Feature Selection Approaches for Optimising Music Emotion Recognition Methods

Cai, L; Ferguson, S; Lu, H; Fang, G

Feature Selection Approaches for Optimising Music Emotion Recognition Methods

Cai, L Ferguson, S Lu, H Fang, G

Permalink

Publisher:: Academy and Industry Research Collaboration Center (AIRCC)
Publication Type:: Conference Proceeding
Citation:: Artificial Intelligence, Soft Computing and Applications, 2022
Issue Date:: 2022-12-22

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (1.13 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Cai, L
dc.contributor.author	Ferguson, S
dc.contributor.author	Lu, H
dc.contributor.author	Fang, G
dc.date.accessioned	2022-12-29T16:30:10Z
dc.date.available	2022-12-29T16:30:10Z
dc.date.issued	2022-12-22
dc.identifier.citation	Artificial Intelligence, Soft Computing and Applications, 2022
dc.identifier.uri	http://hdl.handle.net/10453/164585
dc.description.abstract	<jats:p>The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task.</jats:p>
dc.language	en
dc.publisher	Academy and Industry Research Collaboration Center (AIRCC)
dc.relation.ispartof	Artificial Intelligence, Soft Computing and Applications
dc.relation.ispartof	12th International Conference on Artificial Intelligence, Soft Computing and Applications
dc.relation.isbasedon	10.5121/csit.2022.122302
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Feature Selection Approaches for Optimising Music Emotion Recognition Methods
dc.type	Conference Proceeding
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 Electrical and Data Engineering
utslib.copyright.status	open_access	*
dc.date.updated	2022-12-29T16:30:08Z
pubs.publication-status	Published

Abstract:

The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task.

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

http://hdl.handle.net/10453/164585