Article Sidebar

Submitted
March 31, 2026
Accepted
July 3, 2026
Published
July 12, 2026
Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Automated waste classification is a critical component of intelligent recycling systems, where model selection must balance predictive performance and computational efficiency. This study benchmarks three representative convolutional neural network (CNN) backbones—ResNet50, EfficientNet-B0, and MobileNetV3-Large—for eight-class waste classification under controlled augmentation and unified optimization protocols. Using a fixed 80/10/10 split (7,747 training, 969 validations, and 960 testing images), all models are evaluated across multiple random seeds to ensure statistical reliability. Performance is assessed using macro-F1, precision, recall, and GPU-based inference latency to characterize the accuracy–efficiency trade-off. EfficientNet-B0 achieves the highest macro-F1 (0.9676 ± 0.0034), while MobileNetV3-Large delivers comparable performance (0.9669 ± 0.0023) with substantially lower latency—approximately six times faster than ResNet50. Augmentation sensitivity analysis further reveals architecture-dependent robustness under occlusion-based perturbation. These results demonstrate that lightweight architectures can achieve near-optimal classification performance with significantly reduced computational cost, providing deployment-oriented guidelines for practical waste sorting systems.

Keywords

Waste classification CNN backbones Accuracy–efficiency trade-off Inference latency Model benchmarking Deep learning

Article Details

License

Copyright (c) 2026 Mochamad Rizal Fauzan, Irgi Surya, Resa Pramudita

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Fauzan, M. R. ., Surya, I., & Pramudita, R. (2026). Accuracy–Efficiency Trade-off Analysis of CNN Backbones for Multi-Class Waste Classification. Jurnal Sains, Nalar, Dan Aplikasi Teknologi Informasi, 5(2), 108–117. https://doi.org/10.20885/snati.v5.i2.48169
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX

References

  1. M. Chhabra, B. Sharan, M. Elbarachi, and M. Kumar, “Intelligent waste classification approach based on improved multi-layered convolutional neural network,” Multimed. Tools Appl., vol. 83, no. 36, pp. 84095–84120, Nov. 2024, doi: 10.1007/s11042-024-18939-w. DOI: https://doi.org/10.1007/s11042-024-18939-w
  2. M. Nahiduzzaman et al., "An automated waste classification system using deep learning techniques: Toward efficient waste recycling and environmental sustainability," Knowledge-Based Syst., vol. 310, p. 113028, Feb. 2025, doi: 10.1016/j.knosys.2025.113028. DOI: https://doi.org/10.1016/j.knosys.2025.113028
  3. M. Diqi, “Waste Classification using CNN Algorithm,” Int. Conf. Inf. Sci. Technol. Innov., vol. 1, no. 1, pp. 130–135, Feb. 2022, doi: 10.35842/icostec.v1i1.17. DOI: https://doi.org/10.35842/icostec.v1i1.17
  4. M. Malik et al., “Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models,” Sustain., vol. 14, no. 12, Jun. 2022, doi: 10.3390/su14127222.
  5. W. Hurst et al., “Solid Waste Image Classification Using Deep Convolutional Neural Network,” Infrastructures 2022, Vol. 7, Page 47, vol. 7, no. 4, p. 47, Mar. 2022, doi: 10.3390/infrastructures7040047. DOI: https://doi.org/10.3390/infrastructures7040047
  6. J. J. C. Simbolon, Robet, and Hendri, “Household Waste Image Classification Using Deep Learning Model,” J. Artif. Intell. Eng. Appl., vol. 5, no. 1, pp. 1681–1690, Oct. 2025, doi: 10.59934/jaiea.v5i1.1690. DOI: https://doi.org/10.59934/jaiea.v5i1.1690
  7. L. S. Pieters, “Development of Automatic Waste Classification System using CNN-Based Deep Learning to Support Smart Waste Management,” INOVTEK Polbeng - Seri Inform., vol. 10, no. 1, pp. 214–224, Mar. 2025, doi: 10.35314/wst8mh87. DOI: https://doi.org/10.35314/wst8mh87
  8. D. R. Fauzi and G. A. H. D, “Comparison of CNN Models Using EfficientNetB0, MobileNetV2, and ResNet50 for Traffic Density with Transfer Learning,” J. Intell. Syst. Technol. Informatics, vol. 1, no. 1, pp. 22–30, Jun. 2025, doi: 10.64878/jistics.v1i1.6. DOI: https://doi.org/10.64878/jistics.v1i1.6
  9. X. Li and R. Grammenos, “Evaluation of practical edge computing CNN-based solutions for intelligent recycling bins,” IET Smart Cities, vol. 5, no. 3, pp. 194–209, Sep. 2023, doi: 10.1049/smc2.12057. DOI: https://doi.org/10.1049/smc2.12057
  10. Z. Qiao, “Advancing Recycling Efficiency: A Comparative Analysis of Deep Learning Models in Waste Classification,” Nov. 2024, Accessed: Mar. 01, 2026. [Online]. Available: http://arxiv.org/abs/2411.02779
  11. Y. Chen, Y. He, J. Lin, and S. Sun, “Garbage image recognition and classification based on CNN,” Appl. Comput. Eng., vol. 4, no. 1, pp. 416–421, May 2023, doi: 10.54254/2755-2721/4/20230507. DOI: https://doi.org/10.54254/2755-2721/4/20230507
  12. E. D. Cherpanath, P. R. Fathima Nasreen, K. Pradeep, M. Menon, and V. S. Jayanthi, “Food Image Recognition and Calorie Prediction Using Faster R-CNN and Mask R-CNN,” 9th Int. Conf. Smart Comput. Commun. Intell. Technol. Appl. ICSCC 2023, pp. 83–89, 2023, doi: 10.1109/ICSCC59169.2023.10335053. DOI: https://doi.org/10.1109/ICSCC59169.2023.10335053
  13. M. S. Minu, V. Priya Kasa, H. Ketharaman, V. Mandepudi, and S. Krishnaa, “Waste Classification Using Machine Learning Models: A Comparative Study,” 2026, doi: 10.5220/0013927500004919. DOI: https://doi.org/10.5220/0013927500004919
  14. G. Ahmad et al., “Intelligent waste sorting for urban sustainability using deep learning,” Sci. Reports 2025 151, vol. 15, no. 1, pp. 27078-, Jul. 2025, doi: 10.1038/s41598-025-08461-w. DOI: https://doi.org/10.1038/s41598-025-08461-w
  15. M. Castro-Bello et al., “Convolutional Neural Network Models in Municipal Solid Waste Classification: Towards Sustainable Management,” Sustain. 2025, Vol. 17, Page 3523, vol. 17, no. 8, p. 3523, Apr. 2025, doi: 10.3390/su17083523. DOI: https://doi.org/10.3390/su17083523
  16. A. Thakur, S. K. Biswas, S. Majumdar, and D. M. Thounaojam, “A Comprehensive Review on Different CNN Architectures,” 3rd Int. Conf. Intell. Data Commun. Technol. Internet Things, IDCIoT 2025, pp. 1997–2004, 2025, doi: 10.1109/IDCIOT64235.2025.10914792. DOI: https://doi.org/10.1109/IDCIOT64235.2025.10914792
  17. M. Rybczak and K. Kozakiewicz, “Deep Machine Learning of MobileNet, Efficient, and Inception Models,” Algorithms 2024, Vol. 17, Page 96, vol. 17, no. 3, p. 96, Feb. 2024, doi: 10.3390/a17030096. DOI: https://doi.org/10.3390/a17030096
  18. M. Ragazzi et al., “Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models,” Sustain. 2022, Vol. 14, Page 7222, vol. 14, no. 12, p. 7222, Jun. 2022, doi: 10.3390/su14127222. DOI: https://doi.org/10.3390/su14127222
  19. C. J. Yi and C. F. Kim, “AI-Powered Waste Classification Using Convolutional Neural Networks (CNNs),” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 10, pp. 67–75, Oct. 2024, doi: 10.14569/IJACSA.2024.0151009. DOI: https://doi.org/10.14569/IJACSA.2024.0151009
  20. C. Chen, N. A. Mat Isa, and X. Liu, “A review of convolutional neural network based methods for medical image classification,” Comput. Biol. Med., vol. 185, no. 2, p. 109507, Feb. 2025, doi: 10.1016/j.compbiomed.2024.109507. DOI: https://doi.org/10.1016/j.compbiomed.2024.109507
  21. L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of Image Classification Algorithms Based on Convolutional Neural Networks,” Remote Sens. 2021, Vol. 13, Page 4712, vol. 13, no. 22, p. 4712, Nov. 2021, doi: 10.3390/rs13224712. DOI: https://doi.org/10.3390/rs13224712
  22. X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev. 2024 574, vol. 57, no. 4, pp. 99-, Mar. 2024, doi: 10.1007/s10462-024-10721-6. DOI: https://doi.org/10.1007/s10462-024-10721-6