20.500.12556/DKUM-97912 Image-based waste classification using a hybrid deep learning architecture with transfer learning and edge AI deployment Growing amounts of municipal waste and the need for efficient recycling demand automated and accurate classification systems. This paper investigates deep learning approaches for multi-class waste sorting based on image data, comparing three widely used convolutional neural network architectures (ResNet-50, EfficientNet-B0, and MobileNet V3) with a custom hybrid model (CustomNet). The dataset comprises 13,933 RGB images across 10 waste categories, combining publicly available samples from the Kaggle Garbage Classification dataset (61.1%) with images collected in house (38.9%). The three glass sub-categories (brown, green, and white glass) were merged into a single glass class to ensure consistent class representation across all dataset splits. Preprocessing steps include normalization, resizing, and extensive data augmentation to improve robustness and mitigate class imbalance. Transfer learning is applied to pretrained models, while CustomNet integrates feature representations from multiple backbones using projection layers and attention mechanisms. Performance is evaluated using accuracy, macro-F1, and ROC–AUC on a held-out test set. Statistical significance was assessed using paired t-tests and Wilcoxon signed-rank tests with Bonferroni correction across five-fold cross-validation runs. The results show that CustomNet achieves 97.79% accuracy, a macro-F1 score of 0.973, and a ROC–AUC of 0.992. CustomNet significantly outperforms EfficientNet-B0 and MobileNet V3 (�<0.001 , Bonferroni corrected), and it achieves performance parity with ResNet-50 (�=0.383 ) at a substantially lower parameter count in the classification head (9.7 M vs. 25.6 M). These findings indicate that combining multiple feature extractors with attention mechanisms improves classification performance, supports qualitative model explainability via saliency visualization (Grad-CAM), and enables practical deployment on heterogeneous Edge AI platforms. Inference benchmarking on an NVIDIA Jetson Orin Nano demonstrated real-world deployment feasibility at 86.70 ms per image (11.5 FPS). waste classification image-based waste sorting deep learning convolutional neural networks hybrid neural networks transfer learning attention mechanisms Grad-CAM model explainability edge AI Jetson Orin environmental informatics circular economy razvrščanje odpadkov na podlagi slik globoko učenje konvolucijske nevronske mreže hibridne nevronske mreže prenosno učenje true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics © 2026 by the authors Članek v reviji 2026-04-24 13:18:33 2026-04-24 13:18:34 2026-04-25 03:09:23 0000-00-00 00:00:00 2026 0 0 23 str. no. 7, [article no.] 1176 Vol. 14 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2026-03-13 2026-03-28 2026-04-01 004.8 276035075 10.3390/math14071176 2227-7390 mathematics-14-01176.pdf mathematics-14-01176.pdf 1 7D2D17D27AFE73F31ED18C60315E1F72 d78c05999570de67b9919aee4ab6638825aafb968714045fb8732a8155d2dee0 b02fecd4-3fcf-11f1-903d-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=205615 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0