Comparative Analysis of CNN Architectures with Optuna-Assisted Hyperparameter Optimization for Classifying Drought-Stressed Soybean Seeds
FOOD ANALYTICAL METHODS, cilt.19, sa.10, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 19 Sayı: 10
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s12161-026-03204-7
- Dergi Adı: FOOD ANALYTICAL METHODS
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, Food Science & Technology Abstracts, INSPEC, Natural Science Collection (ProQuest), Biological Science Database (ProQuest)
- Erciyes Üniversitesi Adresli: Evet
Özet
The reduction in soybean yield and quality due to drought makes rapid and non-destructive grading at the seed level critical. In this study, five genotypes & times; four irrigation treatments (20 classes) were discriminated using RGB images in a scalable DL pipeline. ResNet-18, ConvNeXt-Tiny/Base, DenseNet-121, and EfficientNet-B1 were trained using transfer learning. HPO was performed with Optuna, and the accuracy, F1 score, ROC-AUC, and resource consumption were reported. On a held-out test set that was disjoint from model selection, EfficientNet-B1 achieved the best accuracy of 94.8% (AUC = 0.9990), followed by DenseNet-121 96.2% (AUC = 0.9993), ResNet-18 92.9% (AUC = 0.9985), ConvNeXt-Base 92.1% (AUC = 0.9981) and ConvNeXt-Tiny 94.0% (AUC = 0.9985). In terms of efficiency, ResNet-18 was balanced at 2232 s and 46.9 MB, with the lowest inference latency (15.5 ms). Grad-CAM foci pointed to the hilum, edge contours, and shell texture. The results showed that 20-class genotype & times; irrigation discrimination is possible with high accuracy using RGB images, while Grad-CAM provided qualitative support that the models generally focused on seed-related regions rather than background areas. EfficientNet-B1 is recommended when the highest accuracy with a small model footprint is required, whereas ResNet-18 provides the lowest latency on the tested workstation and may be a suitable candidate for future edge-device benchmarking. These capabilities point to potential future directions, including rapid pre-screening prototypes, human-in-the-loop active learning, multi-location validation, on-device inference tests, and RGB+NIR fusion, which remain to be demonstrated.