Interpretable Deep Learning for <i>Varroa</i> Mite Detection: Integrating Deblurring, Morphology-Preserving Preprocessing, and Explainability Analysis
<i>Varroa destructor</i> is the most devastating ectoparasite of <i>Apis mellifera</i>, and early detection is critical for colony survival. This study systematically investigated how image preprocessing, model architecture, and feature map resolution jointly affect classification accuracy and Grad-...
Gardado en:
| Principais autores: | , , , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
MDPI AG
2026-07-01
|
| Series: | Agronomy |
| Assuntos: | |
| Acceso en liña: | https://www.mdpi.com/2073-4395/16/13/1292 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|