A novel approach of audio based feature optimisation for bird classification

Murugaiya Ramashini, . and Pg Emeroylariffion Abas, . and Liyanage C De Silva, . A novel approach of audio based feature optimisation for bird classification. pp. 2383-2407. ISSN 2231-8526

Bird classification using audio data can be beneficial in assisting ornithologists bird watchers and environmentalists. However due to the complex environment in the jungles it is difficult to identify birds by visual inspection. Hence identification via acoustical means may be a better option in such an environment. This study aims to classify endemic Bornean birds using their sounds. Thirty-five (35) acoustic features have been extracted from the pre-recorded soundtracks of birds. In this paper a novel approach for selecting an optimum number of features using Linear Discriminant Analysis (LDA) has been proposed to give better classification accuracy. It is found that using a Nearest Centroid (NC) technique with LDA produces the optimum classification results of bird sounds at 96.7 accuracy with reduced computational power. The low computational complexity is an added advantage for handheld portable devices with minimal computing power which can be used in birdwatching expeditions. Comparison results have been provided with and without LDA using NC and Artificial Neural Network (ANN) classifiers. It has been demonstrated that both classifiers with LDA outperform those without LDA. Maximum accuracies for both NC and ANN with LDA with NC and the ANN classifiers requiring 7 and 10 LDAs to achieve the optimum accuracy respectively are 96.7. However ANN classifier with LDA is more computationally complex. Hence this is significant as the simpler NC classifier with LDA which does not require expensive processing power may be used on the portable and affordable device for bird classification purposes.

Full text available from: Official URL: http://www.pertanika.upm.edu.my/pjst/browse/regula...

Abstract

Bird classification using audio data can be beneficial in assisting ornithologists bird watchers and environmentalists. However due to the complex environment in the jungles it is difficult to identify birds by visual inspection. Hence identification via acoustical means may be a better option in such an environment. This study aims to classify endemic Bornean birds using their sounds. Thirty-five (35) acoustic features have been extracted from the pre-recorded soundtracks of birds. In this paper a novel approach for selecting an optimum number of features using Linear Discriminant Analysis (LDA) has been proposed to give better classification accuracy. It is found that using a Nearest Centroid (NC) technique with LDA produces the optimum classification results of bird sounds at 96.7 accuracy with reduced computational power. The low computational complexity is an added advantage for handheld portable devices with minimal computing power which can be used in birdwatching expeditions. Comparison results have been provided with and without LDA using NC and Artificial Neural Network (ANN) classifiers. It has been demonstrated that both classifiers with LDA outperform those without LDA. Maximum accuracies for both NC and ANN with LDA with NC and the ANN classifiers requiring 7 and 10 LDAs to achieve the optimum accuracy respectively are 96.7. However ANN classifier with LDA is more computationally complex. Hence this is significant as the simpler NC classifier with LDA which does not require expensive processing power may be used on the portable and affordable device for bird classification purposes.

[error in script]

Item Type:	Article
AGROVOC Term:	Birds
AGROVOC Term:	Endemic species
AGROVOC Term:	Sound
AGROVOC Term:	Information recording
AGROVOC Term:	Processing
AGROVOC Term:	Classification systems
AGROVOC Term:	Portable equipment
AGROVOC Term:	Information classification
Depositing User:	Mr. AFANDI ABDUL MALEK
Last Modified:	24 Apr 2025 00:55
URI:	http://webagris.upm.edu.my/id/eprint/10245

Actions (login required)

View Item