Waste Management Practices Through Deep Learning Classification Systems
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Efficient and effective waste management is a pressing global problem and requires disruptive solutions to mitigate waste disposal’s existing impact on the environment and society. Within this frame, automated waste classification using deep learning techniques has recently emerged as one of the promising methods for increasing the efficiency and accuracy of various processes. In this paper, the domain is systematically surveyed, covering primary components, including the importance of automated waste classification, the challenges in traditional approaches, and the responsibility of deep learning to change waste management practices. It then discusses the stage of waste classification systems of popular deep learning techniques/models and evaluation with key performance metrics. The review then looks at the limits of the approaches we currently have, including dataset variability, class imbalance, and computational efficiency and advances towards solving these problems. Finally, the survey identifies research gaps and suggests future directions, including sustainability-aware frameworks, multi-modal data integration, and resource-efficient system deployment for scalable real-time applications in various environments.
Fields of Study & Subjects
Advanced Neural Network Applications
Municipal Solid Waste Management
Waste Management and Recycling
Publication details
- Journal / source
- CRC Press eBooks
- Pages
- 139–146
- Publication date
- 26 March 2026
- Language
- EN
- Document type
- Book chapter