<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Аналіз сучасних рішень для автоматизованої класифікації твердих побутових відходів

Вантажиться...
Ескіз

Дата

Назва журналу

Номер ISSN

Назва тому

DOI

Анотація

The article examines modern methods for automatic classification of municipal solid waste, including visual, spectral, and hybrid approaches. It identifies key limitations of computer vision, NIR/MIR spectroscopy, and existing data-integration techniques. The need for transitioning to multimodal architectures is substantiated. A two-stage accuracy improvement strategy is proposed: optimized visual models based on ResNet-50/EfficientNet and fully integrated multimodal systems with attention modules. The paper outlines future development prospects, including the creation of realistic datasets and lightweight models for real-time operation.

Опис

Тип документа

Мова

ISSN

Бібліографічний опис

Моторний А. П., Кабачій В. В. Аналіз сучасних рішень для автоматизованої класифікації твердих побутових відходів // Матеріали Міжнародної науково-практичної інтернет-конференції «Молодь в науці: дослідження, проблеми, перспективи (МН-2026)», м. Вінниця, 22-26 червня 2026 р. Електрон. текст. дані. 2026. URI: https://conferences.vntu.edu.ua/index.php/mn/mn2026/paper/view/27203.

Схвалення

Рецензія

Доповнено

Цитується в

Список використаної літератури (14)

  1. Zhang, S., Chen, Y., Yang, Z., & Gong, H. (2021). Computer vision based two-stage waste recognitionretrieval algorithm for waste classification. Resources, Conservation and Recycling, 169, 105543. https://doi.org/10.1016/j.resconrec.2021.105543
  2. Liu, Y., Yao, W., Qin, F., Zhou, L., & Zheng, Y. (2023). Spectral classification of large-scale blended (micro) plastics using FT-IR raw spectra and image-based machine learning. Environmental Science & Technology, 57(16), 6656–6663. https://doi.org/10.1021/acs.est.2c08952
  3. Malik, M., Sharma, S., Uddin, M., Chen, C. L., Wu, C. M., Soni, P., & Chaudhary, S. (2022). Waste classification for sustainable development using image recognition with deep learning neural network models. Sustainability, 14(12), 7222. https://doi.org/10.3390/su14127222
  4. Varga, D. (2024). Understanding how image quality affects transformer neural networks. Signals, 5(3), 562–579. https://doi.org/10.3390/signals5030031
  5. Brenner, M., Reyes, N. H., Susnjak, T., & Barczak, A. L. (2023). RGB-D and thermal sensor fusion: A systematic literature review. IEEE Access, 11, 82410–82442. https://doi.org/10.1109/ACCESS.2023.3301119
  6. Itam, D. H., Martin, E. C., & Horsfall, I. T. (2024). Enhanced convolutional neural network methodology for solid waste classification utilizing data augmentation techniques. Waste Management Bulletin, 2(4), 184–193. https://doi.org/10.1016/j.wmb.2024.11.002
  7. Chomicki, A., Wоjcik, F., & Dudycz, H. (2025). Assessing the impact of dataset quality on the performance of artificial intelligence models in automatic waste classification. Procedia Computer Science, 270, 1061–1070. https://doi.org/10.1016/j.procs.2025.09.227 8. Saroth, M. A. F., Wijerathne, P. M. A. K., & Kumara, B. T. G. S. (2024, April). Automatic multi-class non-functional software requirements classification using machine learning algorithms. In Proceedings of the International Research Conference on Smart Computing and Systems Engineering (SCSE) (Vol. 7, pp. 1–6). IEEE. https://doi.org/10.1109/SCSE61872.2024.10550526
  8. Kazmi, M., Hafeez, B., Aftab, F., Shahid, J., & Qazi, S. A. (2023). A deep learning-based framework for visual inspection of plastic bottles. IEEE Access, 11, 125529–125542. https://doi.org/10.1109/ACCESS.2023.3329565
  9. Pavithra, K. C., Kumar, P., Geetha, M., & Bhandary, S. V. (2023). Comparative analysis of pre-trained resnet and densenet models for the detection of diabetic macular edema. Journal of Physics: Conference Series, 2571(1), 012006. https://doi.org/10.1088/1742-6596/2571/1/012006
  10. Boysen, N., Schwerdfeger, S., & Ulmer, M. W. (2023). Robotized sorting systems: Large-scale scheduling under real-time conditions with limited lookahead. European Journal of Operational Research, 310(2), 582–596. https://doi.org/10.1016/j.ejor.2023.03.037