AI-Based Model for Home Waste Separation Using Raspberry Pi 5 AI Kit

Editorial Board PCSS Journal; H. A. Mutar; I. R. N. ALRubeei; I. V. Svyd; Haider TH. Salim ALRikabi; Abdul Hadi M. Alaidi

doi:10.15330/pcss.27.1.44-51

Authors

H. A. Mutar College of Computer Science and Information Technology, Wasit University, Wasit, Iraq
I. R. N. ALRubeei Electrical Engineering Department, College of Engineering, Wasit University, Wasit, Iraq
I. V. Svyd Vasyl Stefanyk Carpathian National University, Ivano-Frankivsk, Ukraine; Ivan Kozhedub Kharkiv National Air Force University (KNAFU), Kharkiv, Ukraine
Haider TH. Salim ALRikabi Electrical Engineering Department, College of Engineering, Wasit University, Wasit, Iraq
Abdul Hadi M. Alaidi College of Computer Science and Information Technology, Wasit University, Wasit, Iraq

DOI:

https://doi.org/10.15330/pcss.27.1.44-51

Keywords:

Edge AI, Raspberry Pi 5, YOLOv5, WasteNet, real-time classification, recycling, sustainability

Abstract

Effective domestic waste separation is also very critical to enhancing recycling and minimizing environmental pollution. Manual sorting, however, is labor-intensive, prone to errors and not practical to be widely adopted. In this paper, a new AI-controlled system of waste separation at home is presented, the computational power of the Raspberry Pi 5 AI Kit is used. It is a system consisting of a large-resolution camera, a conveyor belt system, and an edge deployment-optimized YOLOv5s convolutional neural network (CNN). The model is trained on the WasteNet dataset, with 25, 000 annotated images of five waste types (plastic, paper, glass, metal, and organic) and the classification accuracy of the model is 95.2%, with an average precision of 95.0%, and the time required to make an inference is 45 ms per frame. On average, the system consumes 5.2 W of energy and is therefore a cost-effective and energy-efficient system that can be used to manage household waste. It is possible to compare it with previous work and reveal that this technology is more effective regarding accuracy and latency and can be used as the effective tool to prompt environmentally friendly waste separation.

References

S. Kaza, L. C.Yao, P. Bhada-Tata, & F. Van Woerden. What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050 (Washington DC, World Bank, 2018); https://doi.org/10.1596/978-1-4648-1329-0.

S. Nesmachnow, D. Rossit, and P. Moreno-Bernal, A Literature Review of Recent Advances on Innovative Computational Tools for Waste Management in Smart Cities. Urban Science 9(1), 16 (2025); https://doi.org/10.3390/urbansci9010016.

H. Lee, Smart Waste Sorting with ResNet-50 and Raspberry Pi. Environmental Technology, 33(2), 98 (2022).

A.H.M. Alaidi, et al. AI-based monkeypox detection model using Raspberry Pi 5 AI Kit. Sustainable Engineering and Innovation, 7(1), 1 (2025); https://doi.org/10.37868/sei.v7i1.id393.

X. Zhang, Automated Waste Classification with CNN and Raspberry Pi. Journal of Waste Management, 12(3), 345 (2020).

S. Kumar, and A. Patel, YOLO-based Waste Separation System Using Jetson Nano. International Journal of AI Applications, 14(4), 110 (2021).

F. Ahmed, Optimized YOLOv4-tiny for Real-time Waste Classification. IEEE Access, 11, 451 (2023).

A. Arishi, Real-Time Household Waste Detection and Classification for Sustainable Recycling: A Deep Learning Approach. Sustainability, 17(5), 1902 (2025). https://doi.org/10.3390/su17051902.

L. Chen, & J. Zhu, Water surface garbage detection based on lightweight YOLOv5. Scientific Reports, 14(1); (2024); https://doi.org/10.1038/s41598-024-55051-3.

S. Kunwar, B.R. Owabumoye, & A.S. Alade, Plastic Waste Detection Using Deep Learning: Insights from the WaDaBa Dataset. Industrial and Domestic Waste Management, 5(1), 1 (2025); https://doi.org/10.53623/idwm.v5i1.580.

H.A. Mutar, I.K. Yalwi, Y.S. Mezaal, H. Th. Salim ALRikabi, A.H.M. Alaidi, I.R. Niama ALRubeei, & A. Magdy, Investigation of AI with OpenCV-Python for Detecting Diabetes. У Lecture Notes in Networks and Systems, 217 (2025); https://doi.org/10.1007/978-3-031-82881-2_14.

K.N. Mahmood, et al. Lightweight Convolutional Neural Networks Based Automated Waste Classification: An Efficient and Scalable Approach for Edge Devices. SSRN. (2025); https://doi.org/10.2139/ssrn.5320568.

A.M. Alabdali, Blockchain based solid waste classification with AI powered tracking and IoT integration. Scientific Reports, 15(1), (2025); https://doi.org/10.1038/s41598-025-97030-2.

W. Qiu, C. Xie, and J. Huang. An improved EfficientNetV2 for garbage classification. in arXiv. (2025); https://doi.org/10.48550/arXiv.2503.21208.