EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Statistically Indistinguishable Performance of Lightweight CNNs with Explainable AI for Robust Orchid Disease Classification

Pattharaphorn Intanasak, Dittapol Muntham, Wishanee Matthayom, Thaksina Khongsomlap, Montita Poodsongkram

Applied Sciences · 19.04.2026 · 16 (8) · 3974

DOI: 10.3390/app16083974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.04.2026. Verfasst von Pattharaphorn Intanasak und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Fund (FF) for the 2024 fiscal year from the Thailand Science Research and Innovation (TSRI) and Rajamangala University of Technology Suvarnabhumi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dendrobium Sonia orchid cultivation constitutes a vital commercial industry in Thailand; however, production remains persistently threatened by fungal and bacterial diseases. This study proposes a robust automated framework for orchid disease classification under conditions characterized by high visual uncertainty. A comparative analysis was conducted across four Convolutional Neural Network (CNN) architectures: ResNet-50 and three lightweight counterparts—MobileNetV3-Large, EfficientNetV2-B0, and NASNet-Mobile. All models were optimized using transfer learning, Cosine Decay scheduling, and EarlyStopping on a real-world dataset acquired from commercial orchid farms in Thailand. Experimental results indicate that ResNet-50 attained the highest overall performance (Accuracy: 98.96%, Macro F1: 0.9894, AUC-ROC: 0.9996), while EfficientNetV2-B0 achieved comparable results among the lightweight architectures (Accuracy: 98.47%, Macro F1: 0.9846, AUC-ROC: 0.9985). Importantly, statistical evaluation using the Wilcoxon Signed-Rank Test across five independent trials revealed no statistically significant difference between ResNet-50 and all three lightweight models (p > 0.05). This confirms the practical viability of deploying compact architectures on mobile platforms within smart farming systems without sacrificing diagnostic accuracy. Moreover, integrating Grad-CAM++ enhances interpretability by producing visual explanations that align with expert pathological assessments. This transparency effectively mitigates decision-making ambiguity and strengthens farmer confidence in adopting AI-driven precision agriculture.

Förderung

  • Fundamental Fund (FF) for the 2024 fiscal year from the Thailand Science Research and Innovation (TSRI) and Rajamangala University of Technology Suvarnabhumi

Zitieren

APA

Intanasak, P., Muntham, D., Matthayom, W., Khongsomlap, T., & Poodsongkram, M. (2026). Statistically Indistinguishable Performance of Lightweight CNNs with Explainable AI for Robust Orchid Disease Classification. Applied Sciences, 16(8), 3974. https://doi.org/10.3390/app16083974

Vancouver

Intanasak P, Muntham D, Matthayom W, Khongsomlap T, Poodsongkram M. Statistically Indistinguishable Performance of Lightweight CNNs with Explainable AI for Robust Orchid Disease Classification. Applied Sciences. 2026;16(8):3974. doi:10.3390/app16083974

BibTeX
@article{Intanasak2026,
  author = {Intanasak, Pattharaphorn and Muntham, Dittapol and Matthayom, Wishanee and Khongsomlap, Thaksina and Poodsongkram, Montita},
  title = {Statistically Indistinguishable Performance of Lightweight CNNs with Explainable AI for Robust Orchid Disease Classification},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {3974},
  doi = {10.3390/app16083974}
}
Kostenlos starten →