Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194370,
        author = {kamalesh B and Elamaran V and Gobinathan K and Ramajayam A},
        title = {IntelliWaste: A Deep Learning-Powered Web Architecture for Real-Time Waste Classification and Sustainable Management},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4452-4458},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194370},
        abstract = {Accelerated urbanization and consumption habits have precipitated a global waste management crisis, demanding immediate technological intervention. Conventional manual sort- ing protocols are inherently inefficient, cost-prohibitive, and pose occupational hazards, failing to align with circular economy req- uisites. We propose IntelliWaste, a holistic AI-driven web platform engineered to automate the segregation of waste into Organic and Recyclable streams. The architecture synthesizes a high-precision convolutional neural network (CNN), fine-tuned via transfer learning on the ResNet50 backbone, with a resilient Django-based backend. The interface supports immediate classification through dual modalities: live webcam feeds and static image uploads. Trained on a consolidated dataset of public waste imagery, the model demonstrates a classification accuracy surpassing 95%. This study details the multi-tiered system design, the transfer learning methodology utilized for model optimization, the full- stack deployment pipeline, and a critical analysis of performance metrics. Additionally, we evaluate the socio-economic and ecolog- ical ramifications of such systems, highlighting their capacity to bolster recycling efficiency, mitigate landfill usage, and stimulate community participation in sustainability initiatives, thereby supporting the evolution of resilient smart city infrastructures.},
        keywords = {Artificial Intelligence, Waste Management, Deep Learning, Convolutional Neural Networks (CNN), Transfer Learning, Django, Real-Time Classification, Sustainable Devel- opment, Smart Cities, Circular Economy.},
        month = {March},
        }