Enhancing Banana Leaf Disease Diagnosis Using Explainable AI on a Simple Convolutional Neural Network

  • Unique Paper ID: 183091
  • Volume: 12
  • Issue: no
  • PageNo: 106-110
  • Abstract:
  • While high-performance deep learning models have been applied to banana leaf disease detection [1][3], their interpretability remains underexplored. In this study, we deliberately use a baseline Convolutional Neural Network (CNN) with moderate accuracy to demonstrate how Explainable AI (XAI) techniques—such as Grad-CAM and SoftMax confidence analysis—can validate and interpret model predictions. We train a Global Average Pooling (GAP)-based CNN on the Banana LSD dataset [4] and observe a test accuracy of 74.7%. While more advanced models have reported higher performance [5], [6], our focus remains on interpretability and practical relevance. By integrating explainability techniques, we demonstrate that even a basic model can provide reliable support for disease diagnosis, especially in agricultural environments where transparency and resource efficiency are essential.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 12
  • Issue: no
  • PageNo: 106-110

Enhancing Banana Leaf Disease Diagnosis Using Explainable AI on a Simple Convolutional Neural Network

Related Articles