Bayesian Optimized Pretrained CNNs for Mango Leaf Disease Classification: A Comparative Study

Sri Rahayu; Sayyid Faruk Romdoni

doi:10.52436/1.jutif.2025.6.5.4967

Authors

Sri Rahayu Informatics, Institut Teknologi Garut, Indonesia
Sayyid Faruk Romdoni Informatics, Institut Teknologi Garut, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.5.4967

Keywords:

Bayesian Optimization, Convolutional Neural Networks, Deep Learning, Mango Leaf Disease, MobileNetV3, Transfer Learning

Abstract

Mango leaf diseases pose a major threat to crop productivity, causing significant economic losses for farmers. Accurate and early detection is essential, yet manual diagnosis remains subjective and inefficient. This study aims to evaluate and compare the performance of five pretrained Convolutional Neural Network (CNN) architectures—DenseNet121, ResNet50V2, MobileNetV3 Small, MobileNetV3 Large, and InceptionV3—by systematically optimizing their hyperparameters to identify the most effective model for mango leaf disease classification. The public MangoLeafBD dataset, containing 4,000 images from eight balanced classes, was used. Bayesian Optimization was applied to fine-tune each model, and their performances were assessed before and after optimization. Results show that optimization substantially improved all models, with MobileNetV3 Large achieving the highest accuracy of 100% on the test set, followed by DenseNet121 (99.75%), ResNet50V2 (99.63%), MobileNetV3 Small (99.50%), and InceptionV3 (98.50%). The findings highlight that a well-tuned lightweight model can outperform more complex architectures, offering a practical and efficient solution for developing mobile-based diagnostic tools to support precision agriculture in resource-constrained settings.

Downloads

Download data is not yet available.

References

Badan Pusat Statistik Indonesia, “Produksi Buah–Buahan dan Sayuran Tahunan Menurut Jenis Tanaman.” Accessed: Feb. 21, 2025. [Online]. Available: https://www.bps.go.id/id/statistics-table/3/WXpSVU5uUTBOSEl5WVhGQmVESTVSVnBSVlhWeVVUMDkjMw==/produksi-buah-buahan-dan-sayuran-tahunan-menurut-jenis-tanaman.html?year=2023

A. M. Kiloes, D. Joyce, and A. Abdul Aziz, “Exploring the Challenges and Opportunities of Mango Export from Indonesia: Insights from Stakeholder Interviews,” The Qualitative Report, vol. 29, no. 3, pp. 811–830, Mar. 2024, doi: 10.46743/2160-3715/2024.6343.

A. M. Kiloes, Y. N. Muflikh, D. Joyce, and A. Abdul Aziz, “Understanding the complexity of the Indonesian fresh mango industry in delivering quality to markets: A systems thinking approach,” Food Policy, vol. 118, p. 102497, Jul. 2023, doi: 10.1016/j.foodpol.2023.102497.

G. V. Benatar, A. Wibowo, and Suryanti, “First report of Colletotrichum asianum associated with mango fruit anthracnose in Indonesia,” Crop Protection, vol. 141, p. 105432, Mar. 2021, doi: 10.1016/j.cropro.2020.105432.

S. T. Raza et al., “A Review on White Mango Scale Biology, Ecology, Distribution and Management,” Agriculture, vol. 13, no. 9, p. 1770, Sep. 2023, doi: 10.3390/agriculture13091770.

S. Solikin, “Deteksi Penyakit Pada Tanaman Mangga Dengan Citra Digital : Tinjauan Literatur Sistematis (SLR),” Bina Insani Ict Journal, vol. 7, no. 1, p. 63, 2020, doi: 10.51211/biict.v7i1.1336.

L. Li, S. Zhang, and B. Wang, “Plant Disease Detection and Classification by Deep Learning—A Review,” IEEE Access, vol. 9, no. Ccv, pp. 56683–56698, 2021, doi: 10.1109/ACCESS.2021.3069646.

M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” Frontiers in Plant Science, vol. 14, no. March, pp. 1–22, Mar. 2023, doi: 10.3389/fpls.2023.1158933.

S. Hemalatha and J. J. B. Jayachandran, “A Multitask Learning-Based Vision Transformer for Plant Disease Localization and Classification,” International Journal of Computational Intelligence Systems, vol. 17, no. 1, p. 188, Jul. 2024, doi: 10.1007/s44196-024-00597-3.

S. M. Hassan, M. Jasinski, Z. Leonowicz, E. Jasinska, and A. K. Maji, “Plant Disease Identification Using Shallow Convolutional Neural Network,” Agronomy, vol. 11, no. 12, p. 2388, Nov. 2021, doi: 10.3390/agronomy11122388.

S. Sulaiman, N. Nurhayati, and J. N. Sitompul, “SISTEM PAKAR MENDIAGNOSA PENYAKIT TANAMAN MANGGA ARUMANIS DENGAN METODE CERTAINTY FACTOR,” JURNAL TEKNISI, vol. 1, no. 2, p. 61, Aug. 2021, doi: 10.54314/teknisi.v1i2.660.

G. V. Benatar, Y. Nurhayati, and N. Febryani, “Identifikasi Colletotrichum asianum Penyebab Antraknosa Mangga Kultivar Golek di Indramayu,” Media Pertanian, vol. 8, no. 1, pp. 1–13, May 2023, doi: 10.37058/mp.v8i1.6900.

A. I. Tanzil, I. Sucipto, and W. Muhlison, “Inventory of Pest and Disease in Mango Plants (Mangifera indica),” Jurnal Online Pertanian Tropik, vol. 9, no. 2, pp. 098–105, 2022, doi: 10.32734/jopt.v9i2.8972.

I. W. Susila et al., “Abundance, distribution mapping and DNA barcoding of Procontarinia robusta (Diptera: Cecidomyiidae), a mango gall midge in Bali, Indonesia,” Biodiversitas Journal of Biological Diversity, vol. 23, no. 12, pp. 6428–6436, Jan. 2023, doi: 10.13057/biodiv/d231241.

D. Faye, I. Diop, and D. Dione, “Mango Diseases Classification Solutions Using Machine Learning or Deep Learning: A Review,” Journal of Computer and Communications, vol. 10, no. 12, pp. 16–28, 2022, doi: 10.4236/jcc.2022.1012002.

M. Jelali, “Deep learning networks-based tomato disease and pest detection: a first review of research studies using real field datasets,” Frontiers in Plant Science, vol. 15, no. October, pp. 1–20, Oct. 2024, doi: 10.3389/fpls.2024.1493322.

H. Nugroho, J. X. Chew, S. Eswaran, and F. S. Tay, “Resource-optimized cnns for real-time rice disease detection with ARM cortex-M microprocessors,” Plant Methods, vol. 20, no. 1, p. 159, Oct. 2024, doi: 10.1186/s13007-024-01280-6.

B. U. Mahmud, A. Al Mamun, M. J. Hossen, G. Y. Hong, and B. Jahan, “Light-Weight Deep Learning Model for Accelerating the Classification of Mango-Leaf Disease,” Emerging Science Journal, vol. 8, no. 1, pp. 28–42, Feb. 2024, doi: 10.28991/ESJ-2024-08-01-03.

P. D. Rinanda, D. N. Aini, T. A. Pertiwi, S. Suryani, and A. J. Prakash, “Implementation of Convolutional Neural Network (CNN) for Image Classification of Leaf Disease In Mango Plants Using Deep Learning Approach,” Public Research Journal of Engineering, Data Technology and Computer Science, vol. 1, no. 2, pp. 56–61, Feb. 2024, doi: 10.57152/predatecs.v1i2.872.

M. A. Likorawung and D. M. Wonohadidjojo, “Implementation of DenseNet Architecture With Transfer Learning to Classify Mango Leaf Diseases,” vol. 06, no. 02, pp. 78–86, 2024, doi: 10.52985/insyst.v6i2.401.

V. K. Pratap and N. S. Kumar, “Deep Learning based Mango Leaf Disease Detection for Classifying and Evaluating Mango Leaf Diseases,” Fusion: Practice and Applications, vol. 15, no. 2, pp. 261–277, 2024, doi: 10.54216/FPA.150222.

C. P. Vijay and K. Pushpalatha, “DV-PSO-Net: A novel deep mutual learning model with Heuristic search using Particle Swarm optimization for Mango leaf disease detection,” Journal of Integrated Science and Technology, vol. 12, no. 5, p. 804, May 2024, doi: 10.62110/sciencein.jist.2024.v12.804.

M. Wojciuk, Z. Swiderska-Chadaj, K. Siwek, and A. Gertych, “Improving classification accuracy of fine-tuned CNN models: Impact of hyperparameter optimization,” Heliyon, vol. 10, no. 5, p. e26586, Mar. 2024, doi: 10.1016/j.heliyon.2024.e26586.

B. Khan et al., “Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification,” Scientific Reports 2024 14:1, vol. 14, no. 1, pp. 1–30, 2024, doi: 10.1038/s41598-024-72237-x.

Q. A. Hidayaturrohman and E. Hanada, “A Comparative Analysis of Hyper-Parameter Optimization Methods for Predicting Heart Failure Outcomes,” Applied Sciences, vol. 15, no. 6, p. 3393, Mar. 2025, doi: 10.3390/app15063393.

S. I. Ahmed et al., “MangoLeafBD: A comprehensive image dataset to classify diseased and healthy mango leaves,” Data in Brief, vol. 47, p. 108941, Apr. 2023, doi: 10.1016/j.dib.2023.108941.

I. K. Seneng, P. D. W. Ayu, and R. R. Huizen, “Comparative Analysis of Augmentation and Filtering Methods in VGG19 and DenseNet121 for Breast Cancer Classification,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 3, pp. 1131–1146, 2025, doi: 10.52436/1.jutif.2025.6.3.4397.

T. S. Arulananth, S. W. Prakash, R. K. Ayyasamy, V. P. Kavitha, P. G. Kuppusamy, and P. Chinnasamy, “Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model,” IEEE Access, vol. 12, no. March, pp. 35716–35727, 2024, doi: 10.1109/ACCESS.2024.3371151.

H. I. Fitriasari and M. Rizkinia, “Improvement of Xception-ResNet50V2 Concatenation for COVID-19 Detection on Chest X-Ray Images,” in 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), IEEE, Apr. 2021, pp. 343–347. doi: 10.1109/EIConCIT50028.2021.9431916.

D. Hindarto, “Use ResNet50V2 Deep Learning Model to Classify Five Animal Species,” Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi), vol. 7, no. 4, pp. 758–768, Dec. 2023, doi: 10.35870/jtik.v7i4.1845.

J. Zhu, C. Zhang, and C. Zhang, “Papaver somniferum and Papaver rhoeas Classification Based on Visible Capsule Images Using a Modified MobileNetV3-Small Network with Transfer Learning,” Entropy, vol. 25, no. 3, p. 447, Mar. 2023, doi: 10.3390/e25030447.

A. R. Muslikh, D. R. I. M. Setiadi, and A. A. Ojugo, “RICE DISEASE RECOGNITION USING TRANSFER LEARNING XCEPTION CONVOLUTIONAL NEURAL NETWORK,” Jurnal Teknik Informatika (Jutif), vol. 4, no. 6, pp. 1535–1540, Dec. 2023, doi: 10.52436/1.jutif.2023.4.6.1529.

L. Zhao and L. Wang, “A new lightweight network based on MobileNetV3,” KSII Transactions on Internet and Information Systems, vol. 16, no. 1, pp. 1–15, Jan. 2022, doi: 10.3837/tiis.2022.01.001.

Kaka Kamaludin, Woro Isti Rahayu, and M. Y. Helmi Setywan, “TRANSFER LEARNING TO PREDICT GENRE BASED ON ANIME POSTERS,” Jurnal Teknik Informatika (Jutif), vol. 4, no. 5, pp. 1041–1052, Oct. 2023, doi: 10.52436/1.jutif.2023.4.5.860.

T. Hidayat, I. A. Astuti, A. Yaqin, A. P. Tjilen, and T. Arifianto, “Grouping of Image Patterns Using Inceptionv3 For Face Shape Classification,” JOIV : International Journal on Informatics Visualization, vol. 7, no. 4, pp. 2336–2343, Dec. 2023, doi: 10.30630/joiv.7.4.1743.

Y. Motoyama, R. Tamura, K. Yoshimi, K. Terayama, T. Ueno, and K. Tsuda, “Bayesian optimization package: PHYSBO,” Computer Physics Communications, vol. 278, p. 108405, Sep. 2022, doi: 10.1016/j.cpc.2022.108405.

A. Candelieri, “A Gentle Introduction to Bayesian Optimization,” in 2021 Winter Simulation Conference (WSC), IEEE, Dec. 2021, pp. 1–16. doi: 10.1109/WSC52266.2021.9715413.

M. A. B. Bhuiyan, H. M. Abdullah, S. E. Arman, S. Saminur Rahman, and K. Al Mahmud, “BananaSqueezeNet: A very fast, lightweight convolutional neural network for the diagnosis of three prominent banana leaf diseases,” Smart Agricultural Technology, vol. 4, no. December 2022, p. 100214, Aug. 2023, doi: 10.1016/j.atech.2023.100214.