Improving the Performance of Convolutional Neural Networks (CNN) in Identification of Agricultural Plant Diseases

Dedi Setiadi; Fido Rizki

doi:10.32664/smatika.v16i02.2372

Authors

Dedi Setiadi Institut Teknologi Pagar Alam
Fido Rizki Universitas Bina Insan

DOI:

https://doi.org/10.32664/smatika.v16i02.2372

Keywords:

CNN, Coffee, Diseases, Inception V3

Abstract

This study aims to improve the performance of the Convolutional Neural Network (CNN) algorithm in detecting coffee leaf diseases using the Inception V3 architecture. The main challenge of this classification is the subtle visual similarity in color, texture, and symptom patterns between diseases. To overcome this, Inception V3 is implemented because of its superiority in multi-scale feature extraction through convolution factorization which reduces parameters while increasing accuracy. The dataset used consists of 1,120 images, evenly distributed into four classes (three types of diseases and one healthy class, each with 280 images), with a training, validation, and test data split ratio of 896:112:112. As a comparison, a conventional basic CNN architecture consisting of 3 convolution layers (3 X 3, stride 1), 3 max-pooling, and 1 dense layer, trained with the same hyperparameters (Adam optimizer, learning rate 0.001, batch size 32) is used. The experimental results show a significant performance improvement; Model accuracy increased from 74.4% on a standard CNN to 97.0% after integrating Inception V3. The scientific contribution of this research lies in mapping overlapping visual characteristics of coffee diseases through multi-scale feature optimization, which demonstrates that computational efficiency can go hand in hand with accuracy improvements on complex agricultural image datasets. These findings confirm that the Inception V3 architecture provides a robust and efficient solution for automating plant disease diagnosis in the field.

References

[1] A. Morchid, R. El Alami, A. A. Raezah, and Y. Sabbar, “Applications of Internet of Things (IoT) and Sensors Technology to Increase Food Security and Agricultural Sustainability: Benefits and Challenges,” Ain Shams Eng. J., vol. 15, no. 3, p. 102509, 2024, doi: 10.1016/j.asej.2023.102509.

[2] A. Khaidar, “Integrasi Teknologi Internet Of Things Dalam Smart Farming Sebagai Strategi Digitalisasi Pertanian Menuju Era Industri 4.0,” Improve, vol. 17, no. 2, pp. 34–40, 2025.

[3] A. Hussain, T. Senapati, S. Bibi, K. Ullah, L. Jin, and S. Moslem, “Sustainable Agriculture Method Selection Using Spherical Fuzzy Bonferroni Mean-Based Approach,” Franklin Open, p. 100558, 2026, doi: 10.1016/j.fraope.2026.100558.

[4] K. L. Himayanta and D. F. Wardhani, “Prediksi Hasil Panen Padi Dengan Machine Learning,” Inov. Pembang. J. Kelitbangan, vol. 13, no. 1, 2025.

[5] S. Matarru, G. A. N. Pongdatu, and J. Rusman, “Klasifikasi Penyakit pada Tanaman Kopi Arabika Menggunakan Metode K-Nearest Neighbor (KNN) Berbasis Citra,” Indones. J. Comput. Sci., vol. 12, no. 2, 2023, doi: 10.33022/ijcs.v12i2.3172.

[6] A. I. Saputra, I. Weni, and U. Khaira, “Implementasi Metode Convolutional Neural Network Untuk Deteksi Penyakit Pada Tanaman Kopi Arabika Melalui Citra Daun Berbasis Android,” Decod. J. Pendidik. Teknol. Inf., vol. 4, no. 1, pp. 41–51, 2023, doi: 10.51454/decode.v4i1.231.

[7] Y. P. Putra, A. Susanto, and W. Novrian, “Penerapan Jaringan Syaraf Konvolusional Untuk Deteksi Penyakit Tanaman Kopi Berdasarkan Citra Daun,” J. Pustaka AI, vol. 5, no. 3, pp. 507–513, 2025, doi: 10.55382/jurnalpustakaai.v5i3.1123.

[8] G. A. de Melo and others, “Performance Management in Coffee Growing: A Multivariate Analysis Applied to Coffee Production in the Main Brazilian Regions,” SSRN Electron. J., 2023.

[9] M. H. Alhazmi, “An Explainable AI Framework (XAI-CoffeeNet) with Deep Learning and Vision Transformers for Saudi Coffee Disease Recognition and Severity Assessment,” Smart Agric. Technol., vol. 14, p. 102259, 2026, doi: 10.1016/j.atech.2026.102259.

[10] N. P. D. A. S. Dewi, I. G. Hendrayana, and I. W. A. W. K. Putra, “Optimasi Hyperparameter Convolutional Neural Network Dengan Arsitektur Mobilenet Pada Klasifikasi Penyakit Daun Jagung,” J. Mnemon., vol. 8, no. 1, pp. 92–99, 2025, doi: 10.36040/mnemonic.v8i1.11744.

[11] D. Setiadi and Y. I. Mukti, “An Integrated Framework for Rice Disease Detection and Smart Irrigation Using EfficientNet-B0 and IoT,” Ing. des Syst. d’Information, vol. 30, no. 9, 2025, doi: 10.18280/isi.300907.

[12] S. Irannejad and H. Bagheri, “Gaussian Mixture Integration of CNN and Transformer Models for Forest Biomass Estimation: A Multi-Sensor Fusion Approach with Uncertainty Quantification,” Smart Agric. Technol., p. 102241, 2026, doi: 10.1016/j.atech.2026.102241.

[13] M. A. Mohammed, Y. S. Alsahafi, R. Salama, A. M. Elshewey, and K. M. Hosny, “Explainable Hybrid CNN Model Using DenseNet121 and EfficientNetB0 for Brain Tumor Detection and Classification,” Intell. Syst. with Appl., p. 200670, 2026, doi: 10.1016/j.iswa.2026.200670.

[14] Y. Findawati, “Implementation Of Convolutional Neural Network (CNN) To Detect Hate Speech And Emotions On Twitter.”

[15] B. Baso and N. Huda, “Hybrid Algoritma Convolutional Neural Network dengan Support Vector Machine untuk Klasifikasi Jenis Tenun Timor,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 6, pp. 1233–1242, 2025.

[16] E. Firasari and F. L. D. Cahyanti, “Implementation of Deep Learning for Potato Leaf Disease Detection Using the InceptionResNetV2 Architecture,” Indones. J. Comput. Sci., vol. 4, no. 1, pp. 76–81, 2025, doi: 10.31294/n09m6677.

[17] A. T. Adiana, J. Jumadi, and E. Nurlatifah, “Klasifikasi Penyakit Pada Daun Padi Menggunakan Model Hybrid CNN-SVM,” SMATIKA, vol. 15, no. 2, pp. 258–267, 2025, doi: 10.32664/smatika.v15i02.1548.

[18] A. Iqbal, K. Iqbal, Y. A. Shah, F. Ullah, J. Khan, and S. Yaqoob, “Multi-filter Stacking in Inception V3 for Enhanced Alzheimer’s Severity Classification,” Neuroscience, 2025, doi: 10.1016/j.neuroscience.2025.08.049.

[19] G. Meena, K. K. Mohbey, and S. Kumar, “Sentiment Analysis on Images Using Convolutional Neural Networks Based Inception-V3 Transfer Learning Approach,” Int. J. Inf. Manag. Data Insights, vol. 3, no. 1, p. 100174, 2023, doi: 10.1016/j.jjimei.2023.100174.

[20] M. W. Sardjono, V. Ramadhan, M. Cahyanti, and E. R. Swedia, “Klasifikasi Bentuk Bingkai (Frame) Kacamata Menggunakan CNN dengan Arsitektur Inception V3 dan Augmented Reality Berbasis Android,” J. Syst. Comput. Eng., vol. 5, no. 2, pp. 204–218, 2024, doi: 10.61628/jsce.v5i2.1292.

[21] U. Ungkawa and G. Al Hakim, “Klasifikasi Warna pada Kematangan Buah Kopi Kuning menggunakan Metode CNN Inception V3,” ELKOMIKA, vol. 11, no. 3, p. 731, 2023, doi: 10.26760/elkomika.v11i3.731.

[22] I. P. Agus, K. Hidjah, N. Sulistianingsih, G. Hendro, and S. Syahrir, “Implementasi Arsitektur Deep Convolutional Neural Network (CNN) dengan Transfer Learning untuk Klasifikasi Penyakit Kulit,” J. Teknol. Inf. dan Multimed., vol. 7, no. 3, pp. 461–477, 2025.

[23] K. Z. Maulana and A. Susanto, “Implementasi Arsitektur CNN Inception V3 untuk Identifikasi Spesies Burung Endemik di Indonesia,” J. Pustaka Robot Sister, vol. 2, no. 1, pp. 22–27, 2024, doi: 10.55382/jurnalpustakarobotsister.v2i1.775.

[24] R. P. Lailatul’Ismi and S. R. Nudin, “Deteksi Penyakit pada Tanaman Tomat Menggunakan Model Inception V3 Berbasis Mobile,” J. Informatics Comput. Sci., vol. 7, no. 2, pp. 520–524, 2025.

[25] R. Gunawan, R. Fathurrahman, A. I. S. Widyaningrum, F. Issandra, M. A. Abdurachman, and Y. E. Putra, “Pendekatan Transfer Learning untuk Klasifikasi Penyakit Mata Menggunakan Citra dengan CNN InceptionV3,” J. Comput. Sci. Inf. Technol., vol. 6, no. 1, pp. 60–67, 2025, doi: 10.37859/coscitech.v6i1.8509.

[26] A. B. Dash, S. Dash, S. Padhy, N. Kumar, G. K. Pati, and K. Uthansingh, “Leveraging Inception-V3 CNN Model for Efficient Image Classification,” in Intelligent Computing and Communication Techniques, CRC Press, 2025, pp. 341–348. doi: 10.1201/9781003635680-52.

[27] C. V Kwatra, H. Kaur, M. Mangla, A. Singh, S. N. Tambe, and S. Potharaju, “Early Detection of Gynecological Malignancies Using Ensemble Deep Learning Models: ResNet50 and Inception V3,” Informatics Med. Unlocked, vol. 53, p. 101620, 2025, doi: 10.1016/j.imu.2025.101620.

[28] M. M. Baig and others, “Enhancing Crop Disease Identification and Management Using Inception V3 Transfer Learning,” in 2025 IEEE 1st International Conference on Recent Trends in Computing and Smart Mobility (RCSM), IEEE, 2025, pp. 1–5. doi: 10.1109/RCSM67767.2025.11507538.

[29] M. Ahmed, N. Afreen, M. Ahmed, M. Sameer, and J. Ahamed, “An Inception V3 Approach for Malware Classification Using Machine Learning and Transfer Learning,” Int. J. Intell. Networks, vol. 4, pp. 11–18, 2023, doi: 10.1016/j.ijin.2022.11.005.

[30] M. A. Setiawan, R. Dijaya, C. Taurusta, and A. S. Fitrani, “Mountain Climbing Safety Induction for Beginners Using Augmented Reality,” SMATIKA J., vol. 16, no. 1, pp. 45–56, 2026, doi: 10.32664/smatika.v16i01.2215.

[31] B. Mehta, S. Bharany, D. H. Elkamchouchi, A. U. Rehman, R. Singh, and S. H. Adem, “EffResViT-SE FusionNet: A Hybrid Deep Learning Framework for Accurate Classification of Coffee Leaf Diseases,” Food Sci. Nutr., vol. 13, no. 12, p. e71311, 2025, doi: 10.1002/fsn3.71311.

[32] D. Novtahaning, H. A. Shah, and J.-M. Kang, “Deep Learning Ensemble-Based Automated and High-Performing Recognition of Coffee Leaf Disease,” Agriculture, vol. 12, no. 11, p. 1909, 2022, doi: 10.3390/agriculture12111909.