A hybrid SE-ResNet50 deep learning framework for high-accuracy and explainable cotton leaf disease classification
Emrah Aslan, Yıldırım Özüpak · 2026
Read A hybrid SE-ResNet50 deep learning framework for high-accuracy and explainable cotton leaf disease classification by Emrah Aslan, Yıldırım Özüpak (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13393842.txt.
Description
Emrah Aslan and Yıldırım Özüpak build a deep learning tool for cotton leaf disease in a 2026 study. Foliar disease and pest damage cut cotton yield and fiber quality, so fast, reliable, automated diagnosis matters for sustainable farming.
The hybrid model pairs a ResNet50 backbone with squeeze-and-excitation attention modules, trained on six disease classes with weighted loss and adaptive scheduling. It reached 99.72 percent training accuracy and 99.31 percent validation accuracy, converging by the fourteenth epoch. Heatmaps showed the model focusing on true symptom regions, aiding expert trust in field use.
Catalog record
| CREATOR | Emrah Aslan, Yıldırım Özüpak |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |