EUVIMEDEUVIMED entdecken
Vergleichsstudie

Filtering Out Defects in Open‐Source Meat Freshness Datasets: A New Leak‐Free Benchmark and a Comparative Analysis of Four Different Mobile Deep Learning Models

Ahmet Can Citak, Murat Koklu iD

Journal of Food Science · 2026-10 · 91 (10)

DOI: 10.1111/1750-3841.71554 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Food Science, online erschienen am 10.10.2026. Verfasst von Ahmet Can Citak und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Faculty of Technology, Selcuk University, Konya, Turkey. Hauptthemen laut MEDLINE: Deep Learning, Meat, Food Quality, Red Meat. Die Arbeit nennt 34 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image‐based, nondestructive classification of hourly meat‐freshness stages is important for food‐quality monitoring and supply‐chain management. However, detailed audits of open‐source datasets and their preprocessed subsets can reveal methodological defects that artificially inflate model performance. In this study, a Mendeley Data dataset for hourly meat‐freshness classification was audited at the file and original‐image levels. Two major defects were identified: The 36‐ and 48‐h beef classes contained byte‐identical images, as verified by MD5 hashes, and offline augmentation performed before data partitioning distributed variants of the same original images across the training, validation, and test sets, causing cross‐partition leakage. A leak‐free nine‐class benchmark containing 1849 verified original images was therefore constructed. The duplicated beef stages were represented as a single 36+ h beef class, whereas the distinct 36 and 48 h mutton stages were retained separately. MobileNetV3‐Large, EfficientNet‐B0, ShuffleNetV2, and MobileNetV2 were trained using online augmentation, focal loss, inverse‐frequency class weights, and five prespecified random seeds. MobileNetV3‐Large achieved the highest mean test accuracy (98.51% ± 0.58%) and macro F 1 score (98.54% ± 0.55%) and ranked first in four of five runs. However, its advantage over EfficientNet‐B0 was not significant in any seed‐wise exact McNemar comparison after Holm correction. These findings demonstrate the risks of uncritical reuse of open‐source datasets and provide a leakage‐controlled, reproducible basis for evaluating compact models intended for mobile and edge deployment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMeatFood QualityRed MeatAnimalsCattleBenchmarking

Stichwörter der Autor:innen

deep learningfood safetymeat freshness classification

Autor:innen und Institutionen

  • Department of Computer Engineering, Faculty of Technology, Selcuk University, Konya, Turkey.

ORCID-Profile: Murat Koklu

Zitieren

APA

Citak, A. C., & Koklu, M. (2026). Filtering Out Defects in Open‐Source Meat Freshness Datasets: A New Leak‐Free Benchmark and a Comparative Analysis of Four Different Mobile Deep Learning Models. Journal of Food Science, 91(10). https://doi.org/10.1111/1750-3841.71554

Vancouver

Citak AC, Koklu M. Filtering Out Defects in Open‐Source Meat Freshness Datasets: A New Leak‐Free Benchmark and a Comparative Analysis of Four Different Mobile Deep Learning Models. Journal of Food Science. 2026;91(10). doi:10.1111/1750-3841.71554

BibTeX
@article{Citak2026,
  author = {Citak, Ahmet Can and Koklu, Murat},
  title = {Filtering Out Defects in Open‐Source Meat Freshness Datasets: A New Leak‐Free Benchmark and a Comparative Analysis of Four Different Mobile Deep Learning Models},
  journal = {Journal of Food Science},
  year = {2026},
  volume = {91},
  number = {10},
  doi = {10.1111/1750-3841.71554}
}
Kostenlos starten →