loading
Documents

Research.Publish.Connect.

Paper

Authors: Ngoc Nguyen 1 ; Mera Delimayanti 2 ; Bedy Purnama 3 ; Kunti Mahmudah 1 ; Mamoru Kubo 4 ; Makiko Kakikawa 4 ; Yoichi Yamada 4 and Kenji Satou 4

Affiliations: 1 Department of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, Japan ; 2 Department of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, Japan, Department of Computer and Informatics Engineering, Politeknik Negeri Jakarta, Jakarta, Indonesia ; 3 Department of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, Japan, Telkom School of Computing, TELKOM University, Bandung, Indonesia ; 4 Institute of Science and Engineering, Kanazawa University, Kanazawa, Japan

ISBN: 978-989-758-353-7

Keyword(s): Swimming Mouse Behaviour Recognition, Deep Learning, Transfer Learning, Data Scarcity.

Abstract: Deep learning models have shown their ability to model complicated problems in more efficient ways than other machine learning techniques in many application fields. For human action recognition tasks, the current state-of-the-art models are deep learning models. But they are not well-studied in applying for animal behaviour recognition due to the lack of data required for training these models. Therefore, in this research, we proposed a method to apply deep learning models to recognize the behaviours of a swimming mouse in two mouse forced swim tests with a limited amount of training data. We used deep learning models which are used in human action recognition tasks and fine-tuned them on the largest publicly available mouse behaviour dataset to give the models the knowledge about mouse behaviour recognition tasks. Then we fine-tuned the models one more time using the small amount of data that we have annotated for our swimming mouse behaviour recognition tasks. The good performance of these models in the new tasks proved the efficiency of our approach. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.232.124.77

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Nguyen, N.; Delimayanti, M.; Purnama, B.; Mahmudah, K.; Kubo, M.; Kakikawa, M.; Yamada, Y. and Satou, K. (2019). Applying Deep Learning Models to Action Recognition of Swimming Mice with the Scarcity of Training Data.In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, ISBN 978-989-758-353-7, pages 270-275. DOI: 10.5220/0007567602700275

@conference{bioinformatics19,
author={Ngoc Giang Nguyen. and Mera Kartika Delimayanti. and Bedy Purnama. and Kunti Robiatul Mahmudah. and Mamoru Kubo. and Makiko Kakikawa. and Yoichi Yamada. and Kenji Satou.},
title={Applying Deep Learning Models to Action Recognition of Swimming Mice with the Scarcity of Training Data},
booktitle={Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS,},
year={2019},
pages={270-275},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007567602700275},
isbn={978-989-758-353-7},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS,
TI - Applying Deep Learning Models to Action Recognition of Swimming Mice with the Scarcity of Training Data
SN - 978-989-758-353-7
AU - Nguyen, N.
AU - Delimayanti, M.
AU - Purnama, B.
AU - Mahmudah, K.
AU - Kubo, M.
AU - Kakikawa, M.
AU - Yamada, Y.
AU - Satou, K.
PY - 2019
SP - 270
EP - 275
DO - 10.5220/0007567602700275

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.