Journal of Machine and Computing


Crop Leaf Disease Prediction Using Graph Diffusion TCN with Fibroblast Optimization



Journal of Machine and Computing

Received On : 16 March 2025

Revised On : 26 May 2025

Accepted On : 16 June 2025

Published On : 05 July 2025

Volume 05, Issue 03

Pages : 1736-1744


Abstract


Crop leaf disease prediction is plagued by insufficient generalization over different crop species, the lack of differentiation between similar disease symptoms, and variable environmental conditions affecting image quality. Poorly labelled datasets, model over-fitting, and real-time deployment issues all affect the accuracy and reliability of detecting illnesses in agriculture applications. With the PlantVillage dataset, the Random Graph Diffusion Dual Channel Temporal Convolutional Network with Synergistic Fibroblast Optimization (RGD-DCTCNet-SFO) is employed to resolve these challenges in crop leaf disease detection. The pre-processing by the Blind DE-blurring based Light Weight Wiener Filter (BDE-LWWF) is the first step in the process, which enhances image quality by reducing noise and blurring. Return-Aligned Decision Transformer (RADT) provides accurate boundary definition to enable segmentation by identifying regions using deviation analysis. After features have been obtained, the Random Graph Diffusion Dual Channel Temporal Convolutional Network (RGD-DCTCNet) is utilized for effective crop leaf disease classification. Synergistic Fibroblast Optimization (SFO), which boosts the accuracy of classification and minimizes errors, performs optimization on the search process of ill regions for further improved performance. The RGD-DCTCNet-SFO algorithm surpasses existing methods, recording 99.9% efficiency and 99.8% sensitivity, based on experimental outcomes of a Python-based study. The approach provides a robust and reliable solution for agricultural analysis by significantly improving the accuracy of crop leaf disease diagnosis.


Keywords


Crop Leaf Disease, Plant Village, Return-Aligned Decision Transformer, Synergistic Fibroblast Optimization, Wiener Filter.


  1. Md. M. Islam et al., “Deep Crop: Deep learning-based crop disease prediction with web application,” Journal of Agriculture and Food Research, vol. 14, p. 100764, Dec. 2023, doi: 10.1016/j.jafr.2023.100764.
  2. F. Arshad et al., “PLDPNet: End-to-end hybrid deep learning framework for potato leaf disease prediction,” Alexandria Engineering Journal, vol. 78, pp. 406–418, Sep. 2023, doi: 10.1016/j.aej.2023.07.076.
  3. G. Sravanthi and N. R. Moparthi, “An efficient IoT based crop disease prediction and crop recommendation for precision agriculture,” Cluster Computing, vol. 27, no. 5, pp. 5755–5782, Feb. 2024, doi: 10.1007/s10586-023-04246-w.
  4. K. Singh, A. Rao, P. Chattopadhyay, R. Maurya, and L. Singh, “Effective plant disease diagnosis using Vision Transformer trained with leafy- generative adversarial network-generated images,” Expert Systems with Applications, vol. 254, p. 124387, Nov. 2024, doi: 10.1016/j.eswa.2024.124387.
  5. Ashwini and V. Sellam, “An optimal model for identification and classification of corn leaf disease using hybrid 3D-CNN and LSTM,” Biomedical Signal Processing and Control, vol. 92, p. 106089, Jun. 2024, doi: 10.1016/j.bspc.2024.106089.
  6. N. K. Pegada, Vetrithangam, A. Fathima, and Arunadevi, “A survey on various image analysis techniques,” Innovations in Computational and Computer Techniques: ICACCT-2021, vol. 2555, p. 040013, 2022, doi: 10.1063/5.0108909.
  7. P. Bhuyan, P. K. Singh, S. K. Das, and A. Kalla, “SE_SPnet: Rice leaf disease prediction using stacked parallel convolutional neural network with squeeze‐and‐excitation,” Expert Syst., vol. 40, no. 7, p. e13304, 2023. DOI: 10.1111/exsy.13304.
  8. D. J. Chaudhari and K. Malathi, “Detection and Prediction of Rice Leaf Disease Using a Hybrid CNN-SVM Model,” Optical Memory and Neural Networks, vol. 32, no. 1, pp. 39–57, Mar. 2023, doi: 10.3103/s1060992x2301006x.
  9. S. Aggarwal et al., “Rice Disease Detection Using Artificial Intelligence and Machine Learning Techniques to Improvise Agro-Business,” Scientific Programming, vol. 2022, pp. 1–13, Jun. 2022, doi: 10.1155/2022/1757888.
  10. Naralasetti and J. D. Bodapati, “Enhancing Plant Leaf Disease Prediction Through Advanced Deep Feature Representations: A Transfer Learning Approach,” Journal of The Institution of Engineers (India): Series B, vol. 105, no. 3, pp. 469–482, Feb. 2024, doi: 10.1007/s40031-023-00966-0.
  11. D. S. Joseph, P. M. Pawar, and K. Chakradeo, “Real-Time Plant Disease Dataset Development and Detection of Plant Disease Using Deep Learning,” IEEE Access, vol. 12, pp. 16310–16333, 2024, doi: 10.1109/access.2024.3358333.
  12. Pacal, “Enhancing crop productivity and sustainability through disease identification in maize leaves: Exploiting a large dataset with an advanced vision transformer model,” Expert Systems with Applications, vol. 238, p. 122099, Mar. 2024, doi: 10.1016/j.eswa.2023.122099.
  13. N. H. Shabrina et al., “A novel dataset of potato leaf disease in uncontrolled environment,” Data in Brief, vol. 52, p. 109955, Feb. 2024, doi: 10.1016/j.dib.2023.109955.
  14. C. Haywood and R. Younes, “Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network,” 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, Jun. 2023, doi: 10.1109/ijcnn54540.2023.10191586.
  15. T. Tanaka, K. Abe, K. Ariu, T. Morimura, and E. Simo-Serra, 2024. Return-Aligned Decision Transformer. arXiv preprint arXiv:.
  16. Fan, W. Weng, H. Tian, H. Wu, F. Zhu, and J. Wu, “RGDAN: A random graph diffusion attention network for traffic prediction,” Neural Networks, vol. 172, p. 106093, Apr. 2024, doi: 10.1016/j.neunet.2023.106093.
  17. Ren, F. Zhang, Y. Sun, and Y. Liu, “A Novel Dual-Channel Temporal Convolutional Network for Photovoltaic Power Forecasting,” Energies, vol. 17, no. 3, p. 698, Feb. 2024, doi: 10.3390/en17030698.
  18. P. Subashini, T. T. Dhivyaprabha, and M. Krishnaveni, “Synergistic Fibroblast Optimization,” Artificial Intelligence and Evolutionary Computations in Engineering Systems, pp. 285–294, 2017, doi: 10.1007/978-981-10-3174-8_25.

CRediT Author Statement


The authors confirm contribution to the paper as follows:

Conceptualization: Sashi Kanth Betha, Pallavi L, Santosh Kumar Upadhyay, Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B; Methodology: Sashi Kanth Betha, Pallavi L and Santosh Kumar Upadhyay; Writing- Original Draft Preparation: Sashi Kanth Betha, Pallavi L, Santosh Kumar Upadhyay, Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B; Visualization: Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B; Investigation: Sashi Kanth Betha, Pallavi L and Santosh Kumar Upadhyay; Supervision: Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B; Validation: Sashi Kanth Betha, Pallavi L and Santosh Kumar Upadhyay; Writing- Reviewing and Editing: Sashi Kanth Betha, Pallavi L, Santosh Kumar Upadhyay, Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B; All authors reviewed the results and approved the final version of the manuscript.


Acknowledgements


Authors thank Reviewers for taking the time and effort necessary to review the manuscript.


Funding


No funding was received to assist with the preparation of this manuscript.


Ethics declarations


Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.


Availability of data and materials


Data sharing is not applicable to this article as no new data were created or analysed in this study.


Author information


Contributions

All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.


Corresponding author


Rights and permissions


Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/


Cite this article


Sashi Kanth Betha, Pallavi L, Santosh Kumar Upadhyay, Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B, “Crop Leaf Disease Prediction Using Graph Diffusion TCN with Fibroblast Optimization”, Journal of Machine and Computing, vol.5, no.3, pp. 1736-1744, July 2025, doi: 10.53759/7669/jmc202505137.


Copyright


© 2025 Sashi Kanth Betha, Pallavi L, Santosh Kumar Upadhyay, Satheesh Kumar S, Lakshmanarao A and KrishnaPrasad B. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.