Image-Based Asymmetric Feature Fusion Using EfficientNet-B0 and MobileNetV3Large for Multi-Class Fish Disease Classification
DOI:
https://doi.org/10.63158/journalisi.v8i5.1798Keywords:
Fish disease classification, hybrid feature fusion, EfficientNet-B0, MobileNetV3Large, deep learningAbstract
This study proposes an asymmetric hybrid feature-fusion network that combines EfficientNet-B0 and MobileNetV3Large in parallel for multi-class classification of eight fish disease categories. The approach is designed to exploit the complementary feature-learning capabilities of both lightweight convolutional neural network architectures while maintaining computational efficiency for potential diagnostic applications. The model was evaluated on a public dataset of 2,400 digital images, divided into training, validation, and test sets using an 80:10:10 ratio. The held-out test set contained 240 unseen images, with 30 images representing each class. As all data partitions originated from the same dataset, the evaluation reflects performance on the same source distribution rather than external generalization. The proposed architecture fuses spatial feature representations through parallel Global Average Pooling (GAP) and Global Max Pooling (GMP) layers. Training followed a progressive two-phase strategy comprising top-layer warm-up and micro deep fine-tuning with a learning rate of \(10^{-5}\) and label smoothing. Experimental results achieved a validation accuracy of 0.9667 with a loss of 0.5843, and a test accuracy of 0.9833 with a loss of 0.5375 and a macro-average ROC-AUC of 0.9998. On an NVIDIA RTX 3080 GPU, the model recorded an average inference time of 8.61 ms per image, equivalent to 116.18 FPS. Further evaluation using external farm datasets and low-power edge devices is required before real-world deployment.
Downloads
References
[1] D. R. Wijaya, N. F. Syarwan, M. A. Nugraha, D. Ananda, T. Fahrudin, and R. Handayani, "Seafood Quality Detection Using Electronic Nose and Machine Learning Algorithms With Hyperparameter Optimization," IEEE Access, vol. 11, pp. 62484–62495, 2023, doi: 10.1109/ACCESS.2023.3286980.
[2] B. Hossain et al., "Advancing Fish Farming Through Deep Learning: Applications, Opportunities, Challenges, and Future Directions," Pathfinder Res., vol. 2, no. 3, pp. 39–58, 2024, doi: 10.69937/pf.por.2.3.39.
[3] A. Assefa, "Maintenance of Fish Health in Aquaculture: Review of Epidemiological Approaches for Prevention and Control of Infectious Disease of Fish," Vet. Med. Int., vol. 2018, art. no. 5432497, 2018, doi: 10.1155/2018/5432497.
[4] D. Li, X. Li, Q. Wang, and Y. Hao, "Advanced Techniques for the Intelligent Diagnosis of Fish Diseases: A Review," Animals, vol. 12, no. 21, art. no. 2938, 2022, doi: 10.3390/ani12212938.
[5] J. Li et al., "An Edge-Ready Lightweight Computer Vision Framework for On-Site Fish Disease Detection in Aquaculture Management," Fishes, vol. 10, no. 5, art. no. 280, 2025, doi: 10.3390/fishes10050280.
[6] P. Kabitha and D. U. Nandini, "VMI-ATN-RCNN: A Hybrid Deep Learning Model for Fish Disease Segmentation and Classification in Aquaculture," Aquaculture, vol. 600, art. no. 743047, 2025, doi: 10.1016/j.aquaculture.2024.743047.
[7] M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proc. Int. Conf. Mach. Learn. (ICML), 2019, pp. 6105–6114.
[8] A. Howard et al., "Searching for MobileNetV3," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 1314–1324.
[9] T. Shahriar, "Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices," Pattern Recognit. Image Anal., vol. 35, no. 2, pp. 101–115, 2025, doi: 10.48550/arXiv.2505.03303.
[10] S. M. Raza, S. Murtaza, H. Abidi, and Y. Shin, "Lightweight Deep Learning for Visual Perception: A Survey of Models, Compression Strategies, and Edge Deployment Challenges," Neurocomputing, vol. 656, art. no. 131357, 2025, doi: 10.1016/j.neucom.2025.131357.
[11] H. Malik, S. Hassan, F. Ali, and D. K. Yon, "Multi-Classification Deep Neural Networks for Identification of Fish Species Using Camera Captured Images," PLoS ONE, vol. 18, no. 4, art. no. e0284992, 2023, doi: 10.1371/journal.pone.0284992.
[12] K. Antwi, K. Ebo, D. Kwaku, P. Asiedu, and B. Tekinerdogan, "On the Application of Image Augmentation for Deep Learning Models: A Systematic Literature Review," Smart Agric. Technol., vol. 9, art. no. 100590, 2024, doi: 10.1016/j.atech.2024.100590.
[13] E. Helmud, C. E. Widodo, and O. D. Nurhayati, "Fish Species Classification Through Deep Ensemble Learning: Multi-Scale Feature Integration and Model Averaging Strategy," Math. Model. Eng. Probl., vol. 12, no. 2, pp. 347–355, 2025, doi: 10.18280/mmep.120211.
[14] S. Ahmed, T. T. Aurpa, and A. K. Azad, "Fish Disease Detection Using Image Based Machine Learning Technique in Aquaculture," J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, pp. 5170–5182, 2022, doi: 10.1016/j.jksuci.2021.05.003.
[15] E. Helmud, C. E. Widodo, and O. D. Nurhayati, "Image-Based Fish Freshness Classification Using Two-Phase Transfer Learning with Deep Learning Fusion Model," J. Appl. Data Sci., vol. 6, no. 4, pp. 2974–2987, 2025, doi: 10.47738/jads.v6i4.988.
[16] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826, doi: 10.1109/CVPR.2016.308.
[17] J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How Transferable Are Features in Deep Neural Networks?," in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2014, pp. 3320–3328.
[18] J. A. Hanley and B. J. McNeil, "The Meaning and Use of the Area Under a Receiver Operating Characteristic (ROC) Curve," Radiology, vol. 143, no. 1, pp. 29–36, 1982, doi: 10.1148/radiology.143.1.7063747.
[19] J. Islam, "Fish Disease Dataset," Kaggle, 2025. [Online]. Available: https://www.kaggle.com/datasets/jihad080/fish-disease-dataset
[20] I. Markoulidakis, "Probabilistic Confusion Matrix: A Novel Method for Machine Learning Algorithm Generalized Performance Analysis," Technologies, vol. 12, no. 7, art. no. 113, 2024, doi: 10.3390/technologies12070113.
[21] I. D. Mienye, "A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications," Information, vol. 15, no. 12, art. no. 755, 2024, doi: 10.3390/info15120755.
[22] N. P. Desai, M. Farhan, A. Makrariya, and R. Musheeraziz, "Image Processing Modelwith Deep Learning Approach for Fish Species Classification," Turk. J. Comput. Math. Educ., vol. 13, no. 1, pp. 85–99, 2022, doi: 10.17762/turcomat.v13i1.11963.
[23] A. Choompol, S. Gonwirat, N. Wichapa, A. Sriburum, and S. Thitapars, "Evaluating Optimal Deep Learning Models for Freshness Assessment of Silver Barb Through TOPSIS with Linear Programming," Computers, vol. 14, art. no. 105, 2025, doi: 10.3390/computers14030105.
[24] L. Chen, C. Wang, and Y. Zhang, "Edge-Based Computer Vision Deployment for Smart Aquaculture: Performance and Latency Evaluation," Comput. Electron. Agric., vol. 218, art. no. 108712, 2024, doi: 10.1016/j.compag.2024.108712.
[25] S. Ragab et al., "Overview of Aquaculture Artificial Intelligence (AAI) Applications: Enhance Sustainability and Productivity, Reduce Labor Costs, and Increase the Quality of Aquatic Products," Ann. Anim. Sci., vol. 25, no. 2, pp. 441–453, 2025, doi: 10.2478/aoas-2024-0075.
[26] Z. Zhao and X. Liu, "Deep Feature Fusion Mechanisms for Underwater Vision Systems: A Review," IEEE J. Ocean. Eng., vol. 49, no. 3, pp. 812–828, 2024, doi: 10.1109/JOE.2024.3361102.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
