Enhanced convolutional neural network methodology for solid waste classification utilizing data augmentation techniques

Waste Management Bulletin Pub Date : 2024-11-16 DOI:10.1016/j.wmb.2024.11.002

Daniel Hogan Itam , Ekwueme Chimeme Martin , Ibiba Taiwo Horsfall

{"title":"Enhanced convolutional neural network methodology for solid waste classification utilizing data augmentation techniques","authors":"Daniel Hogan Itam , Ekwueme Chimeme Martin , Ibiba Taiwo Horsfall","doi":"10.1016/j.wmb.2024.11.002","DOIUrl":null,"url":null,"abstract":"<div><div>The increasing volume of solid waste generated globally necessitates efficient classification systems to enhance recycling and waste management processes. Convolutional Neural Networks (CNNs) have emerged as a powerful tool for image classification tasks, including solid waste identification. However, difficult external variables including changes in illumination, occlusion, and background clutter can have a big impact on CNN performance. Furthermore, pooling procedures frequently cause classic CNNs to lose spatial information, which might impair performance on tasks requiring extremely fine sense of place. This paper presents a comprehensive study on the application of an improved CNN-based models for solid waste classification. In the present study we explored image data resizing, augmentation technique and hyperparameter tuning to improve the performance of the proposed model. The results demonstrate that the improved-CNN model achieved high accuracy of 94.40 % compared to the conventional CNN and other deep learning model such as ResNet-50, Inception-V3 and VGG-19 (81.83, 66.67, 52.83 and 56.00 %).</div></div>","PeriodicalId":101276,"journal":{"name":"Waste Management Bulletin","volume":"2 4","pages":"Pages 184-193"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Waste Management Bulletin","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949750724000920","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

The increasing volume of solid waste generated globally necessitates efficient classification systems to enhance recycling and waste management processes. Convolutional Neural Networks (CNNs) have emerged as a powerful tool for image classification tasks, including solid waste identification. However, difficult external variables including changes in illumination, occlusion, and background clutter can have a big impact on CNN performance. Furthermore, pooling procedures frequently cause classic CNNs to lose spatial information, which might impair performance on tasks requiring extremely fine sense of place. This paper presents a comprehensive study on the application of an improved CNN-based models for solid waste classification. In the present study we explored image data resizing, augmentation technique and hyperparameter tuning to improve the performance of the proposed model. The results demonstrate that the improved-CNN model achieved high accuracy of 94.40 % compared to the conventional CNN and other deep learning model such as ResNet-50, Inception-V3 and VGG-19 (81.83, 66.67, 52.83 and 56.00 %).

查看原文本刊更多论文

利用数据增强技术对固体废物进行分类的增强型卷积神经网络方法

全球产生的固体废物数量不断增加，需要高效的分类系统来加强回收和废物管理流程。卷积神经网络（CNN）已成为图像分类任务（包括固体废物识别）的强大工具。然而，光照变化、遮挡和背景杂波等难以解决的外部变量会对 CNN 的性能产生很大影响。此外，池化程序经常会导致经典 CNN 丢失空间信息，这可能会影响对位置感要求极高的任务的性能。本文对基于改进型 CNN 的固体废物分类模型的应用进行了全面研究。在本研究中，我们探索了图像数据大小调整、增强技术和超参数调整，以提高所提模型的性能。结果表明，与传统 CNN 和其他深度学习模型（如 ResNet-50、Inception-V3 和 VGG-19）（81.83%、66.67%、52.83% 和 56.00%）相比，改进型 CNN 模型的准确率高达 94.40%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Waste Management Bulletin

自引率

0.00%

发文量