Among all the plagues threatening cocoa cultivation in general, and particularly in West Africa, the swollen shoot viral disease is currently the most dangerous. The greatest challenge in the fight to eradicate this pandemic remains its early detection. Traditional methods of swollen shoot detection are mostly based on visual observations, leading to late detection and/or diagnostic errors. The use of machine learning algorithms is now an alternative for effective plant disease detection. It is therefore crucial to provide efficient solutions to farmers’ cooperatives. In our study, we built a database of healthy and diseased cocoa leaves. We then explored the power of feature extractors based on convolutional neural networks such as VGG 19, Inception V3, DenseNet 201, and a custom CNN, combining their strengths with the XGBOOST classifier. The results of our experiments showed that this fusion of methods with XGBOOST yielded highly promising scores, outperforming the results of algorithms using the sigmoid function. These results were further consolidated by the use of evaluation metrics such as accuracy, mean squared error, F score, recall, and Matthews’s correlation coefficient. The proposed approach, combining state of the art feature extractors and the XGBOOST classifier, offers an efficient and reliable solution for the early detection of swollen shoot. Its implementation could significantly assist West African cocoa farmers in combating this devastating disease and preserving their crops.
References
[1]
Koffié, K. and Bi, K. (2011) Impact de la maladie virale du swollen shoot du cacaoyer sur la production de cacao en milieu paysan à bazré (côte d’ivoire).
[2]
Lot, H., Djiekpor, E. and Jacquemond, M. (1991) Characterization of the Genome of Cacao Swollen Shoot Virus. Journal of General Virology, 72, 1735-1739. https://doi.org/10.1099/0022-1317-72-7-1735
[3]
Franck, O., Emmanuelle, M., François, B., Bernard, D., Komlan, W. and Christian, C. (2012) Analyse spatio-temporelle de la progression du Cacao Swollen Shoot Virus à l’échelle de parcelles cacaoyères.
[4]
Kouassi, K.E. (2021) Menaces Sur L’Avenir Du Cacao Ivoirien. Revuedes Études Multidisciplinairers en Sciences Économiques et Socicles, 6, 103-120.
[5]
Ofori, A., Padi, F.K., Ameyaw, G.A., Dadzie, A.M., Opoku-Agyeman, M., Domfeh, O., et al. (2022) Field Evaluation of the Impact of Cocoa Swollen Shoot Virus Disease Infection on Yield Traits of Different Cocoa (Theobroma cacao L.) Clones in Ghana. PLOS ONE, 17, e0262461. https://doi.org/10.1371/journal.pone.0262461
[6]
Herrbach, E.E., Maguet, J.L. and Hommay, G. (2012) Les cochenilles, des hémiptères peu connus comme vecteurs de virus. 8th Conference of the Société Française de Phytopathologie, Paris, 5-8 June 2012, 84.
[7]
Couturier, G., Matile-Ferrero, D. and Richard, C. (1985) Sur les cochenilles de la région de Taï (Côte d’Ivoire), recensées dans les cultures et en forêt dense, (Homoptera, Coccoidea).
[8]
Goebel, F. (2015) Bioagresseurs des cultures tropicales face au changement climatique: quelques exemples. https://www.academia.edu/16770599/Bioagresseurs_des_cultures_tropicales_face_au_changement_climatique_quelques_exemples
[9]
Ayikpa, K.J., Mamadou, D., Gouton, P. and Adou, K.J. (2023) Classification of Cocoa Pod Maturity Using Similarity Tools on an Image Database: Comparison of Feature Extractors and Color Spaces. Data, 8, Article 99. https://doi.org/10.3390/data8060099
[10]
Haralick, R.M., Shanmugam, K. and Dinstein, I. (1973) Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics, 3, 610-621. https://doi.org/10.1109/tsmc.1973.4309314
[11]
d’Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G. and Sagun, L. (2022) Convit: Improving Vision Transformers with Soft Convolutional Inductive Biases. Journal of Statistical Mechanics: Theory and Experiment, 2022, Article 114005. https://doi.org/10.1088/1742-5468/ac9830
[12]
Sing Soh, K., Gubin Moung, E., John Julius Danker, K., Dargham, J.A. and Farzamnia, A. (2024) Cocoa Diseases Classification Using Deep Learning Algorithm. ITM Web of Conferences, 63, Article 01014. https://doi.org/10.1051/itmconf/20246301014
[13]
Gyamfi, A., Iddrisu, S.A. and Adegbola, O. (2020) Machine Learning-Based Cocoa E-Health System. 2020 13th CMI Conference on Cybersecurity and Privacy (CMI)—Digital Transformation—Potentials and Challenges(51275), Copenhagen, 26-27 November 2020, 1-7. https://doi.org/10.1109/cmi51275.2020.9322689
[14]
Lomotey, R.K., Kumi, S., Orji, R. and Deters, R. (2023) Automatic Detection and Diagnosis of Cocoa Diseases Using Mobile Tech and Deep Learning. International Journal of Sustainable Agricultural Management and Informatics, 10, 92-119.
[15]
Coulibaly, M., Kouassi, K.H., Kolo, S. and Asseu, O. (2020) Detection of “Swollen Shoot” Disease in Ivorian Cocoa Trees via Convolutional Neural Networks. Engineering, 12, 166-176. https://doi.org/10.4236/eng.2020.123014
[16]
Ayikpa, K.J., Ayikpa, K.J., Ayikpa, K.J., Mamadou, D., Gouton, P. and Adou, K.J. (2022) Experimental Evaluation of Coffee Leaf Disease Classification and Recognition Based on Machine Learning and Deep Learning Algorithms. Journal of Computer Science, 18, 1201-1212. https://doi.org/10.3844/jcssp.2022.1201.1212
[17]
Bueno, G.E., Valenzuela, K.A. and Arboleda, E.R. (2020) Maturity Classification of Cacao through Spectrogram and Convolutional Neural Network. Jurnal Teknologi dan Sistem Komputer, 8, 228-233. https://doi.org/10.14710/jtsiskom.2020.13733
[18]
Kumi, S., Kelly, D., Woodstuff, J., Lomotey, R.K., Orji, R. and Deters, R. (2022) Cocoa Companion: Deep Learning-Based Smartphone Application for Cocoa Disease Detection. Procedia Computer Science, 203, 87-94. https://doi.org/10.1016/j.procs.2022.07.013
[19]
Buenaño Vera, D., Oviedo, B., Chiriboga Casanova, W. and Zambrano-Vega, C. (2024) Deep Learning-Based Computational Model for Disease Identification in Cocoa Pods (Theobroma cacao L.).
[20]
Shukla, N. and Fricklas, K. (2018) Machine Learning with TensorFlow. Manning.
[21]
Rodriguez, C., Alfaro, O., Paredes, P., Esenarro, D. and Hilario, F. (2021) Machine Learning Techniques in the Detection of Cocoa (Theobroma cacao L.) Diseases. Annals of the Romanian Society for Cell Biology, 25, 7732-7741.
[22]
Forsyth, D.A. and Ponce, J. (2002) Computer Vision: A Modern Approach. Prentice Hall Professional Technical Reference. Pearson.
[23]
Zhang, G., Huang, X., Li, S.Z., Wang, Y. and Wu, X. (2004) Boosting Local Binary Pattern (LBP)-Based Face Recognition. In: Lecture Notes in Computer Science, Springer, 179-186. https://doi.org/10.1007/978-3-540-30548-4_21
[24]
Noria, H. and Aniya, A. (2011) Application of Support Vector Machines (SVM) for Handwritten Digit Recognition.
[25]
Bouillant, S., Mitéran, J., Yang, F. and Paindavoine, M. (2003) Détection de défauts temps réel sur des objets à géométrie complexe: Étude par SVM et hyperrectangles. https://core.ac.uk/download/pdf/15494840.pdf
[26]
Harvyanti, A.F.M., Baihaki, R.I., Dafik,, Ridlo, Z.R. and Agustin, I.H. (2023) Application of Convolutional Neural Network for Identifying Cocoa Leaf Disease. In: Advances in Intelligent Systems Research, Atlantis Press International BV, 283-304. https://doi.org/10.2991/978-94-6463-174-6_21
[27]
Samuels, G.J., Ismaiel, A., Rosmana, A., Junaid, M., Guest, D., Mcmahon, P., et al. (2012) Vascular Streak Dieback of Cacao in Southeast Asia and Melanesia: In Planta Detection of the Pathogen and a New Taxonomy. Fungal Biology, 116, 11-23. https://doi.org/10.1016/j.funbio.2011.07.009
[28]
Deng, L. and Yu, D. (2014) Deep Learning: Methods and Applications. Foundations and Trends in Signal Processing, 7, 197-387. https://doi.org/10.1561/2000000039
[29]
Minu, M.S., et al. (2022) Optimal Squeeze Net with Deep Neural Network-Based Arial Image Classification Model in Unmanned Aerial Vehicles. Traitement du Signal, 39, 275-281. https://doi.org/10.18280/ts.390128
[30]
Reza, A.M. (2004) Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology, 38, 35-44. https://doi.org/10.1023/b:vlsi.0000028532.53893.82
[31]
Paul, K.C. and Aslan, S. (2021) An Improved Real-Time Face Recognition System at Low Resolution Based on Local Binary Pattern Histogram Algorithm and CLAHE. Optics and Photonics Journal, 11, 63-78. https://doi.org/10.4236/opj.2021.114005
[32]
Goodfellow, I., Bengio, Y. and Courville, A. (2016) Deep Learning. MIT Press.
[33]
Mascarenhas, S. and Agarwal, M. (2021) A Comparison between VGG16, VGG19 and Resnet50 Architecture Frameworks for Image Classification. 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications, Bengaluru, 19-21 November 2021, 96-99. https://doi.org/10.1109/centcon52345.2021.9687944
[34]
Himel, G.M.S., Islam, M.M. and Rahaman, M. (2024) Vision Intelligence for Smart Sheep Farming: Applying Ensemble Learning to Detect Sheep Breeds. Artificial Intelligence in Agriculture, 11, 1-12. https://doi.org/10.1016/j.aiia.2023.11.002
[35]
Team, K. (2023) Keras documentation: DenseNet, Keras Httpskeras Ioapiapplicationsdensenet.
[36]
Wang, F., Tian, Y., Zhang, X. and Hu, F. (2022) An Ensemble of Xgboost Models for Detecting Disorders of Consciousness in Brain Injuries through EEG Connectivity. Expert Systems with Applications, 198, Article 116778. https://doi.org/10.1016/j.eswa.2022.116778
