Perbandingan Model EfficientNetV2B0 dan ResNet50 untuk Klasifikasi Citra Penyakit Mulut dan Kuku pada Sapi
DOI:
https://doi.org/10.29407/817cfc93Abstract
Abstrak—Penyakit Mulut dan Kuku (PMK) merupakan penyakit menular pada hewan ternak yang berdampak besar terhadap perekonomian peternak. Deteksi dini berbasis citra digital menggunakan deep learning menjadi pendekatan yang menjanjikan untuk mendukung identifikasi PMK secara cepat dan efisien. Penelitian ini membandingkan dua arsitektur Convolutional Neural Network (CNN), yaitu EfficientNetV2B0 dan ResNet50, dalam mengklasifikasikan citra sapi ke dalam empat kelas: Kuku_PMK, Kuku_Sehat, Mulut_PMK, dan Mulut_Sehat. Dataset berjumlah 406 citra asli yang kemudian diperbesar menjadi 2.400 citra melalui augmentasi offline, dengan pembagian 80:20 untuk data latih dan validasi. Kedua model dilatih menggunakan transfer learning dua fase dengan optimizer Adam dan teknik fine-tuning. Hasil evaluasi menunjukkan bahwa ResNet50 mencapai akurasi 92,50% dan F1-score makro 0,93, sedangkan EfficientNetV2B0 menghasilkan akurasi 91,25% dengan F1-score makro 0,92. Meskipun ResNet50 unggul secara akurasi, EfficientNetV2B0 lebih efisien dari sisi jumlah parameter, menjadikannya kandidat potensial untuk implementasi pada perangkat dengan sumber daya terbatas.
Keywords:
Klasifikasi Citra, CNN, EfficientNetV2B0, Penyakit Mulut dan Kuku, ResNet50##plugins.themes.default.displayStats.downloads##
References
[1] R. Prasetya, E. Sudarsono, D. Peternakan, K. Hewan, and K. Lamongan, “Kajian
Epidemiologi Kejadian Diduga Penyakit Mulut dan Kuku di Kabupaten Lamongan
Epidemiological Study of Suspected Occurrence of Foot and Mouth Disease in Lamongan
Regency.” doi: https://doi.org/10.20473/jbmv.v11i1.37197.
[2] S. Alexandersen, Z. Zhang, A. I. Donaldson, and A. J. M. Garland, “The Pathogenesis and
Diagnosis of Foot-and-Mouth Disease,” J. Comp. Pathol., vol. 129, no. 1, pp. 1–36, Jul.
2003, doi: 10.1016/S0021-9975(03)00041-0.
[3] M. J. Grubman and B. Baxt, “Foot-and-Mouth Disease,” Apr. 2004. doi:
10.1128/CMR.17.2.465-493.2004.
[4] I. Dittrich, M. Gertz, B. Maassen-Francke, K. H. Krudewig, W. Junge, and J. Krieter,
“Combining multivariate cumulative sum control charts with principal component
analysis and partial least squares model to detect sickness behaviour in dairy cattle,”
Comput. Electron. Agric., vol. 186, p. 106209, Jul. 2021, doi:
10.1016/J.COMPAG.2021.106209.
[5] M. Tan and Q. V Le, “EfficientNetV2: Smaller Models and Faster Training,” Jul. 01, 2021,
PMLR. Accessed: Dec. 10, 2025. [Online]. Available:
https://proceedings.mlr.press/v139/tan21a.html
[6] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,”
Dec. 2015, doi: https://doi.org/10.48550/arXiv.1512.03385.
[7] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep
Learning,” J. Big Data, vol. 6, no. 1, Dec. 2019, doi: 10.1186/s40537-019-0197-0.
[8] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Jan. 2017, doi:
10.48550/arXiv.1412.6980.
[9] A. Faturohman, D. Anggreani, and R. Yusliana Bakt, “Model Deep Learning Berbasis
Convolutional Neural Network Untuk Identifikasi Stroke Iskemik Pada Citra CT Scan,”
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence), vol. 5, no. 2, pp.
290–297, Aug. 2025, doi: 10.55382/jurnalpustakaai.v5i2.1150.
[10] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep
convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, Jun. 2017, doi:
10.1145/3065386.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
