Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion

Amid the accelerating pace of global urbanization, the volume of municipal solid garbage has surged dramatically, thereby demanding more efficient and precise garbage management technologies. In this paper, we introduce a novel garbage classification approach that leverages a dynamic graph neural ne...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhang Yang, Yuanqing Luo, Yingyu Yang, Shuang Kang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7688
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246466912026624
author Yuhang Yang
Yuanqing Luo
Yingyu Yang
Shuang Kang
author_facet Yuhang Yang
Yuanqing Luo
Yingyu Yang
Shuang Kang
author_sort Yuhang Yang
collection DOAJ
description Amid the accelerating pace of global urbanization, the volume of municipal solid garbage has surged dramatically, thereby demanding more efficient and precise garbage management technologies. In this paper, we introduce a novel garbage classification approach that leverages a dynamic graph neural network based on multimodal feature fusion. Specifically, the proposed method employs an enhanced Residual Network Attention Module (RNAM) network to capture deep semantic features and utilizes CIELAB color (LAB) histograms to extract color distribution characteristics, achieving a complementary integration of multimodal information. An adaptive K-nearest neighbor algorithm is utilized to construct the dynamic graph structure, while the incorporation of a multi-head attention layer within the graph neural network facilitates the efficient aggregation of both local and global features. This design significantly enhances the model’s ability to discriminate among various garbage categories. Experimental evaluations reveal that on our self-curated KRHO dataset, all performance metrics approach 1.00, and the overall classification accuracy reaches an impressive 99.33%, surpassing existing mainstream models. Moreover, on the public TrashNet dataset, the proposed method demonstrates equally outstanding classification performance and robustness, achieving an overall accuracy of 99.49%. Additionally, hyperparameter studies indicate that the model attains optimal performance with a learning rate of 2 × 10<sup>−4</sup>, a dropout rate of 0.3, an initial neighbor count of 20, and 8 attention heads.
format Article
id doaj-art-1bdc34c8019a44efa641dc15fa3ec1cd
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-1bdc34c8019a44efa641dc15fa3ec1cd2025-08-20T03:58:30ZengMDPI AGApplied Sciences2076-34172025-07-011514768810.3390/app15147688Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature FusionYuhang Yang0Yuanqing Luo1Yingyu Yang2Shuang Kang3School of Environmental and Chemical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Environmental and Chemical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Environmental and Chemical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Mechanical and Control Engineering, Baicheng Normal University, Baicheng 137000, ChinaAmid the accelerating pace of global urbanization, the volume of municipal solid garbage has surged dramatically, thereby demanding more efficient and precise garbage management technologies. In this paper, we introduce a novel garbage classification approach that leverages a dynamic graph neural network based on multimodal feature fusion. Specifically, the proposed method employs an enhanced Residual Network Attention Module (RNAM) network to capture deep semantic features and utilizes CIELAB color (LAB) histograms to extract color distribution characteristics, achieving a complementary integration of multimodal information. An adaptive K-nearest neighbor algorithm is utilized to construct the dynamic graph structure, while the incorporation of a multi-head attention layer within the graph neural network facilitates the efficient aggregation of both local and global features. This design significantly enhances the model’s ability to discriminate among various garbage categories. Experimental evaluations reveal that on our self-curated KRHO dataset, all performance metrics approach 1.00, and the overall classification accuracy reaches an impressive 99.33%, surpassing existing mainstream models. Moreover, on the public TrashNet dataset, the proposed method demonstrates equally outstanding classification performance and robustness, achieving an overall accuracy of 99.49%. Additionally, hyperparameter studies indicate that the model attains optimal performance with a learning rate of 2 × 10<sup>−4</sup>, a dropout rate of 0.3, an initial neighbor count of 20, and 8 attention heads.https://www.mdpi.com/2076-3417/15/14/7688multimodal feature fusionadaptive K-nearest neighbor algorithmdynamic graph neural networkgarbage classification
spellingShingle Yuhang Yang
Yuanqing Luo
Yingyu Yang
Shuang Kang
Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
Applied Sciences
multimodal feature fusion
adaptive K-nearest neighbor algorithm
dynamic graph neural network
garbage classification
title Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
title_full Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
title_fullStr Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
title_full_unstemmed Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
title_short Dynamic Graph Neural Network for Garbage Classification Based on Multimodal Feature Fusion
title_sort dynamic graph neural network for garbage classification based on multimodal feature fusion
topic multimodal feature fusion
adaptive K-nearest neighbor algorithm
dynamic graph neural network
garbage classification
url https://www.mdpi.com/2076-3417/15/14/7688
work_keys_str_mv AT yuhangyang dynamicgraphneuralnetworkforgarbageclassificationbasedonmultimodalfeaturefusion
AT yuanqingluo dynamicgraphneuralnetworkforgarbageclassificationbasedonmultimodalfeaturefusion
AT yingyuyang dynamicgraphneuralnetworkforgarbageclassificationbasedonmultimodalfeaturefusion
AT shuangkang dynamicgraphneuralnetworkforgarbageclassificationbasedonmultimodalfeaturefusion