Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis

The expansion of aquaculture necessitates innovative disease detection methods to ensure sustainable production. Fish diseases caused by bacteria, viruses, fungi, and parasites result in significant economic losses and threaten food security. Traditional detection methods are labor-intensive and tim...

Full description

Saved in:
Bibliographic Details
Main Authors: Hayin Tamut, Robin Ghosh, Kamal Gosh, Md Abdus Salam Siddique
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Aquaculture Journal
Subjects:
Online Access:https://www.mdpi.com/2673-9496/5/1/6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342864166748160
author Hayin Tamut
Robin Ghosh
Kamal Gosh
Md Abdus Salam Siddique
author_facet Hayin Tamut
Robin Ghosh
Kamal Gosh
Md Abdus Salam Siddique
author_sort Hayin Tamut
collection DOAJ
description The expansion of aquaculture necessitates innovative disease detection methods to ensure sustainable production. Fish diseases caused by bacteria, viruses, fungi, and parasites result in significant economic losses and threaten food security. Traditional detection methods are labor-intensive and time-consuming, emphasizing the need for automated approaches. This study investigates the application of convolutional neural networks (CNNs) for classifying freshwater fish diseases. Such CNNs offer an efficient and automated solution for fish disease detection, reducing the burden on aquatic health experts and enabling timely interventions to mitigate economic losses. A dataset of 2444 images was used across seven classes—bacterial red disease, bacterial Aeromoniasis disease, bacterial gill disease, fungal disease, parasitic diseases, white tail disease, and healthy fish. The CNNs model incorporates convolutional layers for feature extraction, max-pooling for down-sampling, dense layers for classification, and dropout for regularization. Categorical cross-entropy loss and the Adam optimizer were used over 50 epochs, with continuous training and validation performance monitoring. The results indicated that the model achieved an accuracy of 99.71% and a test loss of 0.0119. This study highlights the transformative potential of artificial intelligence in aquaculture for enhancing food security.
format Article
id doaj-art-b67d0eb8511a4d799f50f58b0a64c9c9
institution Kabale University
issn 2673-9496
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Aquaculture Journal
spelling doaj-art-b67d0eb8511a4d799f50f58b0a64c9c92025-08-20T03:43:14ZengMDPI AGAquaculture Journal2673-94962025-03-0151610.3390/aquacj5010006Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks AnalysisHayin Tamut0Robin Ghosh1Kamal Gosh2Md Abdus Salam Siddique3Department of Engineering and Computing Sciences, Arkansas Tech University, Russellville, AR 72801, USADepartment of Engineering and Computing Sciences, Arkansas Tech University, Russellville, AR 72801, USADepartment of Agriculture and Natural Resources, Langston University, Langston, OK 73050, USADepartment of Engineering and Computing Sciences, Arkansas Tech University, Russellville, AR 72801, USAThe expansion of aquaculture necessitates innovative disease detection methods to ensure sustainable production. Fish diseases caused by bacteria, viruses, fungi, and parasites result in significant economic losses and threaten food security. Traditional detection methods are labor-intensive and time-consuming, emphasizing the need for automated approaches. This study investigates the application of convolutional neural networks (CNNs) for classifying freshwater fish diseases. Such CNNs offer an efficient and automated solution for fish disease detection, reducing the burden on aquatic health experts and enabling timely interventions to mitigate economic losses. A dataset of 2444 images was used across seven classes—bacterial red disease, bacterial Aeromoniasis disease, bacterial gill disease, fungal disease, parasitic diseases, white tail disease, and healthy fish. The CNNs model incorporates convolutional layers for feature extraction, max-pooling for down-sampling, dense layers for classification, and dropout for regularization. Categorical cross-entropy loss and the Adam optimizer were used over 50 epochs, with continuous training and validation performance monitoring. The results indicated that the model achieved an accuracy of 99.71% and a test loss of 0.0119. This study highlights the transformative potential of artificial intelligence in aquaculture for enhancing food security.https://www.mdpi.com/2673-9496/5/1/6aquacultureconvolutional neural networks (CNN)disease detectionfreshwater fishimage classificationdeep learning
spellingShingle Hayin Tamut
Robin Ghosh
Kamal Gosh
Md Abdus Salam Siddique
Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
Aquaculture Journal
aquaculture
convolutional neural networks (CNN)
disease detection
freshwater fish
image classification
deep learning
title Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
title_full Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
title_fullStr Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
title_full_unstemmed Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
title_short Enhancing Disease Detection in the Aquaculture Sector Using Convolutional Neural Networks Analysis
title_sort enhancing disease detection in the aquaculture sector using convolutional neural networks analysis
topic aquaculture
convolutional neural networks (CNN)
disease detection
freshwater fish
image classification
deep learning
url https://www.mdpi.com/2673-9496/5/1/6
work_keys_str_mv AT hayintamut enhancingdiseasedetectionintheaquaculturesectorusingconvolutionalneuralnetworksanalysis
AT robinghosh enhancingdiseasedetectionintheaquaculturesectorusingconvolutionalneuralnetworksanalysis
AT kamalgosh enhancingdiseasedetectionintheaquaculturesectorusingconvolutionalneuralnetworksanalysis
AT mdabdussalamsiddique enhancingdiseasedetectionintheaquaculturesectorusingconvolutionalneuralnetworksanalysis