Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67425
Volume:
10 |
9 |
Sep 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 Technology
Priyadarshini Collage Of Engineering Nagpur
Computer Technology
Priyadarshini Collage Of Engineering Nagpur
Computer Technology
Priyadarshini Collage Of Engineering Nagpur
Computer Technology
Priyadarshini Collage Of Engineering Nagpur
Computer Technology
Priyadarshini Collage Of Engineering Nagpur
Computer Technology
Priyadarshini Collage Of Engineering Nagpur
Civic issues such as potholes, garbage overflow, water leakage, and manholes are common problems in urban areas and often suffer from delayed reporting, incorrect categorization, and lack of transparency. Samadhaan Setu is an AI-enabled Progressive Web App (PWA) designed to provide a smart and transparent civic issue reporting system. The proposed system captures the citizen's precise geographical location, including latitude and longitude, and allows the citizen to upload an image of the issue. A MobileNetV2-based image classification model using transfer learning is trained on approximately 4,132 images across five categories: pothole, garbage overflow, water leakage, manhole, and unknown. The trained model is converted to TensorFlow.js for integration with the web application and enables automatic classification and department-wise routing of reported issues. The system also provides separate administrative panels, complaint status tracking, time-based escalation for unresolved issues, city-wise visibility, and resolution evidence to improve accountability and transparency. Samadhaan Setu is designed to support multiple Indian cities and aims to improve communication between citizens and municipal authorities through the integration of artificial intelligence, geolocation, and digital civic management.
KEYWORDS
Samadhaan Setu provides an AI-enabled framework for civic issue reporting and management by integrating image classification, precise geolocation, automated department routing, complaint tracking, and transparency features. The MobileNetV2-based model achieved a best validation accuracy of 94.78% for five civic image categories. The proposed system can reduce manual complaint categorization and improve communication between citizens and municipal authorities. Resolution evidence, status tracking, and plan social-media integration further enhance transparency and public awareness. The system can be extended to multiple cities and additional civic services in the future.
[1] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510-4520. [2] M. Sandler and A. Howard, “MobileNetV2: The Next Generation of On-Device Computer Vision Networks,” Google Research, Apr. 3, 2018. [3] “A Bayesian Spatial Model to Correct Under-Reporting in Urban Crowdsourcing,” Proceedings of the AAAI Conference on Artificial Intelligence, 2024. [4] TensorFlow, “TensorFlow.js: Machine Learning for JavaScript,” TensorFlow Documentation. [5] “CitySolution: A complaining task distributive mobile application for smart city corporation using deep learning,” SoftwareX, vol. 27, 2024, Article 101829.
Publication Date
9/23/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
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...