期刊文献+

基于深度学习与边缘计算的垃圾分类方法

Garbage Classification Method Based on Deep Learning and Edge Computing
下载PDF
导出
摘要 垃圾分类回收对保护环境和节约资源具有重要意义。为实现高效快捷的垃圾分类,提出了基于深度学习与边缘计算技术的垃圾图像分类方法。首先,在ResNet基础上设计了适用于垃圾图像分类的深度学习模型GarbageCNet,实现基于图像的智能化垃圾分类。然后,将垃圾分类模型部署到边缘计算设备树莓派上,通过树莓派的摄像头模块采集垃圾图像,调用深度学习模型进行垃圾分类预测。实验结果表明,分类准确度最高到达96.33%,与基于VGG19模型的垃圾分类方法相比,分类准确度提高了4%且训练时间更少。相较于现有的垃圾分类神经网络模型,在垃圾种类较多的情况下,分类准确度更高。 Garbage classification and recycling is significant to environmental protection and resource conservation.In order to achieve efficient garbage classification,a garbage image classification method based on deep learning and edge computing technique is proposed.First of all,based on ResNet,a deep learning model GarbageCNet is designed to realize image-based intelligent garbage classification.Then,the garbage classification model is deployed to the edge computing device Raspberry Pi,and garbage images are collected with its camera module.The deep learning model is invoked for garbage classification prediction.Experimental results show that the classification accuracy can reach up to 96.33%.Compared with the garbage classification method based on VGG19,the classification accuracy is improved by 4% while the training takes less time.Compared with the existing garbage classification neural network models,the classification accuracy is higher when there are more types of garbage.
作者 吴琦 闫毕成 王晨晨 崔文旭 辛若腾 司广涛 WU Qi;YAN Bicheng;WANG Chenchen;CUI Wenxu;XIN Ruoteng;SI Guangtao(School of Computer Science,Qufu Normal University,Rizhao 276826)
出处 《计算机与数字工程》 2023年第9期2114-2118,共5页 Computer & Digital Engineering
基金 山东省自然科学基金面上项目(编号:ZR2020MF105)资助。
关键词 垃圾分类 ResNet 边缘计算 迁移学习 树莓派 garbage classification ResNet edge computing migration learning Raspberry Pi
  • 相关文献

参考文献10

二级参考文献139

  • 1岑瑶,赵烜赫,潘新,郜晓晶,刘霞.基于稀疏表示和HOG特征的掌纹识别方法[J].内蒙古农业大学学报(自然科学版),2020,41(1):76-80. 被引量:8
  • 2张星洲,鲁思迪,施巍松.边缘智能中的协同计算技术研究[J].人工智能,2019,0(5):55-67. 被引量:30
  • 3王依欣,胡冠九.我国城市生活垃圾分类问题及对策建议[J].产业与科技论坛,2020(9):200-201. 被引量:7
  • 4Ben-David S,Blitzer J,Crammer K,Pereira F.Analysis of representations for domain adaptation.In:Platt JC,Koller D,Singer Y,Roweis ST,eds.Proc.of the Advances in Neural Information Processing Systems 19.Cambridge:MIT Press,2007.137-144.
  • 5Blitzer J,McDonald R,Pereira F.Domain adaptation with structural correspondence learning.In:Jurafsky D,Gaussier E,eds.Proc.of the Int’l Conf.on Empirical Methods in Natural Language Processing.Stroudsburg PA:ACL,2006.120-128.
  • 6Dai WY,Xue GR,Yang Q,Yu Y.Co-Clustering based classification for out-of-domain documents.In:Proc.of the 13th ACM Int’l Conf.on Knowledge Discovery and Data Mining.New York:ACM Press,2007.210-219.[doi:10.1145/1281192.1281218].
  • 7Dai WY,Xue GR,Yang Q,Yu Y.Transferring naive Bayes classifiers for text classification.In:Proc.of the 22nd Conf.on Artificial Intelligence.AAAI Press,2007.540-545.
  • 8Liao XJ,Xue Y,Carin L.Logistic regression with an auxiliary data source.In:Proc.of the 22nd lnt*I Conf.on Machine Learning.San Francisco:Morgan Kaufmann Publishers,2005.505-512.[doi:10.1145/1102351.1102415].
  • 9Xing DK,Dai WY,Xue GR,Yu Y.Bridged refinement for transfer learning.In:Proc.of the Ilth European Conf.on Practice of Knowledge Discovery in Databases.Berlin:Springer-Verlag,2007.324-335.[doi:10.1007/978-3-540-74976-9_31].
  • 10Mahmud MMH.On universal transfer learning.In:Proc.of the 18th Int’l Conf.on Algorithmic Learning Theory.Sendai,2007.135-149.[doi:10,1007/978-3-540-75225-7_14].

共引文献741

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部