Fish Disease Classification Using MobileNetV3Large Transfer Learning and Fine-Tuning

Authors

  • Dela Fifi Lusiana ISB Atma Luhur
  • Ellya Helmud ISB Atma Luhur
  • Rahmat Sulaiman ISB Atma Luhur

DOI:

10.33395/sinkron.v10i3.16246

Keywords:

Automated Identification, MobileNetV3Large, Fish Disease, Transfer Learning, Fine-Tuning

Abstract

Fish diseases represent a major challenge in the aquaculture industry as this phenomenon frequently leads to significant economic losses. Manual disease identification requires specialized expertise and is time-consuming in the field. Therefore, this study aims to implement the MobileNetV3Large Deep Learning architecture to automatically identify eight types of fish conditions. This research dataset utilizes 2,400 digital images distributed evenly across eight fish condition categories. Each class consists of 300 image samples, including Bacterial Red disease, Aeromoniasis, Bacterial gill disease, EUS Disease, Fungal diseases Saprolegniasis, Parasitic diseases, White tail disease, and a Healthy Fish group. The dataset was sourced from https://www.kaggle.com/datasets/irfanulhuda/fish-disease-detection-dataset. These conditions include bacterial, fungal, viral, and parasitic infections, as well as healthy fish conditions. The research methodology applies Transfer Learning techniques combined with Fine-Tuning optimization on the last 70 layers. The methodology applies a transfer learning strategy with a data split of 80% for training, 10% for validation, and 10% for testing. This step was taken to adapt the model's weights to the visual characteristics of the fish disease images. The process was evaluated using the Adam optimization function and the Categorical Cross-Entropy loss function. Experimental results demonstrate highly superior model performance on the test data. The MobileNetV3Large model successfully achieved a test accuracy of 92.92% with a loss value of 0.2099. Furthermore, evaluation through the Confusion Matrix and ROC curves yielded an average AUC value of 1.00 across the majority of classes. This figure indicates that the model possesses exceptionally high discrimination capacity and sensitivity. In conclusion, the computational efficiency of the MobileNetV3Large architecture makes this system a highly potential solution. Researchers can implement this model on mobile devices to assist fish farmers in diagnosing diseases quickly and accurately directly at the aquaculture sites

GS Cited Analysis

Downloads

Download data is not yet available.

References

Adeeba, S. (2025). AI-Driven Solutions for Automated Fish Freshness Classification Using CNN Architectures. 2025 International Research Conference on Smart Computing and Systems Engineering (SCSE), Prosedings, 1–6. https://doi.org/10.1109/SCSE65633.2025.11031016

Ahmed, S., Aurpa, T. T., & Azad, A. K. (2022). Fish Disease Detection Using Image Based Machine Learning Technique in Aquaculture. Journal of King Saud University - Computer and Information Sciences, 34(8), 5170–5182. https://doi.org/10.1016/j.jksuci.2021.05.003

Antwi, K., Ebo, K., Kwaku, D., Asiedu, P., & Tekinerdogan, B. (2024). Smart Agricultural Technology On the application of image augmentation for plant disease detection : A systematic literature review. Smart Agricultural Technology, 9(September), 100590. https://doi.org/10.1016/j.atech.2024.100590

Beyza, M., Elham, Y., Yasin, T., & Koklu, M. (2024). Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application. European Food Research and Technology, December, 1919–1932. https://doi.org/https://doi.org/10.1007/s00217-024-04493-0

Cheng, W. A. I. K., Member, S., Tan, T. B., Tan, J. O. I. S. A. N., Chan, J. Y., Bea, K. T., Chen, Y., & Member, S. (2025). Smart Aquaculture : Integrating Computer Vision and IoT for Automated Crayfish Health Assessment via Federated Learning. IEEE Access, 13(October), 189979–189994. https://doi.org/10.1109/ACCESS.2025.3624140

Choompol, A., Gonwirat, S., Wichapa, N., Sriburum, A., & Thitapars, S. (2025). Evaluating Optimal Deep Learning Models for Freshness Assessment of Silver Barb Through Technique for Order Preference by Similarity to Ideal Solution with Linear Programming. MDPI, 14.105. https://doi.org/doi.org/10.3390/computers14030105

Eghbal-zadeh, H., Zellinger, W., Pintor, M., Grosse, K., Koutini, K., Moser, B. A., Biggio, B., & Widmer, G. (2024). Rethinking data augmentation for adversarial robustness. Information Sciences, 654(October 2023), 119838. https://doi.org/10.1016/j.ins.2023.119838

Gao, G. (2024). Research on marine fish classification and recognition based on an optimized ResNet50 model. Marine and Coastal Fisheries, August, 1–17. https://doi.org/10.1002/mcf2.10317

Helmud, E., Widodo, C. E., & Nurhayati, O. D. (2024). The Effect of Data Augmentation on the Accuracy of Fish Species Classification Using Deep Learning. 2024 Ninth International Conference on Informatics and Computing (ICIC), 1–7. https://doi.org/10.1109/ICIC64337.2024.10957253

Helmud, E., Widodo, C. E., & Nurhayati, O. D. (2025). Image-Based Fish Freshness Classification Using Two-Phase Transfer Learning with Deep Learning Fusion Model. Journal of Applied Data Sciences, 6(4), 2974–2987. https://doi.org/10.47738/jads.v6i4.988

Helmud, E., Widodo, C. E., & Nurhayati, O. D. (2026). Mathematical Modelling of Engineering Problems Fish Species Classification Through Deep Ensemble Learning : Multi-Scale Feature Integration and Model Averaging Strategy. Mathematical Modelling of Engineering Problems, 13(2), 347–355. https://doi.org/doi.org/10.18280/mmep.130211 Received:

Iqbal, G., Mushtaq, S., Singh, L. S., & Viral, A. (2023). Fungal diseases in aquaculture : A review. The Pharma Innovation, 12(7), 1959–1962.

Jayasekara, S. M., Garbutt, H., & Perera, C. D. (2025). Solvable constraints and unsolvable limits to global climate adaptation in coastal Indigenous food security. 3(2016). https://doi.org/10.1017/cft.2025.2

Kheriji, L., & Kouadri, A. (2025). Deep Learning-Based Fish Health Monitoring and Diagnosis : A Review. IEEE Access, 13(October), 181599–181616. https://doi.org/10.1109/ACCESS.2025.3621487

Markoulidakis, I. (2024). Probabilistic Confusion Matrix : A Novel Method for Machine Learning Algorithm Generalized Performance Analysis. MDPI, 12, 113. https://doi.org/https://doi.org/10.3390/technologies12070113

Mohammed, F. H. (2024). A Convolutional Neural Network Approach for Precision Fish Disease Detection. Evolutionary Studies in Imaginative Culture, 8, 244–256. https://doi.org/10.70082/esiculture.vi.944

Norouzi, N., Zarvani, M., Saberi, S., & Azmi, R. (2021). CBIR-GAN : A Triplet Generative Adversarial Network for Content-based Image Retrieval. SSRN Electronic Journal, October. https://doi.org/10.2139/ssrn.4057354

Odel, M., Rithmetic, A., Evel, I. M., Echniques, T., Lee, J., Mukhanov, L., & Martinez, J. (2021). Resource-Efficient Deep Learning: A Survey on Model Aritmetic and Implementation Lever Techniques. ACM Computing Surveys, 55. https://doi.org/10.1145/3587095

Qian, S. (2021). MobileNetV3 for Image Classification. IEEE Xplore., Icbaie, 490–494. https://doi.org/10.1109/ICCI-BDI51543.2021.9389905

Rangkuti, A. H., Naura, S., Naycilla, L., Manalu, K., Zindi, N., & Putri, A. (2025). Deep Learning for Marine Fish Species Identification with CNNs. 2025 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 1569–1574. https://doi.org/10.1109/ICIMCIS68501.2025.11327382

Sajid, Z., Gamperl, A. K., Parrish, C. C., Colombo, S. M., Santander, J., Mather, C., Holmen, I. M., Neis, B., Filgueira, R., Mckenzie, C. H., Cembella, A., Murray, H. M., Caballero-solares, A., Finnis, J., Fast, M. D., Wells, M., Fleming, I. A., & Singh, G. G. (2024). An aquaculture risk model to understand the causes and consequences of Atlantic Salmon mass mortality events : A review. 16(September 2023), 1674–1695. https://doi.org/10.1111/raq.12917

Shan, Y. I., Zhao, X. U. N., Ran, D. E. C. A. I., & Che, X. (2024). A Deep Learning Image Augmentation Method for Field Agriculture. IEEE Access, 12(March). https://doi.org/10.1109/ACCESS.2024.3373548

Tao, Y., & Zhong, R. (2025). Mitigating Class Imbalance Challenges in Fish Taxonomy : Quantifying Performance Gains Using Robust Asymmetric Loss Within an Optimized Mobile – Former Framework. MDPI, 14(Juni), 1–24. https://doi.org/https://doi.org/10.3390/ electronics14122333

Thu, T., Vo, E., Ko, H., Huh, J., & Kim, Y. (2021). Overview of Smart Aquaculture System : Focusing on Applications of Machine Learning and Computer Vision. MDPI, 10, 1–26. https://doi.org/10.3390/electronics10222882

Vrbančič, G., & Member, G. S. (2020). Transfer Learning With Adaptive Fine-Tuning. IEEE Access, 8(Oktober), 196197–196211. https://doi.org/10.1109/ACCESS.2020.3034343

Yasin, E. T., Ozkan, I. A., & Koklu, M. (2023). Detection of fish freshness using artificial intelligence methods. European Food Research and Technology,249(8), 1979–1990.https://doi.org/10.1007/s00217-023-04271-4

Yu, F., & Xiu, X. (2022). A Survey on Deep Transfer Learning and Beyond. MDPI, 10, 1–27. https://doi.org/10.3390/math10193619

Downloads


Crossmark Updates

How to Cite

Lusiana, D. F. ., Helmud, E., & Sulaiman, R. (2026). Fish Disease Classification Using MobileNetV3Large Transfer Learning and Fine-Tuning. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 10(3), 1679-1687. https://doi.org/10.33395/sinkron.v10i3.16246

Issue

Vol. 10 No. 3 (2026): Article Research July 2026

Section

Articles

License

Copyright (c) 2026 Dela Fifi Lusiana, Ellya Helmud, Rahmat Sulaiman

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC