EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis

Zirije Hasani iD, Jakup Fondaj iD, Dionesa Bytyqi, Sufjan Misini

PLOS One · 18.06.2026 · 21 (6) · e0349901

DOI: 10.1371/journal.pone.0349901 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 18.06.2026. Verfasst von Zirije Hasani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Science, University "Ukshin Hoti" Prizren, Prizren, Kosovo. Hauptthemen laut MEDLINE: Deep Learning, Plant Diseases. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agricultural disease monitoring remains a critical challenge in precision farming, particularly when deploying computer vision systems on resource-constrained platforms. This study presents a rigorous comparative evaluation of four deep learning architectures—ResNet50, DenseNet121, a Binarized Neural Network (BNN), and YOLOv8-cls—for multi-class plant disease classification using the PlantVillage dataset (15 classes). Unlike prior benchmarking studies, we incorporate statistical validation through repeated stratified experiments (5 runs) and report mean ± standard deviation for accuracy, precision, recall, and F1-score. Results show that while DenseNet121 achieves high classification accuracy (99.48)% ± 0.12), it exhibits significantly higher inference latency. The BNN achieves minimal latency but suffers substantial performance degradation (88.31% ± 0.45). YOLOv8-cls provides the best trade-off, achieving 99.64% ± 0.09 accuracy with low latency (3.3 ms ± 0.2). Statistical comparison using paired t-tests confirms that YOLOv8 significantly outperforms ResNet50 p < 0.05 while maintaining substantially lower inference time.We further discuss generalization limitations due to the controlled nature of PlantVillage and moderate claims regarding edge deployment feasibility based on model size and computational profiling. The study provides a statistically grounded and edge-aware benchmarking framework for plant disease classification models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPlant DiseasesClassification AlgorithmsConvolutional Neural NetworksNeural Networks, Computer

Autor:innen und Institutionen

  • Faculty of Computer Science, University "Ukshin Hoti" Prizren, Prizren, Kosovo.
  • Faculty of Mechanical and Computer Engineering, University "Isa Boletini" Mitrovica, Mitrovica, Kosovo.

ORCID-Profile: Zirije Hasani, Jakup Fondaj

Zitieren

APA

Hasani, Z., Fondaj, J., Bytyqi, D., & Misini, S. (2026). Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis. PLOS One, 21(6), e0349901. https://doi.org/10.1371/journal.pone.0349901

Vancouver

Hasani Z, Fondaj J, Bytyqi D, Misini S. Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis. PLOS One. 2026;21(6):e0349901. doi:10.1371/journal.pone.0349901

BibTeX
@article{Hasani2026,
  author = {Hasani, Zirije and Fondaj, Jakup and Bytyqi, Dionesa and Misini, Sufjan},
  title = {Comparative evaluation of deep learning models for plant disease classification with edge-aware performance analysis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0349901},
  doi = {10.1371/journal.pone.0349901}
}
Kostenlos starten →