计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240500057-7.doi: 10.11896/jsjkx.240500057
雷帅, 仇明鑫, 柳先辉, 张颖瑶
LEI Shuai, QIU Mingxin, LIU Xianhui, ZHANG Yingyao
摘要： 针对海量废弃家电回收图像数据在回收技术中难以有效利用的问题,提出了一种基于ResNet和多尺度卷积的废弃家电回收图像分类模型(Multi-scale and Efficient ResNet,ME-ResNet)。首先,基于残差结构设计了多尺度卷积模块以提升不同尺度特征信息提取能力,在此基础上基于ResNet设计了针对废弃家电回收图像分类问题的ME-ResNet模型;其次,通过用深度可分离卷积替换多尺度卷积中的部分卷积层,实现ME-ResNet模型轻量化;最后,通过与其他卷积神经网络的对比实验,对ME-ResNet及其轻量化模型的性能进行了验证。研究结果表明:相较于经典的卷积神经网络ResNet34,ME-ResNet及其轻量化模型均能有效提升识别准确度,针对构建的数据集,其最优准确率分别提升了1.2%和0.3%,宏精确率分别提升了1.7%和0.9%,宏召回率分别提升了1.3%和0.2%,宏F1分数分别提升了1.5%和0.5%。
中图分类号:
| [1]HAYAMI H,NAKAMURA M.An Economic Assessment of Present and Future Electronic-Waste Streams:Japan’s Experience[J].E-waste Recycling and Management,2020,33:40. [2]LI J.Recycling Materials from Waste Electrical and Electronic Equipment Selected papers from the 13th International Conference on Waste Management and Technology in Beijing,China[J].Frontiers of Environmental Science & Engineering,2017,11(5):14. [3]SANCHO-TOMÁS A,SUMNER M,ROBINSON D.Agener-alised model of electrical energy demand from small household appliances[J].Energy and Buildings,2017,135:350. [4]LIU J,BAI H,LIANG H,et al.How to recycle the small waste household appliances in China? A revenue-expenditure analysis[J].Resources,Conservation and Recycling,2018,137:292. [5]GAO P,FAN H,TAN C,et al.Research on recycling mode ofdiscarded household electrical appliance[C]//2009 International Conference on Information Management,Innovation Management and Industrial Engineering.IEEE,2009:171. [6]CHEN Y,YANG Y B,ZHANG Q.Reverse Logistics Network Design of Waste Household Appliances Based on the Third-Party Recovery[J].Mathematics in Practice and Theory,2016,46(17):81-89. [7]MINAEE S,BOYKOV Y,PORIKLI F,et al.Image Segmentation Using Deep Learning:A Survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3523-3542. [8]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNetclassification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90. [9]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//3rd International Conference on Learning Representations(ICLR 2015).2015:1-14. [10]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9. [11]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [12]YANG L,YU X,ZHANG S,et al.GoogLeNet based on residual network and attention mechanism identification of rice leaf diseases[J].Computers and Electronics in Agriculture,2023,204:107543. [13]PENG S,HUANG H,CHEN W,et al.More trainable inception-ResNet for face recognition[J].Neurocomputing,2020,411:9-19. [14]XU Q,LIANG Y L,WANG D Y,et al.Hyperspectral Image Classification Based on SE-Res2Net and Multi-Scale Spatial Spectral Fusion Attention Mechanism[J].Journal of Computer-Aided Design & Computer Graphics,2021,33(11):1726-1734. [15]SHREYAS MADHAV A V,RAJARAMAN R,HARINI S,et al.Application of artificial intelligence to enhance collection of E-waste:A potential solution for household WEEE collection and segregation in India[J].Waste Management & Research,2022,40(7):1047-1053. [16]HU S,ZHANG X,LIAO H,et al.Deep learning and machinelearning techniques to classify electrical and electronic equipment[C]//ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference.American Society of Mechanical Engineers,2021. [17]GAO S H,CHENG M M,ZHAO K,et al.Res2net:A newmulti-scale backbone architecture[J].IEEE transactions on pattern analysis and machine intelligence,2019,43(2):652-662. [18]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017. [19]BAGUI S,LI K.Resampling imbalanced data for network intrusion detection datasets[J].Journal of Big Data,2021,8(1):6. [20]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2017:2261-2269. [21]MA N,ZHANG X,ZHENG H T,et al.ShuffleNet V2:Practical Guidelines for Efficient CNN Architecture Design[C]//15th European Conference(ECCV 2018).2018:122-138. [22]FONTANA F,LANZINO R,MARINI M R,et al.DistilledGradual Pruning with Pruned Fine-tuning[J].IEEE Transactions on Artificial Intelligence,2024,5(8):4269-4279. |
|
||
首页