Article Sidebar

Submitted
October 11, 2025
Accepted
January 7, 2026
Published
January 16, 2026
Download
PDF
Statistic
Read Counter : 0 Download : 1

Main Article Content

Abstract

Banana leaf diseases significantly reduce crop productivity, yet automated detection systems based on deep learning often rely on limited datasets, where training stability and generalization become critical challenges. Although Convolutional Neural Networks (CNNs) have been widely applied for plant disease classification, systematic comparisons of optimization algorithms under small dataset conditions remain limited, particularly for banana leaf disease identification. This study addresses this gap by comparing the performance of Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD) optimizers within a transfer learning–based CNN framework. Six pre-trained architectures VGG16, VGG19, ResNet50, DenseNet121, MobileNet, and NASNetMobile were evaluated using 1,652 annotated banana leaf images classified into Sigatoka, Cordana, Pestalotiopsis, and healthy leaves. Both optimizers were trained under identical experimental settings to ensure a fair comparison. Experimental results show that VGG19 achieved the highest accuracy, reaching 85% with Adam and 83% with SGD, while lightweight architecture exhibited lower performance due to underfitting. The findings demonstrate that optimizer selection plays a crucial role in improving CNN performance for banana leaf disease classification, especially when data availability is limited.

Keywords

Banana leaf disease convolutional neural network transfer learning Adam optimizer SGD optimizer

Article Details

License

Copyright (c) 2026 Zaid Romegar Mair, Rudi Heriansyah, La Ode Hasnuddin S. Sagala

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Mair, Z. R., Heriansyah, R., & Sagala, L. O. H. S. (2026). Performance Comparison of Adam and SGD Optimizers in Transfer Learning Based CNN for Banana Leaf Disease Classification. Jurnal Sains, Nalar, Dan Aplikasi Teknologi Informasi, 5(1), 8–15. https://doi.org/10.20885/snati.v5.i1.43901
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX

References

  1. M. A. B. Bhuiyan, H. M. Abdullah, S. E. Arman, S. S. Rahman, dan K. A. Mahmud, “MusaSqueezeNet: A very fast, lightweight convolutional neural network for the diagnosis of three prominent Musa leaf diseases”, Smart Agricultural Technology, vol. 4, p. 100214, 2022.
  2. P. Hari dan M. P. Singh, “A lightweight convolutional neural network for disease detection of fruit leaves”, Neural Computing and Applications, vol. 35, no. 20, hlm. 14855–14866, 2023.
  3. N. B. Raja dan P. S. Rajendran, “A novel fuzzy-based modified GAN and Faster RCNN for classification of Musa leaf disease”, Journal of the Institution of Engineers (India): Series A, vol. 104, no. 3, hlm. 529–540, 2023.
  4. M. G. Selvaraj, A. Vergara, H. Ruiz, N. Safari, S. Elayabalan, W. Ocimati, dan G. Blomme, “Detection of banana plants and major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin”, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 156, hlm. 1–13, 2019.
  5. Z. R. Mair et al., “CNN Analysis on Handwriting Patterns and Its Relationship to Personality”, Journal of Applied Intelligent Systems, vol. 14, no. 2, hlm. 98–107, 2023.
  6. A. Arman, M. Bhuiyan, H. Abdullah, dan K. Mahmud, “MusaLSD: A dataset for classification of Musa leaf spot disease using deep learning”, Data in Brief, vol. 47, p. 108904, 2023.
  7. S. Tammina, “Transfer learning using VGG-16 with deep convolutional neural network for classifying images”, International Journal of Scientific and Research Publications, vol. 9, no. 10, hlm. 143–150, 2019.
  8. F. Edel dan A. Kapustin, “Performance of MobileNet for lightweight image classification tasks”, Journal of Computer Vision Applications, vol. 32, no. 1, hlm. 77–88, 2022.
  9. A. Allabun, “ECG signal classification and arrhythmia analysis using deep learning”, Biomedical Signal Processing and Control, vol. 89, p. 105566, 2024.
  10. N. Khalid dan A. R. Romle, “Herbal plant image classification using transfer learning”, Procedia Computer Science, vol. 233, hlm. 456–463, 2024.
  11. M. S. Islam, U. Habiba, M. A. Baten, N. Amin, I. Salehin, dan T. T. Jidney, “Improve CNN Model Agro-Crop Leaf Disease Identification Based on Transfer Learning”, dalam: Advanced Communication and Intelligent Systems, Communications in Computer and Information Science, vol. 1749, R. N. Shaw et al. (eds), Springer, Cham, hlm. --, 2023.
  12. A. Anushya, S. Begum, S. Shiwani, dan A. Shrivastava, “Utilizing Transfer Learning Approach in Agriculture 4.0 for Banana Leaf Disease Identification”, American Journal of Pediatric Medicine and Health Sciences, 2024.
  13. I. Rahmana Syihad, M. Rizal, Z. Sari, dan Y. Azhar, “CNN Method to Identify the Banana Plant Diseases based on Banana Leaf Images by Giving Models of ResNet50 and VGG-19”, Jurnal RESTI, 2021.
  14. A. Helmawati dan E. Utami, “Utilization of the Convolutional Neural Network Method for Detecting Banana Leaf Disease”, Jurnal RESTI, 2022.
  15. R. Ridhovan, A. Suharso, dan C. Rozikin, “Disease Detection in Banana Leaf Plants using DenseNet and Inception Method”, Jurnal RESTI, 2022.
  16. S. Chen, J. Liu, P. Wang, C. Xu, S. Cai, dan J. Chu, “Accelerated optimization in deep learning with a proportional-integral-derivative controller,” Nature Communications, vol. 15, Art. no. 10263, Nov. 2024.
  17. J. Yang dan Q. Long, “A modification of adaptive moment estimation (Adam) for machine learning,” Journal of Industrial and Management Optimization, vol. 20, no. 7, pp. 2516–2540, 2024.
  18. D. Mienye, “A comprehensive review of deep learning: architectures, recent advances, and applications,” Information, vol. 15, no. 12, p. 755, 2024.
  19. P. Sunitha, B. Uma, A. G. Kiran, S. Channakeshava, dan C. S. Suresh Babu, “A Convolution Neural Network with Skip Connections (CNNSC) approach for detecting micronutrients boron and iron deficiency in banana leaves,” Journal of Umm Al-Qura University for Engineering and Architecture, vol. 15, pp. 467–485, 2024.
  20. N. Jiménez, S. Orellana, B. Mazon-Olivo, W. Rivas-Asanza, dan I. Ramírez-Morales, “Detection of leaf diseases in banana crops using deep learning techniques,” AI, vol. 6, no. 3, p. 61, 2025.
  21. N. R. Rajalakshmi, “Early Detection of Banana Leaf Disease Using Novel Deep Convolutional Neural Network,” Journal of Data Science and Information Systems (JDSIS), 2024.
  22. A. Khan, A. Sohail, U. Zahoora, and A. S. Qureshi, “A survey of the recent architectures of deep convolutional neural networks,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5455–5516, 2020.
  23. A. Shrestha and A. Mahmood, “Review of deep learning algorithms and architectures,” IEEE Access, vol. 7, pp. 53040–53065, 2019.
  24. Mair Z.R., Irfani M.H. Permainan INGBAS (Gunting, Batu, Kertas) Menggunakan Arsitektur Convolutional Neural Network. Jurnal Teknik Informatika dan Sistem Informasi, 2023.
  25. Pratama, M. D., Gustriansyah, R., & Purnamasari, E.. Klasifikasi penyakit daun pisang menggunakan Convolutional Neural Network (CNN). Jurnal Teknologi Terpadu, 10(1), 1–6. ISSN 2477-0043,2024
  26. Mair Z.R., Harjoko A., Gustriansyah R., Cahyani S., Heriansyah R., Permatasari I., Irfani M.H. An Enhanced Deep Learning Framework for Diabetic Retinopathy Classification Using Multiple Convolutional Neural Network Architectures. International Journal of Advanced Computer Science and Applications, 2025.
  27. Md. A. B. Bhuiyan, S. M. N. Islam, Md. A. I. Bukhari, Md. A. Kader, Md. Z. H. Chowdhury, M. Z. Alam, H. M. Abdullah, and F. Jenny, “First report of Pestalotiopsis microspora causing leaf blight of musa in Bangladesh,” Plant Dis., vol. 106, no. 5, p. 1518, 2022, doi: 10.1094/pdis-05-21-1120-pdn.
  28. J. Andrew, J. Eunice, D. E. Popescu, M. K. Chowdary, and J. Hemanth, “Deep Learning-Based Leaf Disease Detection in Crops Using Images for Agricultural Applications,” Agronomy, vol. 12, no. 10, p. 2395, 2022, doi: 10.3390/agronomy12102395.
  29. K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, pp. 311–318, Sep. 2017, doi: 10.1016/j.compag.2018.01.009.
  30. A. Ramcharan, P. McCloskey, K. Baranowski, N. Mbilinyi, L. Mrisho, M. Ndalahwa, J. Legg, and D. P. Hughes, “A mobile-based deep learning model for cassava disease diagnosis,” Front. Plant Sci., p. 272, 2019.
  31. J. Kamdar, M. Jasani, J. Jasani, J. Praba, and J. J. George, “Artificial intelligence for plant disease detection: past, present, and future,” in Internet of Things and Machine Learning in Agriculture, De Gruyter, 2021, pp. 223–238.