| Naslov: | Image-based waste classification using a hybrid deep learning architecture with transfer learning and edge AI deployment |
|---|
| Avtorji: | ID Verber, Domen (Avtor)
ID Grneva, Teodora (Avtor)
ID Dugonik, Jani (Avtor) |
|---|
| Datoteke: |  mathematics-14-01176.pdf (23,04 MB)
MD5: 7D2D17D27AFE73F31ED18C60315E1F72
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Članek v reviji |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
|
|---|
| Opis: | 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). |
|---|
| Ključne besede: | 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 |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 13.03.2026 |
|---|
| Datum sprejetja članka: | 28.03.2026 |
|---|
| Datum objave: | 01.04.2026 |
|---|
| Založnik: | MDPI |
|---|
| Leto izida: | 2026 |
|---|
| Št. strani: | 23 str. |
|---|
| Številčenje: | Vol. 14, no. 7, [article no.] 1176 |
|---|
| PID: | 20.500.12556/DKUM-97912  |
|---|
| UDK: | 004.8 |
|---|
| COBISS.SI-ID: | 276035075 |
|---|
| DOI: | 10.3390/math14071176 |
|---|
| ISSN pri članku: | 2227-7390 |
|---|
| Avtorske pravice: | © 2026 by the authors |
|---|
| Datum objave v DKUM: | 24.04.2026 |
|---|
| Število ogledov: | 487 |
|---|
| Število prenosov: | 7 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
