TrashNeXt: Classification of recyclable water pollutants using deep transfer learning method

Q1 Environmental Science Case Studies in Chemical and Environmental Engineering Pub Date : 2025-06-01 Epub Date: 2024-12-24 DOI:10.1016/j.cscee.2024.101073
Jahid Tanvir , Sk. Tanzir Mehedi , Bikash Kumar Paul , Monir Morshed
{"title":"TrashNeXt: Classification of recyclable water pollutants using deep transfer learning method","authors":"Jahid Tanvir ,&nbsp;Sk. Tanzir Mehedi ,&nbsp;Bikash Kumar Paul ,&nbsp;Monir Morshed","doi":"10.1016/j.cscee.2024.101073","DOIUrl":null,"url":null,"abstract":"<div><div>An automatic waste classification system embedded with higher accuracy and precision of convolution neural network (CNN) model can significantly the reduce manual labor involved in recycling. The ConvNeXt architecture has gained remarkable improvements in image recognition. A larger dataset, called TrashNeXt, comprising 23,625 images across nine categories has been introduced in this study by combining and thoroughly analyzing various pre-existing datasets. The deep transfer learning (DTL)-based proposed model achieved the highest accuracy of 94.97% compared to other CNN models by applying image augmentation and comprehensively fine-tuning hyperparameters. Additionally, the trained and optimized weights are utilized to classify water-bound liter objects.</div></div>","PeriodicalId":34388,"journal":{"name":"Case Studies in Chemical and Environmental Engineering","volume":"11 ","pages":"Article 101073"},"PeriodicalIF":0.0000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Case Studies in Chemical and Environmental Engineering","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666016424004675","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/12/24 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"Environmental Science","Score":null,"Total":0}
引用次数: 0

Abstract

An automatic waste classification system embedded with higher accuracy and precision of convolution neural network (CNN) model can significantly the reduce manual labor involved in recycling. The ConvNeXt architecture has gained remarkable improvements in image recognition. A larger dataset, called TrashNeXt, comprising 23,625 images across nine categories has been introduced in this study by combining and thoroughly analyzing various pre-existing datasets. The deep transfer learning (DTL)-based proposed model achieved the highest accuracy of 94.97% compared to other CNN models by applying image augmentation and comprehensively fine-tuning hyperparameters. Additionally, the trained and optimized weights are utilized to classify water-bound liter objects.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
TrashNeXt:使用深度迁移学习方法对可回收水污染物进行分类
嵌入更高精度和精度的卷积神经网络(CNN)模型的自动垃圾分类系统可以显著减少回收过程中的人工劳动。ConvNeXt架构在图像识别方面取得了显著的进步。通过结合和彻底分析各种现有数据集,本研究引入了一个更大的数据集,称为TrashNeXt,包含9个类别的23,625张图像。基于深度迁移学习(DTL)的模型通过图像增强和综合微调超参数,与其他CNN模型相比,准确率达到了94.97%。此外,利用训练和优化的权重对受水约束的升物体进行分类。
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 去求助
来源期刊
Case Studies in Chemical and Environmental Engineering
Case Studies in Chemical and Environmental Engineering Engineering-Engineering (miscellaneous)
CiteScore
9.20
自引率
0.00%
发文量
103
审稿时长
40 days
期刊最新文献
Decision optimization for inorganic contaminants in water systems using ecological informatics for sustainable management TiO2-modified g-C3N4 nanocomposite for photocatalytic degradation of reactive red 120 in aqueous solution Investigation of particle accumulation under electrostatic effects in a circulating fluidized bed riser using CFD simulation and statistical experimental design and analysis Dynamic system modelling for the sustainability of the Organic Rankine Cycle (ORC) turbine industry in Indonesia Groundwater hydrochemistry and identification of nitrate pollution sources in the Ouémé Delta (Southern-Benin) using dual isotopes (15N–NO3 and 18O–NO3) and a Bayesian isotope mixing model
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1