Development of the Deep Learning System for Bird Classification Using Birdsong (조류 울음소리를 이용한 조류 분류 딥러닝 시스템 개발)

Min-Jeong Kang (강민정); Young-Seon Kim (김영선); Hwa-Yeong Shin (신화영); Park Jang Woo (박장우)

doi:10.34163/jkits.2020.15.2.005

Development of the Deep Learning System for Bird Classification Using Birdsong

Journal of Knowledge Information Technology and Systems
Abbr : JKITS
2020, 15(2), pp.195-203
DOI : 10.34163/jkits.2020.15.2.005
Publisher : Korea Knowledge Information Technology Society
Research Area : Interdisciplinary Studies > Interdisciplinary Research
Received : November 27, 2019
Accepted : April 10, 2020
Published : April 30, 2020

Min-Jeong Kang ¹, Young-Seon Kim ¹, Hwa-Yeong Shin ¹, Park Jang Woo ¹

¹순천대학교

Accredited

ABSTRACT

The activity and distribution of wild birds are biological indicators to evaluate biodiversity. In order to identify bird habitats, collecting and classifying sounds should have to do. Using the bird sound can make easier to distinguish location or type of wild birds. Recently, attempts to analyze bioacoustic data have been risen using the machine learning. We are going to classify the bird songs using deep learning. The bird songs convert into the spectrogram images. Spectrogram images are used for the input of convolutional neural network. In generally the bird song data set for classification contains a lot of noise. Even obtaining the data including noise is difficult. The data is about 200 bird sounds of 20 species. Based on transfer learning, ResNet34, ResNet50 and AlexNet of Convolutional Neural Network are used as the experiment. The experiment parameter is learning rate and epochs. As a result, the ResNet34 shows the highest accuracy of 99.7% and an average of 93% in the test. Therefore, In this paper, we are going to develop the deep learning system that classifies 20 kinds of bird song using ResNet34. By using this system, it can be helpful various activities such as the prevention of avian influenza.

KEYWORDS

Deep learning, Classification, Spectrogram, AI, Convolutional Neural Networks, ResNet, AlexNet

Citation status

* References for papers published after 2023 are currently being built.

[journal] H-J. Kim / 2018 / A winter waterbird monitoring for AI surveillance / National Institute of Biological Resources / National Institute of Biological Resources

[journal] 박진현 / 2019 / Application of CNN for Fish Species Classification / 한국정보통신학회논문지 / 한국정보통신학회 23(1) : 39~46

[journal] Y. LeCun / 1995 / Convolutional networks for images, speech, and time series / The handbook of brain theory and neural networks 3361(10) : 1~14

[web] / 2019 / What is Convolutional Neural Network? / MATLAB & Simulink / https://kr.mathworks.com/solutions/deep-learning/convolutional-neural-network.html

[web] / 2019 / Convolutional Neural Network Abstract / http://taewan.kim/post/cnn/

[web] / 2019 / Activation functions and it’s types-Which is better? / https://towardsdatascience.com/activation-functions-and-its-types-which-is-better-a9a5310cc8f

[journal] 손병직 / 2017 / Crack Recognition of Sewer with Low Resolution using Convolutional Neural Network(CNN) Method / 한국복합신소재구조학회 논문집 / 한국복합신소재구조학회 8(4) : 58~65

[confproc] K. He / 2016 / Deep residual learning for image recognition / Proceedings of the IEEE conference on computer vision and pattern recognition : 770~778

[book] A. Krizhevsky / 2012 / Advances in neural information processing systems / : 1097~1105

[web] / 2019 / Representative CNN models – AlexNet, VGGNet, GoogLeNet, ResNet / http://blog.naver.com/horajjan/221425497675

[journal] 김성혁 / 2017 / Influence on overfitting and reliability due to change in training data / The International Journal of Advanced Culture Technology / 국제문화기술진흥원 5(2) : 82~89

[journal] N. Srivastava / 2014 / Dropout : a simple way to prevent neural networks from overfitting / The journal of machine learning research 15(1) : 1929~1958

[other] E. Browning / 2017 / Passive acoustic monitoring in ecology and conservation / WWF-UK

[web] / 2019 / basic_train|fastai / https://docs.fast.ai/basic_train.html

[report] W-H. Hur / 2018 / A study of bird population monitoring in different habitats / National Institute of Biological Resources

KJCKorea
Journal Central

Journal of Knowledge Information Technology and Systems 2023 KCI Impact Factor : 0.89

Development of the Deep Learning System for Bird Classification Using Birdsong

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of Knowledge Information Technology and Systems 2023 KCI Impact Factor : 0.89

Development of the Deep Learning System for Bird Classification Using Birdsong

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (6)

REFERENCES (15) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.