ANALISIS PENGARUH VARIASI EPOCH PELATIHAN TERHADAP KINERJA MODEL MOBILENETV2 DALAM KLASIFIKASI PENYAKIT DAUN APEL
DOI:
https://doi.org/10.29407/k3veda10Abstract
Tanaman apel merupakan komoditas hortikultura bernilai ekonomi tinggi yang produktivitasnya bergantung pada kesehatan daun. Proses identifikasi penyakit secara manual oleh petani memiliki kelemahan berupa subjektivitas tinggi, memakan waktu lama, dan rentan salah diagnosis. Penelitian ini bertujuan menganalisis pengaruh variasi jumlah epoch pelatihan terhadap kinerja model deep learning MobileNetV2 dalam klasifikasi penyakit daun apel pada antarmuka web sederhana. Metode yang digunakan adalah Development Research dengan model sekuensial Waterfall. Dataset berjumlah 18.178 citra gabungan dari Plant Pathology 2021 FGVC8 dan data lapangan dengan rasio pembagian 70:15:15. Eksperimen dilakukan dengan memvariasikan jumlah epoch pelatihan dalam tiga fase bertahap guna menentukan konfigurasi optimal yang menghasilkan akurasi tertinggi sekaligus meminimalkan risiko overfitting. Hasil eksperimen menunjukkan model dengan konfigurasi epoch optimal mencapai akurasi 0.9025 (tanpa TTA) dan 0.9182 (dengan TTA 20 varian, F1-Macro 0.9277) dan berhasil diimplementasikan pada antarmuka web sederhana sebagai media demonstrasi klasifikasi penyakit daun apel secara langsung.
Keywords:
Deep Learning, Epoch, Klasifikasi Penyakit Daun, MobileNetV2##plugins.themes.default.displayStats.downloads##
References
[1] M. U. Ali, M. Khalid, M. Farrash, H. F. M. Lahza, A. Zafar, and S. H. Kim,
“AppleLeafNet: a lightweight and efficient deep learning framework for diagnosing apple
leaf diseases,” Front. Plant Sci., vol. 15, 2024, doi: 10.3389/fpls.2024.1502314.
[2] Y. Gao, Z. Cao, W. Cai, G. Gong, G. Zhou, and L. Li, “Apple Leaf Disease Identification
in Complex Background Based on BAM-Net,” Agronomy, vol. 13, no. 5, May 2023, doi:
10.3390/agronomy13051240.
[3] J. Wang, J. Jia, Y. Zhang, H. Wang, and S. Zhu, “RAAWC-UNet: an apple leaf and
disease segmentation method based on residual attention and atrous spatial pyramid
pooling improved UNet with weight compression loss,” Front. Plant Sci., vol. 15, 2024,
doi: 10.3389/fpls.2024.1305358.
[4] T. Li, L. Zhang, and J. Lin, “Precision agriculture with YOLO-Leaf: advanced methods
for detecting apple leaf diseases,” Front. Plant Sci., vol. 15, 2024, doi:
10.3389/fpls.2024.1452502.
[5] M. G. Somoal and A. R. Dzikrillah, “Komparasi MobileNETV2 dengan Kustomisasi
Transfer Learning dan Hyperparameter untuk Identifikasi Tumor Otak,” Jurnal
Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 1, pp. 229–240, Feb. 2025, doi:
10.25126/jtiik.2025129582.
[6] Y. Jiao et al., “LCAMNet: a lightweight model for apple leaf disease classification in
natural environments,” Front. Plant Sci., vol. 16, 2025, doi: 10.3389/fpls.2025.1626569.
[7] A. T. Rahman, A. Setyanto, and H. Al Fatta, “Klasifikasi Penyakit Daun Apel
Mengunakan Arsitektur CNN Dengan Transfer Learning,” 2024, doi:
10.31284/j.senopati.2024.v6i1.6574.
[8] P. C. Gajjar, H. N. Dalal, H. K. Patel, and N. K. Prajapati, “Modified Convolutional Block
Attention Mechanism-Based VGG16 for Apple Plant Leaf Disease Classification,” SSRGInternational Journal of Electronics and Communication Engineering, vol. 11, no. 8, pp.
62–71, Aug. 2024, doi: 10.14445/23488549/IJECE-V11I8P107.
[9] V. K. Vishnoi, K. Kumar, B. Kumar, S. Mohan, and A. A. Khan, “Detection of Apple
Plant Diseases Using Leaf Images Through Convolutional Neural Network,” IEEE
Access, vol. 11, pp. 6594–6609, 2023, doi: 10.1109/ACCESS.2022.3232917.
[10] T. Adriyanto, R. A. Ramadhani, R. Helilintar, and A. Ristyawan, “Classification of Dog
and Cat Images using the CNN Method,” ILKOM Jurnal Ilmiah, vol. 14, no. 3, pp. 203–
208, Dec. 2022, doi: 10.33096/ilkom.v14i3.1116.203-208.
[11] Z. Liu and X. Li, “An improved YOLOv5-based apple leaf disease detection method,”
Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-67924-8.
[12] J. Tao, X. Li, Y. He, and M. A. Islam, “CEFW-YOLO: A High-Precision Model for Plant
Leaf Disease Detection in Natural Environments,” Agriculture (Switzerland), vol. 15, no.
8, Apr. 2025, doi: 10.3390/agriculture15080833.
[13] B. Liu, H. Fan, Y. Zhang, J. Cai, and H. Cheng, “Deep learning architectures for
diagnosing the severity of apple frog-eye leaf spot disease in complex backgrounds,”
Front. Plant Sci., vol. 14, 2023, doi: 10.3389/fpls.2023.1289497.
[14] G. M. Guzu, S. D. Roșu Mareș, C. Moldovan, I. Zagrai, L. A. Zagrai, and M. I. Cordea,
“Results of some apple hybrid populations to the attack of scab and powdery mildew
under natural conditions,” Romanian journal of Horticulture, vol. 5, pp. 77–84, Dec.
2024, doi: 10.51258/RJH.2024.09.
[15] J. Jumadi, Y. Yupianti, and D. Sartika, “PENGOLAHAN CITRA DIGITAL UNTUK
IDENTIFIKASI OBJEK MENGGUNAKAN METODE HIERARCHICAL
AGGLOMERATIVE CLUSTERING,” JST (Jurnal Sains Dan Teknologi), vol. 10, no. 2,
2021, doi: 10.23887/jstundiksha.v10i2.33636.
[16] M. Riziq sirfatullah Alfarizi, M. Zidan Al-farish, M. Taufiqurrahman, G. Ardiansah, and
M. Elgar, “PENGGUNAAN PYTHON SEBAGAI BAHASA PEMROGRAMAN
UNTUK MACHINE LEARNING DAN DEEP LEARNING,” 2023, doi:
10.30997/karimahtauhid.v2i1.7518
[17] N. Wangsa Kencana and R. Umar, “Implementasi Transfer Learning Untuk Klasifikasi
Jenis Ras Ayam Menggunakan Arsitektur MobileNetV2,” JIP (Jurnal Informatika
Polinema), vol. 11, no. 2, 2025, doi: 10.33795/jip.v11i2.6469
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
