Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 10.29 MB
Add to list
  1. Search results
  2. Otolith identification using a deep h...

Otolith identification using a deep hierarchical classification model

Michiel Stock (UGent) , Bac Nguyen Cong (UGent) , Wouter Courtens, Hilbran Verstraete, Eric Stienen and Bernard De Baets (UGent)
(2021) COMPUTERS AND ELECTRONICS IN AGRICULTURE. 180.
Author
Organization
Project
Abstract
The diet of seabirds can yield important insights into the status of economically and ecologically important fish. By analyzing the otoliths found in the birds' droppings, researchers can observe which fish the birds eat in which abundances. However, identifying the species based on an otolith image is quite labor-intensive and requires particular expertise. In this work, we show that a deep convolutional neural network can identify six fish species with high accuracy. We show that this deep learning approach outperforms more traditional methods and is also more accessible to set up in practice. By exploiting the hierarchy in the species labels, we impose a structure on the prediction probabilities, leading to a remarkable improvement compared to a conventional artificial neural network. Importantly, we can attain good results using only a modest dataset, demonstrating that such approaches are feasible for small-scale and specialized projects.
Keywords
Otolith identification, Seabird diet, Deep learning, Hierarchical softmax, SHAPE-ANALYSIS, FORAGE FISH, DIET, TERNS, SEABIRDS, ATLANTIC, ECOLOGY, SIZE, AGE

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 10.29 MB

Citation

Please use this url to cite or link to this publication:

MLA
Stock, Michiel, et al. “Otolith Identification Using a Deep Hierarchical Classification Model.” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 180, 2021, doi:10.1016/j.compag.2020.105883.
APA
Stock, M., Nguyen Cong, B., Courtens, W., Verstraete, H., Stienen, E., & De Baets, B. (2021). Otolith identification using a deep hierarchical classification model. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 180. https://doi.org/10.1016/j.compag.2020.105883
Chicago author-date
Stock, Michiel, Bac Nguyen Cong, Wouter Courtens, Hilbran Verstraete, Eric Stienen, and Bernard De Baets. 2021. “Otolith Identification Using a Deep Hierarchical Classification Model.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 180. https://doi.org/10.1016/j.compag.2020.105883.
Chicago author-date (all authors)
Stock, Michiel, Bac Nguyen Cong, Wouter Courtens, Hilbran Verstraete, Eric Stienen, and Bernard De Baets. 2021. “Otolith Identification Using a Deep Hierarchical Classification Model.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 180. doi:10.1016/j.compag.2020.105883.
Vancouver
1.
Stock M, Nguyen Cong B, Courtens W, Verstraete H, Stienen E, De Baets B. Otolith identification using a deep hierarchical classification model. COMPUTERS AND ELECTRONICS IN AGRICULTURE. 2021;180.
IEEE
[1]
M. Stock, B. Nguyen Cong, W. Courtens, H. Verstraete, E. Stienen, and B. De Baets, “Otolith identification using a deep hierarchical classification model,” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 180, 2021.
@article{8685343,
  abstract     = {{The diet of seabirds can yield important insights into the status of economically and ecologically important fish. By analyzing the otoliths found in the birds' droppings, researchers can observe which fish the birds eat in which abundances. However, identifying the species based on an otolith image is quite labor-intensive and requires particular expertise. In this work, we show that a deep convolutional neural network can identify six fish species with high accuracy. We show that this deep learning approach outperforms more traditional methods and is also more accessible to set up in practice. By exploiting the hierarchy in the species labels, we impose a structure on the prediction probabilities, leading to a remarkable improvement compared to a conventional artificial neural network. Importantly, we can attain good results using only a modest dataset, demonstrating that such approaches are feasible for small-scale and specialized projects.}},
  articleno    = {{105883}},
  author       = {{Stock, Michiel and Nguyen Cong, Bac and Courtens, Wouter and Verstraete, Hilbran and Stienen, Eric and De Baets, Bernard}},
  issn         = {{0168-1699}},
  journal      = {{COMPUTERS AND ELECTRONICS IN AGRICULTURE}},
  keywords     = {{Otolith identification,Seabird diet,Deep learning,Hierarchical softmax,SHAPE-ANALYSIS,FORAGE FISH,DIET,TERNS,SEABIRDS,ATLANTIC,ECOLOGY,SIZE,AGE}},
  language     = {{eng}},
  pages        = {{10}},
  title        = {{Otolith identification using a deep hierarchical classification model}},
  url          = {{http://doi.org/10.1016/j.compag.2020.105883}},
  volume       = {{180}},
  year         = {{2021}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: