Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65318
Volume:
10 |
6 |
Jun 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Engineering
Zeal College of Engineering and Research
Computer Engineering
Zeal College of Engineering and Research
Computer Engineering
Zeal College of Engineering and Research
Computer Engineering
Zeal College of Engineering and Research
Computer Engineering
Zeal College of Engineering and Research
Rapid urbanization creates immense pressure on mu-nicipal solid waste management systems. Tradi-tional collection methods depend heavily on man-ual segregation and static reporting protocols, re-sulting in high operational costs, unhygienic condi-tions, and human error [10]. This paper presents the WALL.E Waste Classification System, an end-to-end cloud-based and AI-powered pipeline designed to automate municipal waste management. The pro-posed framework integrates a serverless computer vi-sion architecture using an enhanced Faster R-CNN with a Feature Pyramid Network (FPN) backbone to classify waste into Wet, Dry, E-Waste, and Mixed categories [5]. Furthermore, the system incorporates real-time geolocation tracking via GPS geotagging to perform area-wise spatial analytics, generating local-ized waste density heatmaps and identifying chronic dumping hotspots. Experimental results confirm that splitting operations into data-driven serverless clas-sification models and geographic aggregation mod-els dramatically reduces municipal oversight delays, advancing smart city resource allocation capabilities [13].
KEYWORDS
The WALL.E Waste Classification System demon-strates an effective framework for modern smart city sanitation by combining deep learning, cloud sys-tems, and area-wise geographic analytics. By uti-lizing a multi-scale Faster R-CNN and Feature Pyra-mid Network pipeline, the system reliably automates waste categorization. Decoupling computer vision processing from geospatial aggregation allows munic-ipal authorities to replace manual, reactive workflows with data-driven urban planning, identifying chronic waste hotspots and optimizing resource distribution across the city.
[1] Y. Zhang et al., “TAMER: Tree-Aware Trans-former for Handwritten Mathematical Expression Recognition,” AAAI, 2024. [2] R. Smith, “An Overview of the Tesseract OCR Engine,” ICDAR, 2007. [3] P. F. Proen¸ca and P. Sim˜oes, “TACO: Trash An-notations in Context for Litter Detection,” arXiv preprint arXiv:2003.06975, 2020. [4] D. Zeng, S. Zhang, F. Chen, and Y. Wang, “Multi-scale CNN based garbage detection of air-borne hyperspectral data,” IEEE Access, vol. 7, pp. 64568–64577, 2019, doi: 10.1109/AC-CESS.2019.2917539. [5] C. Cao, B. Wang, W. Zhang, X. Zeng, X. Yan, Z. Feng, Y. Liu, and Z. Wu, “An improved Faster R-CNN for small object detection,” IEEE Access, vol. 7, pp. 106838–106846, 2019, doi: 10.1109/ACCESS.2019.293273. [6] L. Jiao and J. Zhao, “A Survey on the New Gen-eration of Deep Learning in Image Processing,” IEEE Access, vol. 7, pp. 172231–172268, Dec. 2019, doi: 10.1109/ACCESS.2019.2956508. [7] W. Ma, X. Wang, and J. Yu, “A lightweight feature fusion single shot multibox detector for garbage detection,” IEEE Access, vol. 8, pp. 207646–207657, 2020, doi: 10.1109/AC-CESS.2020.3038880. [8] Z. Kang, J. Yang, G. Li, and Z. Zhang, “An Automatic Garbage Classification System Based on Deep Learning,” IEEE Access, vol. 8, pp. 140018–140030, Aug. 2020, doi: 10.1109/AC-CESS.2020.3010496. [9] N. C. A. Sallang, M. T. Islam, M. S. Islam, and H. Arshad, “A CNN-Based Smart Waste Manage-ment System Using TensorFlow Lite and LoRa-GPS Shield in Internet of Things Environment,” IEEE Access, vol. 9, pp. 153559–153571, Nov. 2021, doi: 10.1109/ACCESS.2021.3128314. [10] I. Sosunova and J. Porras, “IoT-Enabled Smart Waste Management Systems for Smart Cities: A Systematic Review,” IEEE Access, vol. 10, pp. 73325–73348, Jul. 2022, doi: 10.1109/AC-CESS.2022.3188308.
Publication Date
6/23/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...