics
utslib.for	0913 Mechanical Engineering
utslib.for	1201 Architecture
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	2023-06-27T05:42:41Z
pubs.publication-status	Published
pubs.volume	196

Abstract:

Background and purpose: One of the essential purposes of sound classification is to achieve similar/over classification ability of the human auditory system (HAS). A new dataset and a biologically inspired feature extraction function have been proposed to realize this aim. We have developed a highly accurate sound classification architecture using the proposed biological-inspired feature extraction function. Materials and methods: In this research, a new environmental sound classification (ESC) dataset has been collected as a testbed, and this dataset contains 5000 sounds with 50 classes. Moreover, the collected ESC sound dataset is balanced. A new hand-modeled sound classification model has been proposed to classify sounds of this dataset. This model consists of (i) feature generation using a new lateral geniculate nucleus pattern (LGNPat), statistical moments and discrete wavelet transform (DWT), (ii) loop-based (iterative) neighborhood component analysis (INCA) based feature selection, (iii) classification using the selected features by k nearest neighbors (kNN) with 10-fold cross-validation. The proposed sound classification architecture is an extendable model. In this aspect, a new generation of hand-modeled sound/one-dimensional signal classification methods can be proposed. Results: The presented hand-modeled learning method was applied to the ESC dataset acquired, and our LGNPat-based model attained 93.34% classification. Conclusions: The computed 93.34% on the collected ESC dataset has demonstrated the success of our model. Moreover, the collected dataset has been publicly published. In this aspect, the published dataset can be used to improve advanced sound classification models.

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

http://hdl.handle.net/10453/170896