Peningkatan Akurasi Klasifikasi Ikan kepe-kepe (Famili Chaetodontidae) dengan EfficientNetV2 dan Bayesian Hyperparameter Tuning

I Gusti Agung Putu Mahendra; Muhammad Ikhsan Wibowo; Zuliar Efendi

doi:10.30865/json.v7i2.9028

Authors

I Gusti Agung Putu Mahendra Politeknik Negeri Bengkalis
Muhammad Ikhsan Wibowo , Politeknik Negeri Bengkalis
Zuliar Efendi Politeknik Negeri Bengkalis

DOI:

https://doi.org/10.30865/json.v7i2.9028

Keywords:

Klasifikasi Citra; EfficientNetV2; Bayesian Hyperparameter Tuning; Ikan kepe-kepe (Famili Chaetodontidae); Augmentasi Data; Deep Learning

Abstract

Identifikasi cepat dan akurat spesies Chaetodontidae penting untuk monitoring keanekaragaman hayati laut, namun pendekatan manual tidak skala dan rentan kesalahan pada dataset besar. GAP riset yang kami tangani adalah: (i) ketiadaan kajian yang secara khusus mengombinasikan EfficientNetV2 dengan Bayesian hyperparameter tuning untuk klasifikasi Chaetodontidae, dan (ii) belum adanya evaluasi yang menekankan efisiensi penalaan adaptif beserta dampaknya terhadap performa. Kebaruan (novelty) studi ini ialah perancangan pipeline ringkas-efisien berbasis EfficientNetV2 dengan Bayesian Optimization (10 percobaan) pada learning rate, dropout, dan unfreeze backbone, dipadukan augmentasi kuat (MixUp, CutMix) serta regularisasi (label smoothing, L2). Dataset mencakup 1.427 citra/13 spesies dengan praproses center-crop 80% dan resize 224×224. Konfigurasi terbaik (unfreeze=True, dropout=0,2, LR 3,73×10⁻⁴) mencapai val-accuracy 92,75% dan akurasi uji 97%, dengan precision–recall rata-rata >95%, menunjukkan generalisasi yang baik bahkan pada kelas bermorfologi mirip. Dibanding penalaan manual/grid, pendekatan ini lebih hemat eksperimen sekaligus meningkatkan akurasi. Temuan tersebut menegaskan bahwa integrasi EfficientNetV2 + Bayesian tuning efektif dan siap diadopsi untuk sistem identifikasi–monitoring ikan berbasis citra pada konteks konservasi laut Indonesia.

References

[A. Nuryanto, DIAN BHAGAWATI, and KUSBIYANTO, “Evaluation of conservation and trade status of marine ornamental fish harvested from Pangandaran Coastal Waters, West Java, Indonesia,” Biodiversitas, vol. 21, no. 2, Jan. 2020, doi: 10.13057/biodiv/d210212.

J. P. Nowicki, L. A. O’Connell, P. F. Cowman, S. P. W. Walker, D. J. Coker, and M. S. Pratchett, “Variation in social systems within Chaetodon butterflyfishes, with special reference to pair bonding,” PLoS One, vol. 13, no. 4, p. e0194465, Apr. 2018, doi: 10.1371/journal.pone.0194465.

L. Mutawalli, M. T. A. Zaen, and Y. Yuliadi, “Komparasi CNN dengan ResNet Untuk Klasifikasi Paling Akurat Tingkat Keganasan Diabetes Berdasarkan Citra Retinopathy,” Journal of Computer System and Informatics (JoSYC), vol. 4, no. 3, pp. 522–529, May 2023, doi: 10.47065/josyc.v4i3.3248.

A. Mohammadisabet, R. Hasan, V. Dattana, S. Mahmood, and S. Hussain, “CNN-Based Optimization for Fish Species Classification: Tackling Environmental Variability, Class Imbalance, and Real-Time Constraints,” Information, vol. 16, no. 2, p. 154, Feb. 2025, doi: 10.3390/info16020154.

M. Mathur and N. Goel, “FishResNet: Automatic Fish Classification Approach in Underwater Scenario,” SN Comput Sci, vol. 2, no. 4, p. 273, Jul. 2021, doi: 10.1007/s42979-021-00614-8.

M. F. Hanifa et al., “Fishku Apps: Fishes Freshness Detection Using CNN With MobilenetV2,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 17, no. 1, p. 67, Feb. 2023, doi: 10.22146/ijccs.80049.

K. Kurniawan, A. Perdana Windarto, and S. Solikhun, “Refining CNN architecture for forest fire detection: improving accuracy through efficient hyperparameter tuning,” Bulletin of Electrical Engineering and Informatics, vol. 14, no. 2, pp. 1202–1211, Apr. 2025, doi: 10.11591/eei.v14i2.8805.

H. Cho, Y. Kim, E. Lee, D. Choi, Y. Lee, and W. Rhee, “Basic Enhancement Strategies When Using Bayesian Optimization for Hyperparameter Tuning of Deep Neural Networks,” IEEE Access, vol. 8, pp. 52588–52608, 2020, doi: 10.1109/ACCESS.2020.2981072.

A. Susilawati, A. Sh. M. Al-Obaidi, A. Abduh, F. S. Irwansyah, and A. B. D. Nandiyanto, “How to do research methodology: From Literature Review, Bibliometric, Step-by-step Research Stages, to Practical Examples in Science and Engineering Education,” Indonesian Journal of Science and Technology, vol. 10, no. 1, pp. 1–40, Jan. 2025, doi: 10.17509/ijost.v10i1.78637.

C. Cao, F. Zhou, Y. Dai, J. Wang, and K. Zhang, “A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability,” ACM Comput Surv, vol. 57, no. 2, pp. 1–38, Feb. 2025, doi: 10.1145/3696206.

H. Pan, Y. Guo, M. Yu, and J. Chen, “Enhanced Long-Tailed Recognition With Contrastive CutMix Augmentation,” IEEE Transactions on Image Processing, vol. 33, pp. 4215–4230, 2024, doi: 10.1109/TIP.2024.3425148.

D. Liu, W. Wang, X. Wu, and J. Yang, “EfficientNetv2 Model for Breast Cancer Histopathological Image Classification,” 2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI), pp. 384–387, Jan. 2022, doi: 10.1109/IWECAI55315.2022.00081.

[M. Hayat, N. Ahmad, A. Nasir, and Z. Ahmad Tariq, “Hybrid Deep learning EfficientNetV2 and Vision Transformer (EffNetV2-ViT) Model for Breast Cancer Histopathological Image Classification,” IEEE Access, vol. 12, pp. 184119–184131, 2024, doi: 10.1109/ACCESS.2024.3503413.

L. Jiang, S. Zhu, and N. Sun, “An Improved Lightweight Variant of EfficientNetV2 Coupled With Sensor Fusion and Transfer Learning Techniques for Motor Fault Diagnosis,” IEEE Access, vol. 12, pp. 84470–84487, 2024, doi: 10.1109/ACCESS.2024.3412050.

A. H. Victoria and G. Maragatham, “Automatic tuning of hyperparameters using Bayesian Optimization ,” Evolving Systems, vol. 12, no. 1, pp. 217–223, Mar. 2021, doi: 10.1007/s12530-020-09345-2.

M. Heydarian, T. E. Doyle, and R. Samavi, “MLCM: Multi-Label Confusion Matrix,” IEEE Access, vol. 10, pp. 19083–19095, 2022, doi: 10.1109/ACCESS.2022.3151048.

E. Zhang, R. Zhong, M. Munetomo, and M. Wahib, “Validation Loss Landscape Exploration with Deep Q-Learning,” in 2024 International Joint Conference on Neural Networks (IJCNN), IEEE, Jun. 2024, pp. 1–9. doi: 10.1109/IJCNN60899.2024.10651182.

M. M. Bejani and M. Ghatee, “A systematic review on overfitting control in shallow and deep neural networks,” Artif Intell Rev, vol. 54, no. 8, pp. 6391–6438, Dec. 2021, doi: 10.1007/s10462-021-09975-1.

I. P. A. Putra, I. M. A. Wirawan, and I. G. A. Gunadi, “Improving Butterfly Fish Image Classification Accuracy using HSV Feature Extraction and SMOTE-Based Data Balancing,” INOVTEK Polbeng - Seri Informatika, vol. 10, no. 3, pp. 1402–1411, Aug. 2025, doi: 10.35314/vw52nn48.

Herlambang Duwi Prasetyo, Pandu Ananto Hogantara, and Ika Nurlaili Isnainiyah, “MobileNets-V1 Architecture for Web Based Fish Image Classification,” Data Science: Journal of Computing and Applied Informatics, vol. 5, no. 2, pp. 60–70, Jul. 2021, doi: 10.32734/jocai.v5.i2-6291.

D. Rathi, S. Jain, and S. Indu, “Underwater Fish Species Classification using Convolutional Neural Network and Deep learning.” [Online]. Available: http://dhruvrathi.me/http://www.dtu.ac.in/Web/Departments/Electronics/faculty/sindu.php