Junk Identification and Sorting Applications Based on Deep Residue Networks
DOI:
https://doi.org/10.53469/wjimt.2026.09(02).03Keywords:
ResNet18, Transfer learning, Deep learning, Dispose of wasteAbstract
With the advancement of technology, people are thinking more and more about technology and life. One of the major problems is the increasing capacity of urban waste disposal, so the policy of waste sorting (that is, the sorting of garbage in a prescribed order of order) has been introduced to demonstrate and realize the maximum economic value of garbage. Therefore, the sorting and recycling of garbage has great research value and significance. Therefore, solving the problem of garbage identification and classification has become our top priority. Based on this, the author designed a classification system based on ResNet18 network structure and transfer learning. Experiments have shown that based on this garbage sorting system model, the accuracy of garbage classification can reach more than 90%, which largely solves the problem of garbage identifying and sorting.
References
Hong Yu, Huican Liang, Shengfeng Fang, Xiafeng Peng. Innovation and operation mode of "old cattle" intelligent recycling machine [J]. Industrial Innovation Research, 2020 (18): 23-24.
Yu KangZhang, Wei Cai, Wenhao Chen, Mengqi Liu, Mengyao Tang. A review of research on intelligent classification system [J]. China Equipment Engineering, 2020 (09): 31-33.
Ziyuan Dong. Design and Research of Garbage Classification System Based on Deep Learning). 2020. Implementation [D]. University of Chinese Academy of Sciences (Shenyang Institute of Computing Technology, Chinese Academy of Sciences ).
Jin Ma, Jianzong Wang. Identification of Animal Body, Electronic Device and Readable Storage Medium [P]. Quang Dong Province: CN109919005A, 2019-06-21.
Shuxian Guan, Wancheng Ge. Research on speed bump recognition and its environmental impact based on ResNet18 [J]. Communication Technology, 2021,54 (03): 597- 603.
Zeshan Xu. Research on video action recognition based on deep Divine network [D]. South China University of Technology, 2019.
Pan S J, Yang Q A. A Survey on Transfer Learning[J]. Ieee Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.
Li M., Li Y., Lin M. Transfer Learning for Named Entity Recognition [J]. Computer Science and Exploration, 2021, 15 (02): 206-218.
Pan Zhenzhong. Research on Image Super-Resolution Reconstruction Model Based on Neural Network [D]. University of Science and Technology of China, 2020.