International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 17, No. 5, 8 Oct. 2025
Cover page and Table of Contents: PDF (size: 762KB)
Hybrid Machine Learning Model for Cacao Pod Disease Classification Using Visual Features
PDF (762KB), PP.84-94
Views: 0 Downloads: 0
Author(s)
Index Terms
Hybrid Machine Learning, Cacao Pod, Convolutional Neural Network, Support Vector Machine, Black Pod Rot, Pod Borer
Abstract
Early detection of diseases and pests is vital for proper cultivation of in-demand, high-quality crops, such as cacao. With the emergence of recent trends in technology, artificial intelligence has made disease diagnosis and classification more convenient and non-invasive with the applications of image processing, machine learning, and neural networks. This study presented an alternative approach for developing a cacao pod disease classifier using hybrid machine learning models, integrating the capabilities of convolutional neural networks and support vector machines. Convolutional neural networks were employed to extract complex and high-level features from images, breaking the restrictions of conventional image processing techniques in capturing intricate patterns and details. Support vector machines, on the other hand, excel at differentiating between classes by effectively utilizing distinctive numerical parameters representing datasets with clear interclass differences. Raw images of cacao pods were utilized as inputs for extracting relevant parameters that will distinguish three distinct classes: healthy, black pod rot diseased, and pod borer infested. For visual feature extraction, four convolutional neural network architectures were considered: AlexNet, ResNet50, DenseNet201, and MobileNetV2. The outputs of the fully connected layers of the neural networks were used as references for training the support vector machine classifier with the consideration of linear, quadratic, cubic, and Gaussian kernel functions. Among every hybrid pair, the DenseNet201 – Cubic Kernel Support Vector Machine attained the highest testing accuracy of 98.4%. The model even outperformed two pre-existing systems focused on the same application, with corresponding accuracies of 91.79% and 94%, respectively. Thus, it posed an improved, non-invasive method for detecting black pod rot disease or pod borer infestation in cacao pods.
Cite This Paper
Earl Clarence S. San Diego, "Hybrid Machine Learning Model for Cacao Pod Disease Classification Using Visual Features", International Journal of Intelligent Systems and Applications(IJISA), Vol.17, No.5, pp.84-94, 2025. DOI:10.5815/ijisa.2025.05.06
Reference
[1]Department of Science and Technology, “Cacao Industry Profile.” PCAARRD’s Industry Strategic Science and Technology Programs, 2024. [Online]. Available: https://ispweb.pcaarrd.dost.gov.ph/isp-commodities/cacao/
[2]Philippine Statistics Authority, “Second Quarter 2024 Value of Production in Agriculture and Fisheries.” 2024. [Online]. Available: https://psa.gov.ph/system/files/aad/Full%20Report%2C%20Second
%20Quarter%202024%20Value%20of%20Production%20in%20Philippine%20Agriculture%20 and%20Fisheries_signed.pdf
[3]C. Cilas and P. Bastide, “Challenges to Cocoa Production in the Face of Climate Change and the Spread of Pests and Diseases,” Agronomy, vol. 10, no. 9, 2020, doi: 10.3390/agronomy10091232.
[4]J. P. Marelli et al., “Chocolate under threat from old and new cacao diseases,” Phytopathology, vol. 109, no. 8. 2019. doi: 10.1094/PHYTO-12-18-0477-RVW.
[5]J. Niogret et al., “Host preferences of the cocoa pod borer, Conopomorpha cramerella, the main threat to cocoa production in Southeast Asia,” Entomologia Experimentalis et Applicata, vol. 168, no. 3, 2020, doi: 10.1111/eea.12882.
[6]D. O. Cagadas and R. A. Labajan, “Leaf-Based Cacao Diseases Classification Using Image Processing,” Sci.Int.(Lahore), vol. 35, no. 4, pp. 369–373, 2024.
[7]Department of Science and Technology, “Cacao Industry Profile.” PCAARRD’s Industry Strategic Science and Technology Programs, 2024. [Online]. Available: https://ispweb.pcaarrd.dost.gov.ph/isp-commodities/cacao/
[8]Philippine Statistics Authority, “Second Quarter 2024 Value of Production in Agriculture and Fisheries.” 2024. [Online]. Available: https://psa.gov.ph/system/files/aad/Full%20Report%2C%20Second %20Quarter%202024%20Value%20of%20Production%20in%20Philippine%20Agriculture%20and% 20Fisheries_signed.pdf
[9]C. Cilas and P. Bastide, “Challenges to Cocoa Production in the Face of Climate Change and the Spread of Pests and Diseases,” Agronomy, vol. 10, no. 9, 2020, doi: 10.3390/agronomy10091232.
[10]J. P. Marelli et al., “Chocolate under threat from old and new cacao diseases,” Phytopathology, vol. 109, no. 8. 2019. doi: 10.1094/PHYTO-12-18-0477-RVW.
[11]J. Niogret et al., “Host preferences of the cocoa pod borer, Conopomorpha cramerella, the main threat to cocoa production in Southeast Asia,” Entomologia Experimentalis et Applicata, vol. 168, no. 3, 2020, doi: 10.1111/eea.12882.
[12]D. O. Cagadas and R. A. Labajan, “Leaf-Based Cacao Diseases Classification Using Image Processing,” Sci.Int.(Lahore), vol. 35, no. 4, pp. 369–373, 2024.
[13]D. B. Vera, B. Oviedo, W. C. Casanova, and C. Zambrano-Vega, “Deep Learning-Based Computational Model for Disease Identification in Cocoa Pods (Theobroma cacao L.),” International Journal of Advanced Computer Science and Applications, 2024.
[14]S. P. Chakravarthy, C. Gunasundari, K. S. Bhuvaneswari, B. Sharma, and S. Chowdhury, “Convolutional Neural Network (CNN) for Image Detection and Recognition in Medical Diagnosis,” in IET Conference Proceedings, 2022. doi: 10.1049/icp.2023.0579.
[15]M. Ahmad, S. Aftab, M. S. Bashir, N. Hameed, I. Ali, and Z. Nawaz, “SVM Optimization for Sentiment Analysis,” IJACSA) International Journal of Advanced Computer Science and Applications, vol. 9, no. 4. 2018. [Online]. Available: www.ijacsa.thesai.org
[16]A. K. Jean, M. Diarra, B. A. Bakary, G. Pierre, and A. K. Jérôme, “Application based on Hybrid CNN-SVM and PCA-SVM Approaches for Classification of Cocoa Beans,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 9, 2022, doi: 10.14569/IJACSA.2022.0130927.
[17]M. F. Unlersen et al., “CNN–SVM hybrid model for varietal classification of wheat based on bulk samples,” European Food Research and Technology, vol. 248, no. 8, 2022, doi: 10.1007/s00217-022-04029-4.
[18]R. A. Godmalin, C. J. Aliac, and L. Feliscuzo, “Cacao Pod Infection Level Classification Using Transfer Learning,” in 2023 IEEE Open Conference of Electrical, Electronic and Information Sciences, eStream 2023 - Proceedings, 2023. doi: 10.1109/eStream59056.2023.10135062.
[19]C. Rodriguez, O. Alfaro, P. Paredes, D. Esenarro, and F. Hilario, “Machine Learning Techniques in the Detection of Cocoa (Theobroma cacao L.) Diseases,” Annals of the Romanian Society for Cell Biology, 7732–7741, vol. 25, no. 3, 2021.
[20]N. G. Baculio and J. B. Barbosa, “An Objective Classification Approach of Cacao Pods using Local Binary Pattern Features and Artificial Neural Network Architecture (ANN),” Indian Journal of Science and Technology, vol. 15, no. 11, pp. 495–504, Mar. 2022, doi: 10.17485/IJST/v15i11.60.
[21]Basri, R. Tamin, H. A. Karim, Indrabayu, and I. S. Areni, “Mobile image processing application for cacao’s fruits pest and disease attack using deep learning algorithm,” ICIC Express Letters, vol. 14, no. 10, 2020, doi: 10.24507/icicel.14.10.1025.
[22]S. Kumi, D. Kelly, J. Woodstuff, R. K. Lomotey, R. Orji, and R. Deters, “Cocoa Companion: Deep Learning-Based Smartphone Application for Cocoa Disease Detection,” in Procedia Computer Science, 2022. doi: 10.1016/j.procs.2022.07.013.
[23]R. K. Lomotey, S. Kumi, R. Orji, and R. Deters, “Automatic detection and diagnosis of cocoa diseases using mobile tech and deep learning,” International Journal of Sustainable Agricultural Management and Informatics, vol. 10, no. 1, 2024, doi: 10.1504/IJSAMI.2024.135403.
[24]K. S. Soh, E. G. Moung, K. J. J. Danker, J. A. Dargham, and A. Farzamnia, “Cocoa Diseases Classification using Deep Learning Algorithm,” ITM Web of Conferences, vol. 63, 2024, doi: 10.1051/itmconf/20246301014.
[25]R. A. Godmalin, C. J. Aliac, and L. Feliscuzo, “Classification of Cacao Pod if Healthy or Attack by Pest or Black Pod Disease Using Deep Learning Algorithm,” in 4th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2022, 2022. doi: 10.1109/IICAIET55139.2022.9936817.
[26]D. Mamadou, K. J. Ayikpa, A. B. Ballo, and B. M. Kouassi, “Cocoa Pods Diseases Detection by MobileNet Confluence and Classification Algorithms,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 9, 2023, doi: 10.14569/IJACSA.2023.0140937.
[27]H. C. Chen et al., “AlexNet Convolutional Neural Network for Disease Detection and Classification of Tomato Leaf,” Electronics (Switzerland), vol. 11, no. 6, 2022, doi: 10.3390/electronics11060951.
[28]S. R. Shah, S. Qadri, H. Bibi, S. M. W. Shah, M. I. Sharif, and F. Marinello, “Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A Case Study on Early Detection of a Rice Disease,” Agronomy, vol. 13, no. 6, 2023, doi: 10.3390/agronomy13061633.
[29]G. Singhal, “Introduction to DenseNet with TensorFlow,” Pluralsight. Accessed: Oct. 06, 2024. [Online]. Available: https://www.pluralsight.com/guides/introduction-to-densenet-with-tensorflow
[30]K. Dong, C. Zhou, Y. Ruan, and Y. Li, “MobileNetV2 Model for Image Classification,” in Proceedings - 2020 2nd International Conference on Information Technology and Computer Application, ITCA 2020, 2020. doi: 10.1109/ITCA52113.2020.00106.
[31]E. Efeoğlu and G. Tuna, “Machine Learning for Predictive Maintenance: Support Vector Machines and Different Kernel Functions,” Journal of Machinery Manufacture and Reliability, vol. 51, no. 5, 2022, doi: 10.3103/S1052618822050041.