Analisis Hyperparameter Tuning MobileNetV2 dengan Metode Sequential Search dalam Sistem Klasifikasi Penyakit Daun Kentang
- Muhammad Ivan Khoirur Rizky Universitas Dian Nuswantoro, Semarang, Indonesia
- Akfi Rozada Universitas Dian Nuswantoro, Semarang, Indonesia
- Nurul Baroroh Universitas Dian Nuswantoro, Semarang, Indonesia
-
Ricardus Anggi Pramunendar
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
(*) Corresponding Author
Abstract
Indonesia’s national potato production faces significant threats from leaf diseases, while manual classification remains slow, subjective, and prone to error due to the high visual similarity across disease categories. This highlights the need for a precise and reliable automated classification system. However, many previous studies have not applied systematic hyperparameter optimization, leaving the capacity of deep learning architectures underutilized. Addressing this research gap, this study aims to enhance the performance of MobileNetV2 for potato leaf disease classification through a structured hyperparameter optimization process. A Sequential Search strategy validated through 3 fold Stratified Cross Validation is employed to obtain stable performance estimates. Four key hyperparameters are examined: learning rate from 0.001 to 0.009, dropout from 0.1 to 0.9, batch size from 8 to 192, and epochs from 10 to 100. The optimal configuration consists of a learning rate of 0.007, dropout of 0.2, batch size of 32, and 60 epochs, which enables MobileNetV2 to achieve an accuracy of 99 percent. Despite this strong performance, evaluation results reveal a minor limitation in the Young Blight class, where precision is slightly lower due to overlapping visual characteristics. These findings establish a new benchmark for potato leaf disease classification and provide a reproducible optimization framework for future studies. The study offers both methodological and practical contributions to the development of precise and efficient plant disease classification systems within the context of smart agriculture.
Downloads
References
B. Setiawan, P. Yudono, and S. Waluyo, “Evaluasi Tipe Pemanfaatan Lahan Pertanian dalam Upaya Mitigasi Kerusakan Lahan Di Desa Giritirta, Kecamatan Pejawaran, Kabupaten Banjarnegara,” Vegetalika, vol. 7, no. 2, doi: https://doi.org/10.22146/veg.35769.
A. Kurniawan, “Uji Kandungan Flavanoid Pada Ekstrak Kentang Secara Kualitatif Dan Kuantitatif,” BENZENA Pharm. Sci. J., vol. 1, no. 01, June 2022, doi: 10.31941/benzena.v1i01.2024.
S. Ghandi, I. Ma’ruf Nugroho, and Y. Raymond Ramadhan, “Penerapan Metode Convolutional Neural Network (CNN) dalam Aplikasi Pendeteksi Penyakit Daun Tanaman Kentang Berbasis Android,” JATI J. Mhs. Tek. Inform., vol. 8, no. 5, pp. 8701–8708, Sept. 2024, doi: 10.36040/jati.v8i5.10769.
Badan Pusat Statistik Indonesia, “Produksi Tanaman Sayuran, 2023,” Badan Pusat Statistik Indonesia. [Online]. Available: https://www.bps.go.id/id/statistics-table/2/NjEjMg==/produksi-%20tanaman-sayuran.html
S. Savary, L. Willocquet, S. J. Pethybridge, P. Esker, N. McRoberts, and A. Nelson, “The global burden of pathogens and pests on major food crops,” Nat. Ecol. Evol., vol. 3, no. 3, pp. 430–439, Feb. 2019, doi: 10.1038/s41559-018-0793-y.
S. Somantri, A. Fergina, A. Renjani, J. A. Malik, and A. Yasa, “Pemanfaatan AgriVision Sebagai Media Pembelajaran dan Deteksi Penyakit Tanaman untuk Petani Indonesia,” J. Pengabdi. Masy. Bangsa, vol. 3, no. 5, pp. 1941–1952, July 2025, doi: 10.59837/jpmba.v3i5.2597.
M. S. Pramono and A. P. Wibowo, “Penerapan Convolutional Neural Network untuk Identifikasi Penyakit pada Tanaman Padi dari Citra Daun Menggunakan Model ResNet-101,” Djtechno J. Teknol. Inf., vol. 5, no. 3, pp. 415–430, Dec. 2024, doi: 10.46576/djtechno.v5i3.5098.
S. Wahyuni, Indratin, Poniman, and A. N. Ardiwinata, “Identifikasi Cemaran Insektisida Profenofos dari Lahan Bawang Merah di Kabupaten Brebes,” J. Litbang Provinsi Jawa Teng., vol. 17, no. 2, pp. 207–215, Dec. 2019, doi: 10.36762/jurnaljateng.v17i2.800.
T. Alami, Y. Herdiyeni, W. A. Kusuma, B. Tjahjono, and I. Z. Siregar, “Kecerdasan Buatan untuk Monitoring Hama dan Penyakit pada Tanaman Eucalyptus: Systematic Literature Review,” vol. 10, no. 2, doi: https://doi.org/10.29244/jika.10.2.224-237.
F. Irhamna Rahman, Lukman, and Ikbal, “Klasifikasi Image Tinggi Tanaman Jagung dengan Menggunakan Algoritma Convolution Neural Network (CNN),” J. Inform. Dan Tek. Elektro Terap., vol. 12, no. 3S1, Oct. 2024, doi: 10.23960/jitet.v12i3S1.5348.
S. Sodikin, Tutik Khotimah, and Ahmad Jazuli, “Penerapan Transfer Learning Menggunakan Mobile NetV2 untuk Klasifikasi Penyakit Daun Jagung Berbasis Citra,” J. Ekon. Manaj. Sist. Inf., vol. 6, no. 6, pp. 4276–4282, July 2025, doi: 10.38035/jemsi.v6i6.5743.
R. Gunawan, F. Salim, A. I. Wahyudhy, A. Y. Wibowo, G. Yordan, and R. Fauzan, “Klasifikasi Penyakit Daun Kentang dengan Transfer Learning Menggunakan CNN optimalisasi Arsitektur MobileNetV2,” vol. 6, no. 2, 2025, doi: https://doi.org/10.37859/coscitech.v6i2.8599.
M. F. Wijayanto, D. Swanjaya, and R. Wulanningrum, “Penerapan MobileNet Architecture pada Identifikasi Foto Citra Makanan Indonesia,” Digit. Transform. Technol., vol. 4, no. 1, pp. 652–662, Aug. 2024, doi: 10.47709/digitech.v4i1.4449.
D. P. Prabowo et al., “Adaptive Inertia Weight Particle Swarm Optimization for Augmentation Selection in Coral Reef Classification with Convolutional Neural Networks,” JOIV Int. J. Inform. Vis., vol. 9, no. 1, p. 216, Jan. 2025, doi: 10.62527/joiv.9.1.2726.
Joshua Agung Nurcahyo and Theopilus Bayu Sasongko, “Hyperparameter Tuning Algoritma Supervised Learning untuk Klasifikasi Keluarga Penerima Bantuan Pangan Beras,” Indones. J. Comput. Sci., vol. 12, no. 3, July 2023, doi: 10.33022/ijcs.v12i3.3254.
F. Amaludin, M. I. Zulfa, and H. Siswantoro, “Pengaruh Hyperparameter Tuning pada Kinerja MobileNetV2 dengan Transfer Learning untuk Deteksi Penyakit Kuli,” J. SINTA Sist. Inf. Dan Teknol. Komputasi, vol. 2, no. 2, May 2025, doi: 10.61124/sinta.v2i2.43.
R. Fadilatul Fajriyah and Y. Sulistyo Nugroho, “Analisis Tren Penelitian Hyperparameter Tuning dalam Software Engineering melalui Systematic Literature Review dan Bibliometric Analysis,” J. Pendidik. Dan Teknol. Indones., vol. 5, no. 8, pp. 2278–2294, Aug. 2025, doi: 10.52436/1.jpti.817.
Afis Julianto, Andi Sunyoto, and Ferry Wahyu Wibowo, “Optimasi Hyperparameter Convolutional Neural Network untuk Klasifikasi Penyakit Tanaman Padi,” Tek. Teknol. Inf. Dan Multimed., vol. 3, no. 2, pp. 98–105, Dec. 2022, doi: 10.46764/teknimedia.v3i2.77.
W. Nugraha and A. Sasongko, “Hyperparameter Tuning on Classification Algorithm with Grid Search,” SISTEMASI, vol. 11, no. 2, p. 391, May 2022, doi: 10.32520/stmsi.v11i2.1750.
N. Gill, P. Hall, K. Montgomery, and N. Schmidt, “A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing,” Information, vol. 11, no. 3, p. 137, Feb. 2020, doi: 10.3390/info11030137.
A. Soni, C. Arora, R. Kaushik, and V. Upadhyay, “Evaluating the Impact of Data Quality on Machine Learning Model Performance,” J. Nonlinear Anal. Optim., vol. 14, no. 01, pp. 13–18, 2023, doi: 10.36893/JNAO.2023.V14I1.0013-0018.
Rachmat Santoso, “Augmentasi Data pada Prasasti Logam untuk Deteksi Aksara Kawi,” J. FASILKOM, vol. 14, no. 1, pp. 234–241, Apr. 2024, doi: 10.37859/jf.v14i1.6952.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” 2014, arXiv. doi: 10.48550/ARXIV.1412.6980.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Hyperparameter Tuning MobileNetV2 dengan Metode Sequential Search dalam Sistem Klasifikasi Penyakit Daun Kentang
Pages: 1951-1962
Copyright (c) 2025 Muhammad Ivan Khoirur Rizky, Akfi Rozada, Nurul Baroroh, Ricardus Anggi Pramunendar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
