EUVIMEDEUVIMED entdecken
Crossref

A multi-objective intelligent self-distilled lightweight network for explainable grape leaf disease recognition and decision support

Nidhi Sharma, Alok Misra, Raj Gaurang Tiwari

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology · 2026-12 · 50 (12) · 3887-3908

DOI: 10.1177/18758967261476523 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, online erschienen am 11.08.2026. Verfasst von Nidhi Sharma und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Grapevine foliar diseases require timely scouting, yet many image-based diagnostic models remain too demanding for routine edge deployment. This study presents MOHEOA–SDM-LiteNet , a lightweight, explainable classification framework for Black Rot, Esca, Leaf Blight, and Healthy grape leaves, evaluated on a public dataset of 9,027 images. The framework combines a MobileNetV2-derived search space, an auxiliary training exit with logit-level self-distillation, and multi-objective human evolutionary optimization over validation accuracy, inference latency, and parameter count. Methodological safeguards include perceptual-hash grouping, a post-split Hamming-distance audit, and an independent calibration split for temperature scaling. Representative pretrained backbones and focused ablations are evaluated using the same leakage-resistant partitions. The selected self-distilled model contains 0.54 million parameters and achieves 98.78% test accuracy, 0.9882 macro-F1, and an expected calibration error (ECE) of 0.0055, reduced to 0.0048 after temperature scaling. Across three matched seeds, the compact configuration without the auxiliary exit or self-distillation and the full model attain the same mean test accuracy (0.9893). The compact variant uses 0.338 million parameters and is therefore the recommended resource-efficient operating point, whereas the full model provides lower calibrated test ECE (0.00490 versus 0.00792) in every paired seed and is retained as a secondary calibration-oriented variant. Thus, self-distillation is not claimed to improve accuracy. Grad-CAM++ provides qualitative evidence that predictions often focus on symptomatic regions, without establishing formal lesion localization. Overall, the workflow offers a reproducible within-dataset framework for uncertainty-aware grape leaf decision support. Reported latency is a controlled CUDA-based efficiency proxy, not a device-specific deployment guarantee.

Zitieren

APA

Sharma, N., Misra, A., & Tiwari, R. G. (2026). A multi-objective intelligent self-distilled lightweight network for explainable grape leaf disease recognition and decision support. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 50(12), 3887-3908. https://doi.org/10.1177/18758967261476523

Vancouver

Sharma N, Misra A, Tiwari RG. A multi-objective intelligent self-distilled lightweight network for explainable grape leaf disease recognition and decision support. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology. 2026;50(12):3887-3908. doi:10.1177/18758967261476523

BibTeX
@article{Sharma2026,
  author = {Sharma, Nidhi and Misra, Alok and Tiwari, Raj Gaurang},
  title = {A multi-objective intelligent self-distilled lightweight network for explainable grape leaf disease recognition and decision support},
  journal = {Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology},
  year = {2026},
  volume = {50},
  number = {12},
  pages = {3887--3908},
  doi = {10.1177/18758967261476523}
}
Kostenlos starten →