Abnormal behaviour in rock bream (Oplegnathus fasciatus) detected using deep learning-based image analysis
Various approaches have been applied to transform aquaculture from a manual, labour-intensive industry to one dependent on automation technologies in the era of the fourth industrial revolution. Technologies associated with the monitoring o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Society of Fisheries and Aquatic Science
2022-03-01
|
| Series: | Fisheries and Aquatic Sciences |
| Subjects: | |
| Online Access: | http://www.e-fas.org/archive/view_article?pid=fas-25-3-151 |
| _version_ | 1818030397079945216 |
|---|---|
| author | Jun-Chul Jang Yeo-Reum Kim SuHo Bak Seon-Woong Jang Jong-Myoung Kim |
| author_facet | Jun-Chul Jang Yeo-Reum Kim SuHo Bak Seon-Woong Jang Jong-Myoung Kim |
| author_sort | Jun-Chul Jang |
| collection | DOAJ |
| description | Various approaches have been applied to transform aquaculture from a manual,
labour-intensive industry to one dependent on automation technologies in the era
of the fourth industrial revolution. Technologies associated with the monitoring
of physical condition have successfully been applied in most aquafarm
facilities; however, real-time biological monitoring systems that can observe
fish condition and behaviour are still required. In this study, we used a video
recorder placed on top of a fish tank to observe the swimming patterns of rock
bream (Oplegnathus fasciatus), first one fish alone and then a
group of five fish. Rock bream in the video samples were successfully identified
using the you-only-look-once v3 algorithm, which is based on the Darknet-53
convolutional neural network. In addition to recordings of swimming behaviour
under normal conditions, the swimming patterns of fish under abnormal conditions
were recorded on adding an anaesthetic or lowering the salinity. The abnormal
conditions led to changes in the velocity of movement (3.8 ± 0.6 cm/s)
involving an initial rapid increase in speed (up to 16.5 ± 3.0 cm/s, upon
2-phenoxyethanol treatment) before the fish stopped moving, as well as changing
from swimming upright to dying lying on their sides. Machine learning was
applied to datasets consisting of normal or abnormal behaviour patterns, to
evaluate the fish behaviour. The proposed algorithm showed a high accuracy
(98.1%) in discriminating normal and abnormal rock bream behaviour. We conclude
that artificial intelligence-based detection of abnormal behaviour can be
applied to develop an automatic bio-management system for use in the aquaculture
industry. |
| first_indexed | 2024-12-10T05:34:56Z |
| format | Article |
| id | doaj.art-7d4150e2764949b6a0dd97607f1202dd |
| institution | Directory Open Access Journal |
| issn | 2234-1757 |
| language | English |
| last_indexed | 2024-12-10T05:34:56Z |
| publishDate | 2022-03-01 |
| publisher | The Korean Society of Fisheries and Aquatic Science |
| record_format | Article |
| series | Fisheries and Aquatic Sciences |
| spelling | doaj.art-7d4150e2764949b6a0dd97607f1202dd2022-12-22T02:00:26ZengThe Korean Society of Fisheries and Aquatic ScienceFisheries and Aquatic Sciences2234-17572022-03-0125315115710.47853/FAS.2022.e13fas-25-3-151Abnormal behaviour in rock bream (Oplegnathus fasciatus) detected using deep learning-based image analysisJun-Chul Jang0Yeo-Reum Kim1SuHo Bak2Seon-Woong Jang3Jong-Myoung Kim4Department of Fisheries Biology, Pukyong National University, Department of Fisheries Biology, Pukyong National University, IREMTECH. Co., Ltd, IREMTECH. Co., Ltd, Department of Fisheries Biology, Pukyong National University, Various approaches have been applied to transform aquaculture from a manual, labour-intensive industry to one dependent on automation technologies in the era of the fourth industrial revolution. Technologies associated with the monitoring of physical condition have successfully been applied in most aquafarm facilities; however, real-time biological monitoring systems that can observe fish condition and behaviour are still required. In this study, we used a video recorder placed on top of a fish tank to observe the swimming patterns of rock bream (Oplegnathus fasciatus), first one fish alone and then a group of five fish. Rock bream in the video samples were successfully identified using the you-only-look-once v3 algorithm, which is based on the Darknet-53 convolutional neural network. In addition to recordings of swimming behaviour under normal conditions, the swimming patterns of fish under abnormal conditions were recorded on adding an anaesthetic or lowering the salinity. The abnormal conditions led to changes in the velocity of movement (3.8 ± 0.6 cm/s) involving an initial rapid increase in speed (up to 16.5 ± 3.0 cm/s, upon 2-phenoxyethanol treatment) before the fish stopped moving, as well as changing from swimming upright to dying lying on their sides. Machine learning was applied to datasets consisting of normal or abnormal behaviour patterns, to evaluate the fish behaviour. The proposed algorithm showed a high accuracy (98.1%) in discriminating normal and abnormal rock bream behaviour. We conclude that artificial intelligence-based detection of abnormal behaviour can be applied to develop an automatic bio-management system for use in the aquaculture industry.http://www.e-fas.org/archive/view_article?pid=fas-25-3-151abnormal behaviourdeep learningobject detectionrock breamsmart aquafarm |
| spellingShingle | Jun-Chul Jang Yeo-Reum Kim SuHo Bak Seon-Woong Jang Jong-Myoung Kim Abnormal behaviour in rock bream (Oplegnathus fasciatus) detected using deep learning-based image analysis Fisheries and Aquatic Sciences abnormal behaviour deep learning object detection rock bream smart aquafarm |
| title | Abnormal behaviour in rock bream (Oplegnathus
fasciatus) detected using deep learning-based image
analysis |
| title_full | Abnormal behaviour in rock bream (Oplegnathus
fasciatus) detected using deep learning-based image
analysis |
| title_fullStr | Abnormal behaviour in rock bream (Oplegnathus
fasciatus) detected using deep learning-based image
analysis |
| title_full_unstemmed | Abnormal behaviour in rock bream (Oplegnathus
fasciatus) detected using deep learning-based image
analysis |
| title_short | Abnormal behaviour in rock bream (Oplegnathus
fasciatus) detected using deep learning-based image
analysis |
| title_sort | abnormal behaviour in rock bream oplegnathus fasciatus detected using deep learning based image analysis |
| topic | abnormal behaviour deep learning object detection rock bream smart aquafarm |
| url | http://www.e-fas.org/archive/view_article?pid=fas-25-3-151 |
| work_keys_str_mv | AT junchuljang abnormalbehaviourinrockbreamoplegnathusfasciatusdetectedusingdeeplearningbasedimageanalysis AT yeoreumkim abnormalbehaviourinrockbreamoplegnathusfasciatusdetectedusingdeeplearningbasedimageanalysis AT suhobak abnormalbehaviourinrockbreamoplegnathusfasciatusdetectedusingdeeplearningbasedimageanalysis AT seonwoongjang abnormalbehaviourinrockbreamoplegnathusfasciatusdetectedusingdeeplearningbasedimageanalysis AT jongmyoungkim abnormalbehaviourinrockbreamoplegnathusfasciatusdetectedusingdeeplearningbasedimageanalysis |