Deep Neuro-Fuzzy for Disease Severity Estimationin Agricultural Potato Crops

Authors

  • Debraj Roy * Department of Computer Science, Tamralipta Mahavidyalaya, Tamluk, Purba Medinipur 721636, West Bengal, India.

https://doi.org/10.48314/tsc.v1i4.74

Abstract

Disease classification alone does not state how urgently a crop requires intervention. A deep neuro–fuzzy model is developed to convert image evidence into both a potato-blight class and a continuous severity score. A ResNet-18 backbone supplies visual representations, while a segmentation and quantification layer produces four measurable variables: lesion-area ratio, lesion density, chromatic degradation, and texture damage. These variables enter a normalized fuzzy rule system with interval-valued inputs. Monotonicity conditions, a Lipschitz perturbation bound, and an exact corner-enumeration bound are derived. On the supplied PlantVillagebased study split of 2,152 potato images, the classifier reports 98.6% accuracy, macro F1 of 0.970, weighted F1 of 0.986, and class AUC values of 1.000, 0.999, and 0.999. Severity estimation has MAE 13.41 and RMSE 16.54 on a 0–100 scale. The final output also assigns a clear plant-health status: Healthy, Mild, Moderate, Severe, or Critical. A worked leaf profile produces a score of
74.50 (Severe) with an input-uncertainty range of 70.91–77.56. The active fuzzy rules show how the pathological measurements determine the final score, while the controlled-image results are kept distinct from field performance. By providing both an estimate and an explanation, the method offers a practical tool for managing crop diseases.

Keywords:

Neuro–fuzzy system, Plant disease, Severity estimation, Interval analysis, Potato blight

References

  1. [1] Dang, M., Wang, H., Li, Y., Nguyen, T. H., Tightiz, L., Xuan-Mung, N., & Nguyen, T. N. (2024). Computer vision for plant disease recognition: A comprehensive review. The botanical review, 90(3), 251–311. https://doi.org/10.1007/s12229-024-09299-z
  2. [2] Pineda Medina, D., Miranda Cabrera, I., De La Cruz, R. A., Guerra Arzuaga, L., Cuello Portal, S., & Bianchini, M. (2024). A mobile app for detecting potato crop diseases. Journal of imaging, 10(2), 1-12. https://doi.org/10.3390/jimaging10020047
  3. [3] Santhana Krishnan, R., & Golden Julie, E. (2023). Computer aided detection of leaf disease in agriculture using convolution neural network based squeeze and excitation network. Automatika, 64(4), 1038–1053. https://doi.org/10.1080/00051144.2023.2241792
  4. [4] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in plant science, 7, 215232. https://doi.org/10.3389/fpls.2016.01419
  5. [5] Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and electronics in agriculture, 145, 311-318. https://doi.org/10.1016/j.compag.2018.01.009
  6. [6] Rehman, T. U., Ma, D., Wang, L., Zhang, L., & Jin, J. (2020). Predictive spectral analysis using an end-to-end deep model from hyperspectral images for high-throughput plant phenotyping. Computers and electronics in agriculture, 177, 105713. https://doi.org/10.1016/j.compag.2020.105713
  7. [7] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision (pp. 618-626). IEEE. https://doi.org/10.1109/ICCV.2017.74
  8. [8] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). " Why should i trust you?" Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144). ACM Digital Library. https://doi.org/10.1145/2939672.2939778
  9. [9] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (pp. 4765–4774). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
  10. [10] Zadeh, L. A. (1965). Fuzzy sets. Information and control, 8(3), 338-353. https://doi.org/10.1016/S0019-9958(65)90241-X
  11. [11] Jang, J. S. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685. https://doi.org/10.1109/21.256541
  12. [12] Sibiya, M., & Sumbwanyambe, M. (2021). Automatic fuzzy logic-based maize common rust disease severity predictions with thresholding and deep learning. Pathogens, 10(2), 1-17. https://doi.org/10.3390/pathogens10020131
  13. [13] Afzaal, H., Farooque, A. A., Schumann, A. W., Hussain, N., McKenzie-Gopsill, A., Esau, T., ... & Acharya, B. (2021). Detection of a potato disease (early blight) using artificial intelligence. Remote sensing, 13(3), 1-17. https://doi.org/10.3390/rs13030411
  14. [14] Meng, X., Tian, X., Wu, Q., Chen, Y., Pan, J., & Hang, Y. (2022). Meta-baseline based on deep neuro-fuzzy network for few-shot plant leaf fungal diseases recognition. The imaging science journal, 70(3), 168-180. https://doi.org/10.1080/13682199.2022.2164402
  15. [15] Sachdeva, G., Singh, P., & Kaur, P. (2021). Plant leaf disease classification using deep convolutional neural network with Bayesian learning. Materials today: Proceedings, 45, 5584-5590. https://doi.org/10.1016/j.matpr.2021.02.312
  16. [16] Rashid, J., Khan, I., Ali, G., Almotiri, S. H., AlGhamdi, M. A., & Masood, K. (2021). Multi-level deep learning model for potato leaf disease recognition. Electronics, 10(17), 1-27. https://doi.org/10.3390/electronics10172064
  17. [17] Kukreja, V., Baliyan, A., Salonki, V., & Kaushal, R. K. (2021). Potato blight: Deep learning model for binary and multi-classification. 2021 8th international conference on signal processing and integrated networks (SPIN) (pp. 967-972). IEEE. https://doi.org/10.1109/SPIN52536.2021.9566079
  18. [18] Aleynikov, A., & Gavrish, M. (2024). Method for identifying fungal diseases of cultivated plants using fuzzy logic. E3S web of conferences (Vol. 486, pp. 03011). EDP Sciences. https://doi.org/10.1051/e3sconf/202448603011
  19. [19] Azimi-Saghin, B., Omid, M., Rezvani, F., & Arefi, M. (2023). An algorithm to extract the defective areas of potato tubers infected with black scab disease using Fuzzy C Means clustering for automatic grading. Biomechanism and bioenergy research, 2(1), 32-39. https://doi.org/10.22103/bbr.2023.21783.1046
  20. [20] Yang, B., Wang, Z., Guo, J., Guo, L., Liang, Q., Zeng, Q., ... & Li, C. (2023). Identifying plant disease and severity from leaves: A deep multitask learning framework using triple-branch Swin Transformer and deep supervision. Computers and electronics in agriculture, 209, 107809. https://doi.org/10.1016/j.compag.2023.107809
  21. [21] Natarajan, S., Chakrabarti, P., & Margala, M. (2024). Robust diagnosis and meta visualizations of plant diseases through deep neural architecture with explainable AI. Scientific reports, 14(1), 13695. https://doi.org/10.1038/s41598-024-64601-8
  22. [22] Chen, F., Wu, B., Wu, P., Feng, Z., Ren, K., Li, Y., & Sun, H. (2026). An integrated imaging and deep learning system for automated detection and severity analysis of potato scab. Journal of food measurement and characterization, 20, 11821-11841. https://doi.org/10.1007/s11694-026-04433-4

Published

2025-12-12

Issue

Vol. 1 No. 4 (2025): Transactions on Soft Computing (TSC)

Section

Articles

License

Copyright (c) 2026 Transactions on Soft Computing

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Roy, D. (2025). Deep Neuro-Fuzzy for Disease Severity Estimationin Agricultural Potato Crops. Transactions on Soft Computing , 1(4), 247-256. https://doi.org/10.48314/tsc.v1i4.74

Similar Articles

1-10 of 15

You may also start an advanced similarity search for this article.