EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Explainable CNN benchmark for snake fruit ripeness classification using grad-CAM visualization

Brian Rizqi Paradisiaca Darnoto, Sulisetijono Sulisetijono, Makhziah Makhziah, Ainun Nikmati Laily, Arif Yustian Maulana Noor

Bulletin of Electrical Engineering and Informatics · 01.12.2026 · 15 (6) · 5149-5161

DOI: 10.11591/eei.v15i6.13354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Electrical Engineering and Informatics, online erschienen am 01.12.2026. Verfasst von Brian Rizqi Paradisiaca Darnoto und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Snake fruit ripeness classification lacks both a standardized image dataset and a systematic multi-architecture convolutional neural network (CNNs) benchmark. This study addresses both gaps by constructing a dataset of 741 images (ripe and unripe, class-balanced in training and validation, imbalanced in test by design) through web scraping and large language model (LLM)-assisted annotation with confidence-based quality filtering, and by benchmarking five transfer learning architectures (VGG16, MobileNetV2, EfficientNetB0, DenseNet121, and ResNet50) with gradient-weighted class activation mapping (Grad-CAM) explainability on metrics relevant to field deployment, reporting results as mean ±95% confidence interval over five random seeds. DenseNet121 achieved the highest mean test accuracy (91.29%±1.67, F1: 0.9135±0.0166), closely followed by MobileNetV2 (90.82%±2.61) with the smallest model size (8.7 MB) and fastest practical inference among the mid-accuracy architectures (0.18 ms); confidence intervals overlap substantially across all five architectures, indicating no single architecture is statistically clearly superior on accuracy alone. Grad-CAM maps confirm that models attend to fruit surface texture rather than background. Dataset, trained models, and the annotation and evaluation pipeline are publicly released to support reproducible research on snake fruit quality assessment.

Zitieren

APA

Darnoto, B. R. P., Sulisetijono, S., Makhziah, M., Laily, A. N., & Noor, A. Y. M. (2026). Explainable CNN benchmark for snake fruit ripeness classification using grad-CAM visualization. Bulletin of Electrical Engineering and Informatics, 15(6), 5149-5161. https://doi.org/10.11591/eei.v15i6.13354

Vancouver

Darnoto BRP, Sulisetijono S, Makhziah M, Laily AN, Noor AYM. Explainable CNN benchmark for snake fruit ripeness classification using grad-CAM visualization. Bulletin of Electrical Engineering and Informatics. 2026;15(6):5149-5161. doi:10.11591/eei.v15i6.13354

BibTeX
@article{Darnoto2026,
  author = {Darnoto, Brian Rizqi Paradisiaca and Sulisetijono, Sulisetijono and Makhziah, Makhziah and Laily, Ainun Nikmati and Noor, Arif Yustian Maulana},
  title = {Explainable CNN benchmark for snake fruit ripeness classification using grad-CAM visualization},
  journal = {Bulletin of Electrical Engineering and Informatics},
  year = {2026},
  volume = {15},
  number = {6},
  pages = {5149--5161},
  doi = {10.11591/eei.v15i6.13354}
}
Kostenlos starten →