| Title: | Image-based waste classification using a hybrid deep learning architecture with transfer learning and edge AI deployment |
|---|
| Authors: | ID Verber, Domen (Author)
ID Grneva, Teodora (Author)
ID Dugonik, Jani (Author) |
|---|
| Files: |  mathematics-14-01176.pdf (23,04 MB)
MD5: 7D2D17D27AFE73F31ED18C60315E1F72
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | 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). |
|---|
| Keywords: | 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 |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 13.03.2026 |
|---|
| Article acceptance date: | 28.03.2026 |
|---|
| Publication date: | 01.04.2026 |
|---|
| Publisher: | MDPI |
|---|
| Year of publishing: | 2026 |
|---|
| Number of pages: | 23 str. |
|---|
| Numbering: | Vol. 14, no. 7, [article no.] 1176 |
|---|
| PID: | 20.500.12556/DKUM-97912  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 2227-7390 |
|---|
| COBISS.SI-ID: | 276035075 |
|---|
| DOI: | 10.3390/math14071176 |
|---|
| Copyright: | © 2026 by the authors |
|---|
| Publication date in DKUM: | 24.04.2026 |
|---|
| Views: | 488 |
|---|
| Downloads: | 7 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
