Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 12;25(14):4364.
doi: 10.3390/s25144364.

Autonomous Waste Classification Using Multi-Agent Systems and Blockchain: A Low-Cost Intelligent Approach

Sergio García González  1 , David Cruz García  1 , Rubén Herrero Pérez  1 , Arturo Álvarez Sanchez  1 , Gabriel Villarrubia González  1
Affiliations

Autonomous Waste Classification Using Multi-Agent Systems and Blockchain: A Low-Cost Intelligent Approach

Sergio García González et al. Sensors (Basel). .

Abstract

The increase in garbage generated in modern societies demands the implementation of a more sustainable model as well as new methods for efficient waste management. This article describes the development and implementation of a prototype of a smart bin that automatically sorts waste using a multi-agent system and blockchain integration. The proposed system has sensors that identify the type of waste (organic, plastic, paper, etc.) and uses collaborative intelligent agents to make instant sorting decisions. Blockchain has been implemented as a technology for the immutable and transparent control of waste registration, favoring traceability during the classification process, providing sustainability to the process, and making the audit of data in smart urban environments transparent. For the computer vision algorithm, three versions of YOLO (YOLOv8, YOLOv11, and YOLOv12) were used and evaluated with respect to their performance in automatic detection and classification of waste. The YOLOv12 version was selected due to its overall performance, which is superior to others with mAP@50 values of 86.2%, an overall accuracy of 84.6%, and an average F1 score of 80.1%. Latency was kept below 9 ms per image with YOLOv12, ensuring smooth and lag-free processing, even for utilitarian embedded systems. This allows for efficient deployment in near-real-time applications where speed and immediate response are crucial. These results confirm the viability of the system in both accuracy and computational efficiency. This work provides an innovative solution in the field of ambient intelligence, characterized by low equipment cost and high scalability, laying the foundations for the development of smart waste management infrastructures in sustainable cities.

Keywords: blockchain; intelligent classification; multi-agent systems; smart waste management.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Multi-agent system of the proposed architecture.
Figure 2
Figure 2
List of system components.
Figure 3
Figure 3
Electrical diagram of the system.
Figure 4
Figure 4
Final machine prototype.
Figure 5
Figure 5
Operation flow of the intelligent detection system.
Figure 6
Figure 6
Example of residue visualization on the blockchain.
Figure 7
Figure 7
YOLOv12 model architecture.
Figure 8
Figure 8
Confusion matrix generated for the YOLOv8 model.
Figure 9
Figure 9
Confusion matrix generated for the YOLOv11 model.
Figure 10
Figure 10
Confusion matrix generated for the YOLOv12 model.
Figure 11
Figure 11
Precision metric comparison.
Figure 12
Figure 12
Recall metric comparison.
Figure 13
Figure 13
F1 score metric comparison.
Figure 14
Figure 14
System web interface showing sorted waste and the filling status of containers using circular indicators.
Figure 15
Figure 15
Image of the recycling process, where waste is sorted and automatically redirected to its corresponding container.
Figure 16
Figure 16
Daily evolution of waste classification by type in each location.
Figure 17
Figure 17
Total daily waste sorting rate by location.
Figure 18
Figure 18
Average hourly frequency of recycling by location on the busiest day.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Wowrzeczka B. City of Waste—Importance of Scale. Sustainability. 2021;13:3909. doi: 10.3390/su13073909. - DOI
    1. Valentin A.P.M., Bonifacio P.B.S.D., Castro S.I.C.O., Ruiz J.C.A., Sy T.I.L., Trinidad E.L.O. Predicting Waste Management Behaviors Using an Extended Theory of Reasoned Action Model. Clean. Waste Syst. 2024;9:100193. doi: 10.1016/j.clwas.2024.100193. - DOI
    1. Bueno-Suárez C., Coq-Huelva D. Sustaining What Is Unsustainable: A Review of Urban Sprawl and Urban Socio-Environmental Policies in North America and Western Europe. Sustainability. 2020;12:4445. doi: 10.3390/su12114445. - DOI
    1. Campos-Alba C.M., Garrido-Rodríguez J.C., Plata-Díaz A.M., Pérez-López G. The Selective Collection of Municipal Solid Waste and Other Factors Determining Cost Efficiency: An Analysis of Service Provision by Spanish Municipalities. Waste Manag. 2021;119:11–20. doi: 10.1016/j.wasman.2021.07.039. - DOI - PubMed
    1. Ahmadi M., Karbassi A.R., Amrane A. A review of soil pollution around municipal solid waste landfills in Iran and comparable instances from other parts of the world. Int. J. Environ. Sci. Technol. 2024;21:4567–4585. doi: 10.1007/s13762-024-05728-z. - DOI

LinkOut - more resources