NAMMACITYFIX – FROM COMPLAINTS TO COMPLETION

The proposed NammaCityFix – From Complaint to Completion system effectively integrates deep learning and web-based technologies to provide a smart and efficient solution for civic issue reporting and management. Unlike traditional complaint systems that are often manual, time-consuming, and lack transparency, the proposed system enables users to report issues using images and location details, while automatically classifying and routing them to the appropriate departments. The implementation of a ResNet18-based deep learning model ensures reliable classification of various civic issues such as potholes, garbage, sewage, and electrical faults. The system also enhances user experience by providing real-time tracking, role-based dashboards for authorities, and timely status updates, improving both efficiency and accountability in the complaint handling process. However, certain challenges remain, including the need for larger and more diverse datasets to improve model generalization, handling variations in real-world image quality, and ensuring scalability for large-scale deployment. Additionally, further improvements can be made in optimizing response time and enhancing system accessibility across different platforms. The system also has some limitations that need to be considered. The classification model depends on the quality and size of the dataset, so the accuracy may reduce when images are unclear, taken in poor lighting, or contain more than one civic issue. In addition, real-time deployment would require stronger security, proper user authentication, reliable server hosting, and integration with actual municipal departments. These aspects are important before the system can be used on a large scale. In future, the system can be improved by adding more training images, supporting regional languages, developing a mobile application, and including analytics to identify complaint-prone areas. A feedback option can also be added so that users can confirm whether the complaint was resolved properly. These improvements would make the platform more useful for practical smart city applications. Future work will focus on expanding the  dataset,  improving  model  accuracy,  and integrating additional features such as mobile application support, multilingual interfaces, and advanced analytics for identifying high-risk civic areas. Overall, this project demonstrates the potential of AI-driven solutions in transforming urban governance by bridging the gap between citizens and authorities, enabling faster resolution of civic issues, and contributing to smarter and more responsive cities.

[1] “Smart Civic Issue Reporting System”, Dnyanesh Walwadkar, Jayesh Patil, Mujahid Hussain, Saurav Yadav, Department of Information Technology, Sinhgad College of Engineering, Pune, Maharashtra, India [2]  “Citizen Apps to Solve Complex Urban Problems” Kevin C. Desouza &Akshay Bhagwatwar, Published online: 10 Aug 2012 [3] “Citizen or customer? Complaints handling in the public sector” Brian Brewer, Department of Public and Social Administration, City University of Hong Kong, Volume 73, Issue, https://doi.org/10.1177/0020852307083457. [4] “CitySolution: A complaining task distributive mobile application for smart city corporation using deep learning”, Farhatun Shama, Abdul Aziz, Lamisa Bintee, Mizan Deya, https://doi.org/10.1016/j.softx.2024.101829 [5] Smart Civic Issue Reporting System Dnyanesh Walwadkar1, Jayesh Patil2, Mujahid Hussain3, Saurav Yadav4 International Journal of Advanced Research in Science, Communication and Technology (IJARSCT) Volume 2, Issue 1, March 2022 DOI: 10.48175/IJARSCT-2659 [6] Real-Time Garbage, Potholes and Manholes Monitoring System using Deep Learning Techniques Shahzia Sayyad; Shaily Parmar; Mrinalini Jadhav; Karan Khadayate 2020 4th International Conference on Trends in Electronics andInformatics(ICOEI)(48184) DOI: 10.1109/ICOEI48184.2020.9143030 [7] Urban drainage issues in developing countries by Carlos E.M. Tucci (capítulo do livro Urban Drainage in Humid Tropics que erá publicado pela UNESCO) [8] Building Virtual Drainage Systems Based on Open Road Data and Assessing Urban Flooding Risks by Haowen Li 1,Chuanjie Yan 1,Chun Zhou 2 andLi Zhou doi.org/10.3390/w18030341 [9]  AI-Enabled Participatory Governance for Sustainable Urban Problem Reporting Shivam Nikhra, Shubham Jaiswal Shreshtha Tudha , Kunj Bihari Meena and Vipin Tyagi DOI: 10.4018/979-8-3373-7804-6.ch002 [10]   A Deep Learning Framework for Real-Time Pothole Detection from Combined Drone Imagery and Custom Dataset Using Enhanced YOLOv8 and Custom Feature Extraction by Shiva Shankar Reddy https://doi.org/10.3390/math14050898 [11] A Crowdsourced Hyperlocal Alert Platform For Real- Time Civic Issue Reporting And Information Dissemination Glady Andrews  P; Kishor  Kumar  M  G; Marcian  Benedict D; C.S.Madhumathi DOI: 10.1109/GCWCN66157.2025.11447484