A Spider Wasp Optimizer-Based Deep Learning Framework for Efficient Citrus Disease Detection
Main Article Content
Keywords
Citrus Disease Detection, Deep Convolutional Neural Network, Spider Wasp Optimizer, Hyperparameter Optimization
Abstract
Managing citrus diseases is important for lowering crop losses and raising the economic value of citrus output. To provide a novel approach for the identification and classification of three significant citrus diseases—Citrus Canker, Citrus Greening, and Citrus Black Spot—this study uses a Deep Convolutional Neural Network (DCNN) optimized using the Spider Wasp Optimizer (SWO). Traditional disease diagnosis methods heavily rely on expert visual inspection, which is often subjective and time-consuming. To overcome these drawbacks, the proposed SWO-DCNN model automates hyperparameter tuning, improving classification accuracy and reducing computation time. Citrus image datasets containing both healthy and infected samples were pre-processed using grayscale conversion, normalization, and augmentation, and then trained using a 10-fold cross-validation technique. Performance evaluations based on sensitivity, specificity, false positive rate, accuracy, and identification time show that the SWO-DCNN outperforms the conventional DCNN in every disease category. With accuracies of 96.22%, 96.51%, 95.70%, and 97.04% for the classification of Black Spot, Greening, Canker, and overall healthy/non-healthy, respectively, the SWO-DCNN significantly reduced false positive rates and recognition times. This paper contributes to knowledge by presenting the Spider Wasp Optimizer, a hyperparameter tuning technique for deep learning models used in the identification of agricultural diseases. The SWO-DCNN framework offers a dependable and scalable approach for automated citrus disease classification by enhancing model performance and computational efficiency. This innovation supports precision farming initiatives and provides a reliable alternative to traditional diagnostic methods, which may improve export quality control and reduce citrus farming's financial losses.
Article Metrics Graph
References
[2] Gottwald TR. Current epidemiological understanding of citrus Huanglongbing. Annu Rev Phytopathol. 2010;48:119–39. doi:10.1146/annurev-phyto-073009-114418.
[3] Wang N, Trivedi P. Citrus Huanglongbing: A newly relevant disease presents unprecedented challenges. Phytopathol-ogy. 2013;103(7):652–65. doi:10.1094/PHYTO-12-12-0331-RVW.
[4] da Graça JV, Douhan GW, Halbert SE, Keremane ML, Lee RF, Vidalakis G, Zhao H. Huanglongbing: An overview of a complex pathosystem ravaging the world's citrus. J Integr Plant Biol. 2016;58(4):373–87. doi:10.1111/jipb.12437.
[5] Gent DH, Grove GG, Nelson ME, Wolfenbarger SN, Woods JL. Corrigendum: Crop damage caused by powdery mil-dew on hop and its relationship to late season management. Plant Pathol. 2015;64(1). doi:10.1111/ppa.12312.
[6] Khattak A, Asghar MU, Batool U, Asghar MZ, Ullah H, Al-Rakhami M, Gumaei A. Automatic detection of citrus fruit and leaves diseases using deep neural network model. IEEE Access. 2021; 9:112942–54. doi:10.1109/ACCESS.2021.3096895.
[7] Panchal AV, Patel SC, Bagyalakshmi K, Kumar P, Khan IR, Soni M. Image-based plant diseases detection using deep learning. Mater Today Proc. 2023; 80:3500–6. doi: 10.1016/j.matpr.2021.07.281.
[8] Arsenovic M, Karanovic M, Sladojevic S, Anderla A, Stefanovic D. Solving current limitations of deep learning-based approaches for plant disease detection. Symmetry. 2019;11(7):939. doi:10.3390/sym11070939.
[9] Duth PS, Bhat SG. Disease classification in citrus leaf using deep learning. In: 2022 IEEE International Conference on Data Science and Information System (ICDSIS); 2022 Jul. p. 1–5. doi:10.1109/ICDSIS55133.2022.9915847.
[10] Moussafir M, Chaibi H, Saadane R, Chehri A, Rharras AE, Jeon G. Design of efficient techniques for tomato leaf disease detection using genetic algorithm-based and deep neural networks. Plant Soil. 2022;479(1):251–66. doi:10.1007/s11104-022-05513-2.
[11] Son Y, Lee SB, Kim H, Song ES, Huh H, Czosnyka M, Kim D. J. Automated artifact elimination of physiological signals using a deep belief network: an application for continuously measured arterial blood pressure waveforms. Inf Sci (Ny). 2018; 456:145–58. doi: 10.1016/j.ins.2018.05.018.
[12] Singh UP, Chouhan SS, Jain S, Jain S. Multilayer convolution neural network for the classification of mango leaves infected by anthracnose disease. IEEE Access. 2019; 7:43721–9. doi:10.1109/ACCESS.2019.2907383.
[13] Abade A, Ferreira PA, de Barros Vidal F. Plant diseases recognition on images using convolutional neural networks: a systematic review. Comput Electron Agric. 2021; 185:106125. doi: 10.1016/j.compag.2021.106125.
[14] Khan A, Nawaz U, Ulhaq A, Robinson RW. Real-time plant health assessment via implementing cloud-based scalable transfer learning on AWS DeepLens. PLoS One. 2020;15(12): e0243243. doi: 10.1371/journal.pone.0243243.
[15] Thakur PS, Chaturvedi S, Khanna P, Sheorey T, Ojha A. Vision transformer meets convolutional neural network for plant disease classification. Ecol Inform. 2023; 77:102245. doi: 10.1016/j.ecoinf.2023.102245.
[16] Benfenati A, Causin P, Oberti R, Stefanello G. Unsupervised deep learning techniques for powdery mildew recognition based on multispectral imaging. arXiv [Preprint]. 2021. arXiv:2112.11242. doi:10.48550/arXiv.2112.11242.
[17] Doutoum AS, Tugrul B. A systematic review of deep learning techniques for apple leaf diseases classification and detection. PeerJ Comput Sci. 2025;11:e2655. doi:10.7717/peerj-cs.2655.
[18] Sankhe SR, Ambhaikar A. Plant disease detection and classification techniques: a review. Multiagent Grid Syst. 2024;20(3–4):265–82. doi:10.1177/15741702241304087.
[19] Pandian JA, Kumar VD, Geman O, Hnatiuc M, Arif M, Kanchanadevi K. Plant disease detection using deep convolu-tional neural network. Appl Sci. 2022;12(14):6982. doi:10.3390/app12146982.
[20] Barman U, Choudhury RD, Sahu D, Barman GG. Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease. Comput Electron Agric. 2020; 177:105661. doi: 10.1016/j.com-pag.2020.105661.
[21] Tiwari V, Joshi RC, Dutta MK. Dense convolutional neural networks based multiclass plant disease detection and clas-sification using leaf images. Ecol Inform. 2021; 63:101289. doi: 10.1016/j.ecoinf.2021.101289.
[22] Deng X, Zhu Z, Yang J, Zheng Z, Huang Z, Yin X, Lan Y. Detection of citrus huanglongbing based on multi-input neural network model of UAV hyperspectral remote sensing. Remote Sens. 2020;12(17):2678. doi:10.3390/rs12172678.
[23] Mei H, Deng X, Hong T, Luo X. Early detection and grading of citrus huanglongbing using hyperspectral imaging technique. Trans Chin Soc Agric Eng. 2014;30(9):140–7.
[24] Hadipour-Rokni R, Asli-Ardeh EA, Jahanbakhshi A, Sabzi S. Intelligent detection of citrus fruit pests using machine vision system and convolutional neural network through transfer learning technique. Comput Biol Med. 2023; 155:106611. doi: 10.1016/j.compbiomed.2023.106611.
[25] Yang D, Wang F, Hu Y, Lan Y, Deng X. Citrus huanglongbing detection based on multi-modal feature fusion learning. Front Plant Sci. 2021; 12:809506. doi:10.3389/fpls.2021.809506.
[26] Dhiman P, Kukreja V, Kaur A. Citrus fruits classification and evaluation using deep convolution neural networks: an input layer resizing approach. In: 2021 9th International Conference on Reliability, Infocom Technologies and Optimi-zation (Trends and Future Directions) (ICRITO); 2021. p. 1–4. doi:10.1109/ICRITO51393.2021.9596357.
[27] Dhiman P, Kukreja V, Manoharan P, Kaur A, Kamruzzaman MM, Dhaou IB, Iwendi C. A novel deep learning model for detection of severity level of the disease in citrus fruits. Electronics. 2022;11(3):495. doi:10.3390/electron-ics11030495.
[28] Yadav PK, Burks T, Frederick Q, Qin J, Kim M, Ritenour MA. Citrus disease detection using convolution neural net-work generated features and Softmax classifier on hyperspectral image data. Front Plant Sci. 2022;13:1043712. doi:10.3389/fpls.2022.1043712.
[29] Sharma P, Abrol P. Multi-component image analysis for citrus disease detection using convolutional neural networks. Crop Prot. 2025; 193:107181. doi: 10.1016/j.cropro.2025.107181.
[30] Negi A, Kumar K. Classification and detection of citrus diseases using deep learning. In: Data Science and Its Applica-tions. Chapman and Hall/CRC; 2021. p. 63–85. doi:10.1201/9781003102380-4.
[31] Syed-Ab-Rahman SF, Hesamian MH, Prasad M. Citrus disease detection and classification using end-to-end anchor-based deep learning model. Appl Intell. 2022;52(1):927–38. doi:10.1007/s10489-021-02452-w.
[32] Çetiner H. Citrus disease detection and classification based on convolution deep neural network. Microprocess Mi-crosyst. 2022; 95:104687. doi: 10.1016/j.micpro.2022.104687.
[33] Abdel-Basset M, Mohamed R, Jameel M, Abouhawwash M. Spider wasp optimizer: a novel meta-heuristic optimization algorithm. Artif Intell Rev. 2023;56(10):11675–738. doi:10.1007/s10462-023-10446-y.
[34] Narayanan R, Ganesh N. A comprehensive review of metaheuristics for hyperparameter optimization in machine learn-ing. In: Metaheuristics for Machine Learning: Algorithms and Applications. 2024. p. 37–72. doi: 10.1002/9781394233953.ch2.
[35] Mohamed EA, Braik MS, Al-Betar MA, Awadallah MA. Boosted spider wasp optimizer for high-dimensional feature selection. J Bionic Eng. 2024;21(5):2424–59. doi:10.1007/s42235-024-00558-8.
[36] Abdel-Basset M, Mohamed R, Hezam IM, Sallam K, Hameed IA. An enhanced spider wasp optimization algorithm for multilevel thresholding-based medical image segmentation. Evol Syst. 2024;15(6):2249–71. doi:10.1007/s12530-024-09614-4.
[37] Baskaran NK, Pratap B, Bansal S. Hyperparameter tuning of convolutional neural networks using nature-inspired me-taheuristic algorithms for image classification. In: Nature-inspired Metaheuristic Algorithms. CRC Press; 2025. p. 119–55. doi:10.1201/9781003612858.
[38] Sui J, Tian Z, Wang Z. Multiple strategies improved spider wasp optimization for engineering optimization problem solving. Sci Rep. 2024;14(1):29048. doi:10.1038/s41598-024-78589-8.
[39] Shtayat MBM, Hasan MK, Budhati AK, Solaiman R, Islam S, Pandey B, Saeed MMA. An improved binary spider wasp optimization algorithm for intrusion detection for industrial Internet of Things. IEEE Open J Commun Soc. 2024; 6:2926–44. doi:10.1109/OJCOMS.2024.3421647.
[40] Huang Z, Jiang X, Huang S, Qin S, Yang S. An efficient convolutional neural network-based diagnosis system for citrus fruit diseases. Front Genet. 2023; 14:1253934. doi:10.3389/fgene.2023.1253934.
[41] Arifin KN, Rupa SA, Anwar MM, Jahan I. Lemon and orange disease classification using CNN-extracted features and machine learning classifier. arXiv [Preprint]. 2024. arXiv:2408.14206. doi:10.1145/3723178.3723199.
[42] Das H, Das S, Gourisaria MK, Khan SB, Almusharraf A, Alharbi AI, TR M. Enhancing software fault prediction through feature selection with spider wasp optimization algorithm. IEEE Access. 2024. doi:10.1109/ACCESS.2024.3435333.
[43] Bengio Y. Practical recommendations for gradient-based training of deep architecture. In: Neural Networks: Tricks of the Trade. 2nd ed. Berlin, Heidelberg: Springer; 2012. p. 437–78. doi:10.1007/978-3-642-35289-8_26.
[44] Hutter F, Kotthoff L, Vanschoren J. Automated machine learning: methods, systems, challenges. Springer Nature; 2019. p. 219. Available from: http://library.oapen.org/handle/20.500.12657/23012.
[45] Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Vol. 1, No. 2. Cambridge: MIT Press; 2016.
[46] Zhao M, Shi P, Xu X, Xu X, Liu W, Yang H. Improving the accuracy of an R-CNN-based crack identification system using different preprocessing algorithms. Sensors. 2022;22(18):7089. doi:10.3390/s220807089.
[47] Subramanian M, Shanmugavadivel K, Nandhini PS. On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leaves. Neural Comput Appl. 2022;34(16):13951–68. doi:10.1007/s00521-022-07246-w.
[48] Mohakud R, Dash R. Designing a grey wolf optimization based hyper-parameter optimized convolutional neural net-work classifier for skin cancer detection. J King Saud Univ Comput Inf Sci. 2022;34(8):6280–91. doi: 10.1016/j.jksuci.2021.05.012.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Licensing information
Creative Commons Attribution-Non-Commercial License
Abisola Olayiwola, Department of Computer Engineering, Olabisi Onabanjo University, Ago Iwoye, Ogun State, Nigeria
Dr. Abisola Ayomide Olayiwola is a Lecturer in the Department of Computer Engineering at Olabisi Onabanjo University, Ogun State. She holds a Ph.D. in Intelligent Systems Engineering from Obafemi Awolowo University, Ile-Ife, Osun sate and has over a decade of experience spanning academia and international research collaborations. Her areas of expertise include Artificial Intelligence, Natural Language Processing, and Software Engineering. Dr. Olayiwola is a registered COREN engineer and an active member of the Nigerian Computer Society.
Ajibola Oyedeji, Department of Electrical Engineering Science, University of Johannesburg, Johannesburg, 2006, South Africa.
Ajibola Oyedeji is a Lecturer at the Department of Computer Engineering, Olabisi Onabanjo University, Nigeria. He received his B.Sc. and M.S degrees in Computer Engineering from the Olabisi Onabanjo University, Nigeria and Eastern Mediterranean University, TRNC, respectively. He conducts his research in artificial intelligence, computer vision, IoT and wireless sensor networks.
Dare Olayiwola, Department of Computer Engineering, Ladoke Akintola University of Technology, Ogbomoso, Oyo State, Nigeria
Dr. Olayiwola Dare holds a Ph.D. in Computer Engineering from Ladoke Akintola University of Technology, Ogbomoso, Oyo state. His areas of expertise include Artificial Intelligence, Biometrics, and Software Engineering. Dr. Olayiwola Dare is a registered COREN engineer.
Olufemi Awodoye, Department of Computer Engineering, Ladoke Akintola University of Technology, Ogbomoso, Oyo State, Nigeria
Engr. Dr. O. O. Awodoye is an eminent faculty member in the Department of Computer Engineering, Faculty of Engineering at Ajayi Crowther University (ACU), Oyo State, Nigeria. His areas of specialization include Biometrics, Pattern Recognition, Artificial Intelligence (AI) and Machine Learning. He is also registered by The Council Regulating Engineering in Nigeria (COREN) as a professional Engineer. He has some articles and conference publications published in various research platforms worldwide. He can be communicated via email at ooawodoye50@lautech.edu.ng.
Olukunle Oyebode, Department of Computer Science, Faculty of Computing, University of Ilesa, Osun State, Nigeria
Dr. E. O. Oyebode is a Senior Lecturer in the Department of Computer Science, Faculty of Computing, University of Ilesa, Osun State, Nigeria. His areas of specialization include Cloud Computing, Computer Networks, Cyber Security and Knowledge- based Systems. He is also a registered member of the Nigeria Computer Society. He has some articles and conference publications published in various research platforms worldwide. He can be communicated via email at ebenezer_oyebode@unilesa.edu.ng.
How to Cite
