EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EcoReward: An Automated Deep Learning Framework for Recyclable Plastic Classification and Incentive Distribution Using YOLOv8

Arati Dandavate, Vedant Shete, Tanishq Kudale, Samarth Lokhande

International Journal of Scientific Research in Science, Engineering and Technology · 18.11.2026 · 13 (6) · 128-139

DOI: 10.32628/ijsrset2613610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 18.11.2026. Verfasst von Arati Dandavate und 3 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing consumption of plastic-based products and packaging poses significant challenges for municipal solid waste management. Conventional recycling workflows often depend on manual identification and segregation, which can cause delays, inconsistent classification, and contamination of recyclable streams, while the absence of immediate and transparent incentives may limit public participation. This paper presents EcoReward, an automated deep learning framework that couples recyclable-packaging detection with an incentive distribution mechanism. The system uses a custom-trained YOLOv8n detector to identify four packaging categories: PET bottles, HDPE containers, squeeze tubes, and UHT beverage cartons/multilayer packaging. A web-based interface and a Python FastAPI backend support image submission, object detection, visual annotation, reward calculation, and transaction recording. To suit limited cloud resources, the implementation applies client-side image resizing with HTML5 Canvas, CPU-based inference, and explicit memory management. Detected objects are passed to a class-dependent reward allocation model that awards Eco-Points according to the number and category of recognized items, and each transaction (detected counts, reward value, and timestamp) is stored in SQLite. Unlike image-level classification, EcoReward performs object-level detection and counting and links the output to a structured incentive workflow. The paper describes the architecture, theoretical background, mathematical reward model, implementation observations, and ethical considerations. Quantitative evaluation of detection performance on a documented test set is reserved for future work.

Zitieren

APA

Dandavate, A., Shete, V., Kudale, T., & Lokhande, S. (2026). EcoReward: An Automated Deep Learning Framework for Recyclable Plastic Classification and Incentive Distribution Using YOLOv8. International Journal of Scientific Research in Science, Engineering and Technology, 13(6), 128-139. https://doi.org/10.32628/ijsrset2613610

Vancouver

Dandavate A, Shete V, Kudale T, Lokhande S. EcoReward: An Automated Deep Learning Framework for Recyclable Plastic Classification and Incentive Distribution Using YOLOv8. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(6):128-139. doi:10.32628/ijsrset2613610

BibTeX
@article{Dandavate2026,
  author = {Dandavate, Arati and Shete, Vedant and Kudale, Tanishq and Lokhande, Samarth},
  title = {EcoReward: An Automated Deep Learning Framework for Recyclable Plastic Classification and Incentive Distribution Using YOLOv8},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2026},
  volume = {13},
  number = {6},
  pages = {128--139},
  doi = {10.32628/ijsrset2613610}
}
Kostenlos starten →