Smart City Gnosys

Smart city article details

Title	Intelligent Waste Management Using Wasteiqnet With Hierarchical Learning And Meta-Optimization
ID_Doc	32693
Authors	Tiwari S.; Bisht S.; Sharma K.
Year	2025
Published	IEEE Access, 13
DOI	http://dx.doi.org/10.1109/ACCESS.2025.3574095
Abstract	Effective waste management remains a critical pillar for sustainable urban development, particularly in rapidly growing regions like Delhi-NCR, where heterogeneous waste streams complicate classification. This study presents WasteIQNet, an intelligent, hierarchy-aware deep hybrid model for fine-grained waste classification across 18 categories structured under Wet and Dry waste types. The model integrates MobileNetV3 for semantic feature extraction with GraphSAGE to capture structural relationships among image representations. To address class imbalance and feature sparsity, the architecture incorporates Feature-wise Attention (FWA), Top-K Mixture of Experts (TopK-MoE), and advanced regularization techniques including Dynamic Sparse Training (DST) and Model-Agnostic Meta-Learning (MAML). We introduce a novel Hierarchical Tree Loss function to penalize semantically distant misclassifications by leveraging domain-specific waste hierarchy paths. The proposed framework is trained and evaluated on the WEDR dataset, a curated collection of 360,000 images reflecting real-world waste conditions across Delhi’s major landfill zones. WasteIQNet achieves a peak classification accuracy of 97.87%, demonstrating substantial improvements in both interpretability and generalization. This work contributes a scalable, robust, and deployment-ready solution tailored for real-time smart city waste segregation initiatives. © 2013 IEEE.
Author Keywords	Class imbalance handling; deep learning; dynamic sparse training; feature extraction; graph neural networks; hierarchical classification; meta-learning; mixture of experts; smart cities; waste management

Similar Articles

Id	Similarity	Authors	Title	Published
58394	0.927	Islam M.; Hasan S.M.M.; Rakib H.; Uddin P.; Mamun A.	Towards Sustainable Solutions: Effective Waste Classification Framework Via Enhanced Deep Convolutional Neural Networks	PLOS ONE, 20, 6 June (2025)
56836	0.922	Cai W.; Xie M.; Liu Y.; Yang X.	The Smart City Waste Classification Management System: Strategies And Applications Based On Computer Vision	Journal of Organizational and End User Computing, 36, 1 (2024)
4798	0.919	Lilhore U.K.; Simaiya S.; Dalal S.; Damaševičius R.	A Smart Waste Classification Model Using Hybrid Cnn-Lstm With Transfer Learning For Sustainable Environment	Multimedia Tools and Applications, 83, 10 (2024)
23601	0.916	Kabilan B.; Sairam R.; Praveen M.	Enhanced Cnn Architecture For Accurate Waste Classification In Smart Cities	Proceedings of 5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024 (2024)
7826	0.912	Saghana K.; Saranya P.; Mahesh Reddy A.; Keerthy Rai V.; Ramasubramanian B.; Sudhakaran P.	An Efficient Deep Learning Based Waste Management System For Sustainable Environment	3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025 (2025)
47322	0.91	Singh P.; Hasija T.; Ramkumar K.R.	Scalable Deep Learning Techniques For Automated Waste Segregation In Smart City Environments	2024 IEEE 8th International Conference on Information and Communication Technology, CICT 2024 (2024)
61435	0.909	Ruiz V.; Sánchez Á.; Vélez J.F.; Raducanu B.	Waste Classification With Small Datasets And Limited Resources	Intelligent Systems Reference Library, 224 (2022)
24091	0.906	Srizon A.Y.; Sarker A.; Mamun M.A.; Faruk M.F.; Hasan S.M.M.	Enhancing Waste Categorization Using Ensemble Of Transfer Learning And Light-Weight Convolutional Neural Network	2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023 (2023)
39264	0.906	Thirumalraj A.; Chandrashekar R.; Gunapriya B.; Balasubramanian P.K.	Nmra-Facilitated Optimized Deep Learning Framework: A Case Study On Iot-Enabled Waste Management In Smart Cities	Developments Towards Next Generation Intelligent Systems for Sustainable Development (2024)
51722	0.905	Cheema S.M.; Hannan A.; Pires I.M.	Smart Waste Management And Classification Systems Using Cutting Edge Approach	Sustainability (Switzerland), 14, 16 (2022)