Abstract

Maize (corn) is a major and high-yielding crop, cultivated worldwide, although diseases may cause severe yield reductions. Monitoring and identifying maize diseases throughout the growth cycle are crucial tasks. Accurately detecting diseases is an issue for farmers who need expertise in plant pathology, while professional diagnosis can be time-consuming and expensive. Meanwhile, conventional machine learning techniques based on optimised support vector machine with optimisation techniques and image recognition models were impacted with issues which affecting their performance in the classification task. Therefore, this study proposes an improved machine learning model based on optimised support vector machine (SVM) (IMLMBOSVM) using enhanced Binary Particle Swarm Optimisation and Enhanced Reptile search Algorithm to optimise the support vector machine. The aim of the (IMLMBOSVM-EBPSO) and (IMLMBOSVM-ERSA) methods is to detect and categorise maize leaf diseases. The IMLMBOSVM-EBPSO and IMLMBOSVM-ERSA methods apply luminosity to convert RGB images to grayscale images, bi-histogram equalisation for contrast enhancement of the images, morphological filtering for sharpening of the images, adaptive median filtering for noise removal, Sobel edge detection method for segmenting lesions from uninfected part of the leaf, gray level co-occurrence matrix to extract both texture, shape features and colour moment to extract colour features, and the EBPSO or ERSA technique for hyperparameters tuning of the SVM. The IMLMBOSVM-EBPSO and IMLMBOSVM-ERSA techniques exploit EBPSO-SVM and ERSA-SVM for maize leaf disease classification, respectively. Experimental evaluation was conducted to validate the IMLMBOSVM-EBPSO and IMLMBOSVM-ERSA approaches, and the results show that IMLMBOSVM-EBPSO achieved a false positive rate of 2.48%, a specificity of 97.53%, a sensitivity of 97.33%, a precision of 97.84%, and an accuracy of 97.41%. The IMLMBOSVM-ERSA achieved a false positive rate of 3.60%, a specificity of 96.40%, a sensitivity of 96.34%, a precision of 96.85%, and an accuracy of 96.36%.

References

• Ashwini, C., Sellam, V. 2024. An optimal model for identification and classification of corn leaf disease using hybrid 3D-CNN and LSTM. Biomedical Signal Processing and Control, 9, 1-18.
• Vimalkumar, S., Latha, R. 2024. Maize leaf disease detection using manta-ray foraging optimization with deep learning model. Engineering, Technology & Applied Science Research, 14(5), 17068-17074. https://etasr.com/index.php/ETASR/article/view/7821/4089
• Haque, A., Marwaha, S., Deb, C. K., Nigam, S., Arora, A. 2023. Recognition of diseases of maize crop using deep learning models. Neural Computing and Applications, 35(10), 7407–7421.
• Rai, C.K., Pahuja, R. 2024. Northern maize leaf blight disease detection and segmentation using deep convolution neural networks. Multimedia Tools and Applications, 83(7), 19415-19432.
• Qian, X., Zhang, C., Chen, L., Li, K. 2022. Deep learning-based identification of maize leaf diseases is improved by an attention mechanism: Self-attention. Frontiers in plant science, 13(864486), 1-15. https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.864486/pdf
• Rajagopal, M., Kayikci, S., Abbas, M., Sivasakthivel, R. 2024. A novel technique for leaf disease classification using legion kernels with parallel support vector machine (LK-PSVM) and fuzzy C means image segmentation. Heliyon, 10(32707), 1-17. https://pmc.ncbi.nlm.nih.gov/articles/PMC11237940/pdf/main.pdf
• Reddy, Y.A., Adimoolam, M. 2024. Efficient plant leaf disease detection using support vector machine algorithm and compare its features with Naive Bayes classification. AIP Conference Proceedings, 2729(1), 1-15.
• Raju, T., Supriya, V., Swathi, P., Shamshuddin, S.H., Mohan, V. 2024. Support vector machine based diseases detection of various plant leaf using image processing techniques. The International Journal of Analytical and Experimental Modal Analysis, 15(3), 1366-1372.
• Islam, S., Samsuzzaman, Reza, N., Lee, K., Ahmed, S., Cho, Y.J., Noh, D.H., Chung, S. 2024. Image processing and support vector machine (SVM) for classifying environmental stress symptoms of pepper seedlings grown in a plant factory. Agronomy, 14(9), 1-28. https://www.mdpi.com/2073-4395/14/9/2043/pdf?version=1725853039
• Pannakkong, W., Thiwa-Anont, K., Singthong, K., Parthanadee, P., Buddhakulsomsiri, J. 2022. Hyperparameter tuning of machine learning algorithms using response surface methodology: A case study of ANN, SVM, and DBN. Hindawi Mathematical Problems in Engineering, 2022(8513719), 1-17.
• Yang, N., Li, S., Liu, J., Bian, F. 2014. Sensitivity of support vector machine classification to various training features. TELKOMNIKA Indonesian Journal of Electrical Engineering, 12(1), 286-291.
• Gad, A. G. 2022. Particle swarm optimization algorithm and its applications: A systematic review. Archives of Computational Methods in Engineering, 29(12), 2531–2561. https://www.researchgate.net/publication/360057862_Particle_Swarm_Optimization_Algorithm_and_Its_Applications_A_Systematic_Review
• Zhang, D., Liu, J., Jiang, L., Bu, G., Hu, R., Luo, Y. 2020. The improvement of v-shaped transfer function of binary particle swarm optimisation. Advances in Swarm Intelligence, 12145, 202-211.
• Isiet, M., Gadala, M. 2020. Sensitivity analysis of control parameters in particle swarm optimization. Journal of Computational Science, 41(1), 1-13. https://dspace.adu.ac.ae/bitstream/handle/1/1850/gadala%20Sensitivity%20analysis%20of%20control%20parameters%20in%20particle%20swarmoptimization.pdf?sequence=1&isAllowed=y
• Yuan, Q., Zhang, Y., Dai, X., Zhang, S. 2022. A modified reptile search algorithm for numerical optimisation problems. Computational Intelligence and Neuroscience, 2022(975200), 1-20.
• Kailasam, J.k., Nalliah, R., Muthusamy, S.N., Manoharan, P. 2023. MLBRSA: Multi-learning-based reptile search algorithm for global optimisation and software requirements prioritisation problems. Biomimetics (Basel), 8(8), 1-49.
• Padmavathi, K., Thangadurai, K. 2016. Implementation of RGB and gray scale images in plant leaves disease detection: Comparative study. Indian Journal of Science and Technology, 9(6), 1-6. https://indjst.org/downloadarticle.php?Article_Unique_Id= INDJST 5373&Full_Text Pdf_Download=True
• Ayoade, O.B. 2025 Development of an optimised support vector machine for classification of cassava and maize diseases. A Ph.D. Thesis Submitted to the Department of Computer Sciences, Faculty of Natural Sciences, Ajayi Crowther University, Oyo, Nigeria. Unpublished Dissertation.
• Aslam, A., Khan, E., Beg, M. M. S. 2015. Improved edge detection algorithm for brain tumor segmentation. Procedia Computer Science, 58(2015), 430-437.
• Gou, J., Lei, Y. X., Guo, W. P., Wang, C., Cai, Y. Q., Luo, W. 2017. A novel improved particle swarm optimization algorithm based on individual difference evolution. Applied Soft Computing Journal, 57, 468–481.
• Chen, Y., Li, L., Peng, H., Xiao, J., Wu, Q. 2018. Dynamic multi-swarm differential learning particle swarm optimizer. Swarm Evolutionary Computation Journal, 39, 209-221.
• Lynn, N., Ali, M. Z, Suganthan, P. N. 2018. Population topologies for particle swarm optimization and differential evolution. Swarm Evolutionary Computation Journal, 39, 24-35.
• Khatami, A., Mirghasemi, S., Khosravi, A., Lim, C.P., Nahavandi, S. (2017). A new PSO-based approach to fire flame detection using K-Medoids clustering. Expert System Application, 68, 69-80.
• Lin, C.W., Yang, L., Fournier-Viger, P., Hong, T.P., Voznak, M. 2017. A binary PSO approach to mine high-utility item sets. Soft computing, 21, 5103-5121.
• Zhou, Y., Wang, N., Xiang, W. 2017. Clustering hierarchy protocol in wireless sensor networks using an improved PSO algorithm. IEEE Access, 5, 2241-2253.
• Chouikhi, N., Ammar, B., Rokbani, N., Alimi, A.M. 2017. PSO-based analysis of echo state network parameters for time series forecasting. Applied Soft Computing, 55, 211-225.
• Ma, Z., Yuan, X., Han, S., Sun, D., Ma, Y. 2019. Improved chaotic particle swarm optimisation algorithm with more symmetric distribution for numerical function optimisation. Symmetry, 11(876), 1-19.
• Khan, M. K., Zafar, M. H., Rashid, S., Mansoor, M., Raza Moosavi, S. K., Sanfilippo, F. 2023. Improved reptile search optimization algorithm: Application on Regression and classification problems. Applied Sciences, 13(945), 1-29. https://www.mdpi.com/2076-3417/13/2/945
• Zhou, L., Liu, X., Tian, R., Wang, W., Jin, G. 2025. A multi-strategy enhanced reptile search algorithm for global optimisation and engineering optimization design problems. Cluster Computing, 28(141), 1-41.
• Fu, Y., Liu, D., Chen, J., He, L. 2024. Secretary bird optimisation algorithm: a new metaheuristic for solving global optimisation problems. Artificial Intelligence Review, 57(123), 1-102. https://link.springer.com/content/pdf/10.1007/s10462-024-10729-y.pdf
• Zhao, S., Zhang, T., Ma, S., Chen, M. 2022. Dandelion optimizer: a nature-inspired metaheuristic algorithm for engineering applications. Engineering Application of Artificial Intelligence, 114(2), 1-28.
• Ibrahim, M. A., Ayotunde, O. O., Abeke, A. A. Samushudeen, B. O., Obiyemi, O. O. 2022. Development of hybrid learning technique for detection and classification of plant diseases. Adeleke University Journal of Engineering and Technology, 5(1), 87-102. http://aujet.adelekeuniversity.edu.ng/index.php/aujet/article/view/227/155
• Yang, J., Zhu, W., Liu, G., Dai, W., Xu, Z., Wan, L, Zhou, G. 2024. ICPNet: Advanced maize leaf disease detection with multidimensional attention and coordinate depthwise convolution. Plants, 13(2277), 1-21. https://www.mdpi.com/2223-7747/13/16/2277/pdf?version=1723725644
• Theerthagiri, P., Ruby, A.U., Chandran, J.G.C., Sardar, T.H., Ahamed S, B.M. 2024. Deep SqueezeNet learning model for diagnosis and prediction of maize leaf diseases. Journal of Big Data, 11(112), 1-16. https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00972-z.pdf
• Bachhal, P., Kukreja, V., Ahuja, S., Kumar, Lilhore, U.K., Simaiya, S., Bijalwan, A., Alroobaea, R. Algarni, S. 2024. Maize leaf disease recognition using PRF SVM integration: A breakthrough technique. Scientific Reports, 14(10219), 1-20. https://pmc.ncbi.nlm.nih.gov/articles/PMC11068775/pdf/41598_2024_Article_60506.pdf
• Kauri, K., Bansal, K. 2024. Enhancing Plant Disease Detection using Advanced Deep Learning Models. Indian Journal of Science and Technology, 17(17), 1755-1766.https://indjst.org/download-article.php?Article_Unique_Id=INDJST13524&Full_Text_Pdf_Download=True
• Ashurov, A.Y., Mehdhar S. A., Al-Gaashani , M., Samee, N.A., Alkanhel, R., Atteia, G., Abdallah, H.A., Muthanna, M.S. A. 2025. Enhancing plant disease detection through deep learning: A Depthwise CNN with squeeze and excitation integration and residual skip connections. Frontiers in Plant Science, 15, 1-16. https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2024.1505857/pdf
• Rani, R., Sahoo, J., Bellamkonda, S., Kumar, S. 2025. Attention-enhanced corn disease diagnosis using few-shot learning and VGG16, MethodsX, 2025(103172), 1-12. https://pmc.ncbi.nlm.nih.gov/articles/PMC11795141/pdf/main.pdf
• Aboelenin, S., Elbasheer, F.A., Eltoukhy, M.M., El-Hady, W.M., Hosny, K, M. (2025). A hybrid framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer. Complex & Intelligent Systems, 11(142), 1-17. https://link.springer.com/content/pdf/10.1007/s40747-024-01764-x.pdf
• Nan, F., Song, Y., Yu, X., Nie, C., Liu, Y., Bai, Y., Zou, D., Wang, C., Yin, D., Yang, W., Jin, X. 2023. A novel method for maize leaf disease classification using the RGB-D post-segmentation image data. Frontiers in Plant Science, 14, 1-14. https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1268015/pdf
• Alzubaidi, L., Zhang, J., Humaidi, A.J., Al-Dujaili, A., Duan, Y. Al-Shamma, O., Santamaria, J., Fadhel, M.A. 2021. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(53), 1-74. https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-021-00444-8.pdf