Enhancing detection of common bean diseases using Fast Gradient Sign Method–trained Vision Transformers
| dc.contributor.author | Mwaibale, Upendo | |
| dc.contributor.author | Mduma, Neema | |
| dc.contributor.author | Laizer, Hudson | |
| dc.contributor.author | Mgawe, Bonny | |
| dc.date.accessioned | 2025-09-15T13:11:22Z | |
| dc.date.issued | 2025-08-06 | |
| dc.description | SDG - 2 : Zero Hunger SDG - 3 : Good Health and Well-being SDG - 9 : Industry, Innovation, and Infrastructure SDG -12 : Responsible Consumption and Production SDG -13 : Climate Action | |
| dc.description.abstract | Common bean production in Tanzania is threatened by diseases such as bean rust and bean anthracnose, with early detection critical for effective management. This study presents a Vision Transformer (ViT)-based deep learning model enhanced with adversarial training to improve disease detection robustness under real- world farm conditions. A dataset of 100,000 annotated images augmented with geometric, color, and FGSM-based perturbations, simulating field variability. FGSM was selected for its computational efficiency in low-resource settings. The model, fine-tuned using transfer learning and validated through cross-validation, achieved an accuracy of 99.4%. Results highlight the effectiveness of integrating adversarial robustness to enhance model reliability for mobile-based plant disease detection in resource-constrained environments. | |
| dc.identifier.uri | https://doi.org/10.3389/frai.2025.1643582 | |
| dc.identifier.uri | https://dspace.nm-aist.ac.tz/handle/123456789/3242 | |
| dc.language.iso | en | |
| dc.publisher | Frontiers in Artificial Intelligence | |
| dc.subject | bean rust | |
| dc.subject | bean anthracnose | |
| dc.subject | deep learning | |
| dc.subject | Vision Transformers (ViT) | |
| dc.subject | adversarial attacks | |
| dc.subject | Fast Gradient Sign Method | |
| dc.title | Enhancing detection of common bean diseases using Fast Gradient Sign Method–trained Vision Transformers | |
| dc.type | Article |