Classification of bearded seals signal based on convolutional neural network

被引:1
作者
Kim, Ji Seop
Yoon, Young Geul
Han, Dong-Gyun
La, Hyoung Sul
Choi, Jee Woong
机构
[1] Department of Marine Sciences and Convergence Engineering, Hanyang University, 55 Hanyangdaehak-ro, Sangnok-gu, Gyeonggi Province, Ansan
来源
JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA | 2022年 / 41卷 / 02期
关键词
Passive acoustic monitoring; Bearded seal; Deep learning; Convolution neural network; Classification;
D O I
10.7776/ASK.2022.41.2.235
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Several studies using Convolutional Neural Network (CNN) have been conducted to detect and classify the sounds of marine mammals in underwater acoustic data collected through passive acoustic monitoring. In this study, the possibility of automatic classification of bearded seal sounds was confirmed using a CNN model based on the underwater acoustic spectrogram images collected from August 2017 to August 2018 in East Siberian Sea. When only the clear seal sound was used as training dataset, overfitting due to memorization was occurred. By evaluating the entire training data by replacing some training data with data containing noise, it was confirmed that overfitting was prevented as the model was generalized more than before with accuracy (0.9743), precision (0.9783), recall (0.9520). As a result, the performance of the classification model for bearded seals signal has improved when the noise was included in the training data.
引用
收藏
页码:235 / 241
页数:7
相关论文
共 27 条
[1]  
[Anonymous], 2012, PREPRINT
[2]  
Behnke S, 2003, LECT NOTES COMPUT SC, V2766, P1
[3]   Bearded seal males perceive geographic variation in their trills [J].
Charrier, Isabelle ;
Mathevon, Nicolas ;
Aubin, Thierry .
BEHAVIORAL ECOLOGY AND SOCIOBIOLOGY, 2013, 67 (10) :1679-1689
[4]   Seabed classification using physics-based modeling and machine learninga) [J].
Frederick, Christina ;
Villar, Soledad ;
Michalopoulou, Zoi-Heleni .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2020, 148 (02) :859-872
[5]   Effects of Geophony and Anthrophony on the Underwater Acoustic Environment in the East Siberian Sea, Arctic Ocean [J].
Han, Dong-Gyun ;
Joo, Jongmin ;
Son, Wuju ;
Cho, Kyoung Ho ;
Choi, Jee Woong ;
Yang, Eun Jin ;
Kim, Jeong-Hoon ;
Kang, Sung-Ho ;
La, Hyoung Sul .
GEOPHYSICAL RESEARCH LETTERS, 2021, 48 (12)
[6]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[7]  
Hinton GE., 2012, COMPUT SCI, V3, P212
[8]   Seasonal variations in the call presence of bearded seals in relation to sea ice in the southern Chukchi Sea [J].
Jimbo, Mina ;
Mizuguchi, Daisuke ;
Shirakawa, Hokuto ;
Tsujii, Koki ;
Fujiwara, Amane ;
Miyashita, Kazushi ;
Mitani, Yoko .
POLAR BIOLOGY, 2019, 42 (10) :1953-1958
[9]   Application of the artificial intelligence for automatic detection of shipping noise in shallow-water [J].
Kim, Sunhyo ;
Jung, Seom-Kyu ;
Kang, Donhyug ;
Kim, Mira ;
Choi, Sungho .
JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2020, 39 (04) :279-285
[10]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90