A data-driven fusion of deep learning and transfer learning for orange disease classification

In agriculture, early detection of crop diseases is imperative for sustainability and maximizing yields.  Rooted in Agriculture 4.0, our innovative approach  combines pre-trained Convolutional Neural Networks (CNNs) models with data-driven solutions to address global challenges related to water scarcity.  By integrating the combined $L_{1}/L_{2}$ regularization technique to our model layers, we enhance their flexibility, reducing the risk of the overfitting effect of the model.  In the orange dataset used in our experiments, we have 1790 orange images, including a class of fresh oranges and three disease categories.  Applied on this dataset for classification, our model exhibits notable performance, namely $92.17\%$ for CNN and $97.28\%$ for ResNet-50 model.  Evaluated across metrics like accuracy, precision, recall, F1-score, confusion matrix, and cross validation, our approach surpasses traditional classifiers, significantly contributing to smart agricultural and global food resilience amidst mounting water scarcity pressures.

multi-class classification
orange disease
water scarcity
Agriculture 4.0
data-driven
глибинне навчання
convolutional neural networks
transfer learning
ResNet-50
  1. Zhang D., Sial M. S., Ahmad N., Filipe A. J., Thu P. A., Zia-Ud-Din M., Caleiro A. B.  Water scarcity and sustainability in an emerging economy: A management perspective for future.  Sustainability.  13 (1), 144 (2020).
  2. Li S., Wu F., Duan Y., Singerman A., Guan Z.  Citrus greening: Management strategies and their economic impact.  HortScience.  55 (5), 604–612 (2020).
  3. Chlingaryan A., Sukkarieh S., Whelan B.  Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review.  Computers and Electronics in Agriculture.  151, 61–69 (2018).
  4. Fuentes A. F., Yoon S., Lee J., Park D. S.  High-performance deep neural network-based tomato plant diseases and pests diagnosis system with refinement filter bank.  Frontiers in Plant Science.  9, 1162 (2018).
  5. Saha R., Neware S.  Orange fruit disease classification using deep learning approach.  International Journal of Advanced Trends in Computer Science and Engineering.  9 (2), 2297–2301 (2020).
  6. Dhiman P., Kaur A., Hamid Y., Alabdulkreem E., Elmannai H., Ababneh N.  Smart Disease Detection System for Citrus Fruits Using Deep Learning with Edge Computing.  Sustainability.  15 (5), 4576 (2023).
  7. Chen J., Chen J., Zhang D., Sun Y., Nanehkaran Y. A.  Using deep transfer learning for image-based plant disease identification.  Computers and Electronics in Agriculture.  173, 105393 (2020).
  8. Zhang Y., Liu Y. P.  Identification of navel orange diseases and pests based on the fusion of DenseNet and self-attention mechanism.  Computational Intelligence and Neuroscience.  2021, 5436729 (2021).
  9. Barman U., Choudhury R. D., Sahu D., Barman G. G.  Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease.  Computers and Electronics in Agriculture.  177, 105661 (2020).
  10. Vasconez J. P., Delpiano J., Vougioukas S., Cheein F. A.  Comparison of convolutional neural networks in fruit detection and counting: A comprehensive evaluation.  Computers and Electronics in Agriculture.  173, 105348 (2020).
  11. Alom M. Z., Taha T. M., Yakopcic C., Westberg S., Sidike P., Nasrin M. S., Hasan M., Van Essen B. C., Awwal A. A., Asari V. K.  A state-of-the-art survey on deep learning theory and architectures.  Electronics.  8 (3), 292 (2019).
  12. Calin O.  Deep Learning Architectures – A Mathematical Approach.  Springer Series in the Data Sciences, Springer (2020).
  13. Wiatowski T., Bölcskei H.  A mathematical theory of deep convolutional neural networks for feature extraction.  IEEE Transactions on Information Theory.  64 (3), 1845–1866 (2017).
  14. Cao J., Pang Y., Li X., Liang J.  Randomly translational activation inspired by the input distributions of ReLU.  Neurocomputing.  275, 859–868 (2018).
  15. Sun R.  Optimization for deep learning: theory and algorithms.  Preprint arXiv:1912.08957 (2019).
  16. Zhang J.  Gradient descent based optimization algorithms for deep learning models training.  Preprint arXiv:1903.03614 (2019).
  17. Yang Q., Zhang Y., Dai W., Pan S. J.  Transfer Learning. Cambridge University Press (2020).
  18. He K., Zhang X., Ren S., Sun J.  Deep residual learning for image recognition.  2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770–778 (2016).