.png){kind=icon}
.png){kind=icon}
Return
Solid waste classification using deep neural network: A transfer learning approach
.png){kind=icon}
PRE
AI
DOI：10.1007/s12145-025-01743-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Effective solid waste classification is crucial for efficient waste management and environmental sustainability. Addressing this challenge is essential for improving urban quality of life. This study develops an accurate and efficient model for automatically classifying various types of solid waste. We leverage a large, annotated dataset of waste objects from diverse sources and apply state-of-theart deep learning techniques, including advanced architectures such as Xception, DenseNet, and EfficientNet. While previous studies have used computer vision for waste classification, our approach demonstrates the significant effectiveness of deep learning methods in solving this problem. By improving classification accuracy, our model aims to optimize waste management practices, contributing to a cleaner and more sustainable urban environment.
Keywords:
Solid waste classification
Deep neural networks
Computer vision
Deep learning
Ensemble model
Transfer learning
Xception model
Dense-net model
Exception model