New research by TSYS School student Md Nurullah and TSYS School faculty Rania Hodhod, Hyrum Carroll and Yi Zhou that aims to improve plant disease detection appears in the latest issue of Electronics. As the study indicates, plant diseases pose a significant threat to global food security, affecting crop yield, quality, and overall agricultural productivity. Traditionally, diagnosing plant diseases has relied on time-consuming visual inspections by experts, which can often lead to errors. Machine learning (ML) and artificial intelligence (AI), particularly Vision Transformers (ViTs), and Convolutional Neural Networks, offer a faster, automated alternative for identifying plant diseases through leaf image analysis. However, these models are often criticized for their “black box” nature, limiting trust in their predictions due to a lack of transparency. The TSYS School team's findings show that incorporating Explainable AI (XAI) techniques, such as Grad-CAM, Integrated Gradients, and LIME, significantly improves model interpretability, making it easier for practitioners to identify the underlying symptoms of plant diseases. With training accuracies of 100% for ViT, 96.88% for EfficientNetB7, 93.75% for EfficientNetB0, and 87.5% for ResNet50, along with corresponding validation accuracies of 96.39% for ViT, 86.98% for EfficientNetB7, and 82.00% for EfficientNetB0, their proposed models outperform earlier research on the same dataset. This demonstrates a notable improvement in model performance while maintaining transparency and trustworthiness through interpretable and reliable decision-making. According to Hodhod, "This work is the result of a master’s thesis project by Md. Nurullah . . . A big 'thank you' to the thesis committee, Hyrum Carroll and Yi Zhou, for their valuable contributions. I am proud of the excellent graduate research emerging from our program."
Comments
Post a Comment