Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis
Zirije Hasani, Jakup Fondaj, Dionesa Bytyqi, Sufjan Misini, Yile Chen, Yile Chen, Yile Chen, Yile Chen · 2026
Read Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis by Zirije Hasani, Jakup Fondaj, Dionesa Bytyqi, Sufjan Misini, Yile Chen, Yile Chen, Yile Chen, Yile Chen (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/PMC13278434.txt.
Description
Zirije Hasani leads a 2026 comparison of four deep learning models, computer vision programs, for classifying plant diseases from leaf images. The team used the PlantVillage dataset with fifteen disease classes and repeated each test five times for sound statistics. They also weighed speed, since farm devices often have weak hardware.
One model reached the highest accuracy, at about ninety-nine point six percent, with low response time, giving the best trade-off. A densely connected model was nearly as accurate but slower. A binarized model was fastest but dropped to about eighty-eight percent accuracy. The authors caution that the dataset's controlled photos limit how far results generalize to real fields.
Catalog record
| CREATOR | Zirije Hasani, Jakup Fondaj, Dionesa Bytyqi, Sufjan Misini, Yile Chen, Yile Chen, Yile Chen, Yile Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 76985 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |