Identification of Waste Textiles Based on PCA+KNN and kernel-PCA + KNN Algorithms

LI Ning-ning; LIU Zheng-dong; WANG Hai-bin; HAN Xi; LI Wen-xia

doi:10.12452/j.fxcsxb.24032104

您当前的位置：

首页 >

文章列表页 >

Identification of Waste Textiles Based on PCA+KNN and kernel-PCA + KNN Algorithms

Experimental Techniques and Methods | 更新时间：2024-07-08

- Identification of Waste Textiles Based on PCA+KNN and kernel-PCA + KNN Algorithms
- Journal of Instrumental Analysis Vol. 43, Issue 7, Pages: 1039-1045(2024)
- 作者机构：
  
  1.北京服装学院材料设计与工程学院，北京 100029
  2.北京服装学院服装艺术与工程学院，北京 100029
  3.即发集团染整厂，山东青岛 266200
  4.北京伟创英图科技有限公司，北京 100070
- 作者简介：
- 基金信息：
- DOI：10.12452/j.fxcsxb.24032104
  CLC： O657.3;TS106
- Published：15 July 2024，
  
  Received：21 March 2024，
  
  Revised：11 May 2024，
- 稿件说明：
扫描看全文
李宁宁,刘正东,王海滨,韩熹,李文霞.基于PCA+KNN和kernal-PCA+ KNN算法的废旧纺织物鉴别[J].分析测试学报,2024,43(07):1039-1045.

LI Ning-ning,LIU Zheng-dong,WANG Hai-bin,HAN Xi,LI Wen-xia.Identification of Waste Textiles Based on PCA+KNN and kernel-PCA + KNN Algorithms[J].Journal of Instrumental Analysis,2024,43(07):1039-1045.
李宁宁,刘正东,王海滨,韩熹,李文霞.基于PCA+KNN和kernal-PCA+ KNN算法的废旧纺织物鉴别[J].分析测试学报,2024,43(07):1039-1045. DOI： 10.12452/j.fxcsxb.24032104.

LI Ning-ning,LIU Zheng-dong,WANG Hai-bin,HAN Xi,LI Wen-xia.Identification of Waste Textiles Based on PCA+KNN and kernel-PCA + KNN Algorithms[J].Journal of Instrumental Analysis,2024,43(07):1039-1045. DOI： 10.12452/j.fxcsxb.24032104.

摘要

该研究采集了15类废旧纺织物的4 998张近红外谱图，以7∶3的比例分为训练集和验证集，并分别采用主成分分析（PCA）与核主成分分析（kernal-PCA）两种不同降维方法对数据进行降维，并选用余弦相似度（cosine）核作为kernal-PCA的最佳核函数，最后分别将PCA和kernal-PCA降维处理后的数据进行k-近邻算法（KNN）训练。结果表明，kernal-PCA +KNN的模型准确率（95.17%）优于PCA+KNN模型的准确率（92.34%）。研究表明，kernal-PCA +KNN算法可以实现15类废旧纺织物识别准确率的提升，为废旧纺织物在线近红外自动分拣提供有力的技术支撑。

Abstract

The study collected 4 998 near infrared spectra of 15 types of waste textiles，which were divided into a training set and a validation set in a ratio of 7∶3，and the data were downscaled using two different downscaling methods，namely principal component analysis（PCA） and kernal principal component analysis（kernal-PCA），respectively，and the cosine similarity（cosine） kernel was selected as the best kernel function for kernal-PCA. Finally the PCA and kernal-PCA dimensionality reduction processed data are trained by k-nearest neighbour algorithm（KNN） respectively. The results show that the model accuracy of kernal-PCA +KNN（95.17%） is better than that of PCA+KNN model（92.34%） . The study shows that the kernal-PCA +KNN algorithm can achieve the improvement of the recognition accuracy of 15 types of waste textiles，and provide a strong technical support for the online near infrared automatic sorting of waste textiles.

关键词

废旧纺织物主成分分析（PCA）核主成分分析（kernel-PCA）k-近邻算法（KNN）分类识别

Keywords

waste textilesprincipal component analysis（PCA）kernel principal component analysis（kernel-PCA）k-nearest neighbour（KNN） algorithmclassification recognition

references

Tomra. Waste Clothing Textile Sorting - Inside Sweden's Automated Fabric Sorting Plant SIPTex（陶朗. 废弃衣物纺织品分选—走进瑞典的自动化织物分选厂SIPTex）.［2024-02-21］. https：//www.tomra.cn/recycling/case-studies/siptex-textile-sorting/https://www.tomra.cn/recycling/case-studies/siptex-textile-sorting/.

Global Textile News. Fibersort Fabric Sorting Technology Promotes Textile Recycling Process（全球纺织资讯网. Fibersort布料分类技术推动纺织品循环再生进程）. ［2024-03-01］. https：//www.tnet.org.tw/Article/Detail/26615https://www.tnet.org.tw/Article/Detail/26615.

Zheng J H，Du Y J，Li W X，Liu Z D，Wang H P. J. Instrum. Anal.（郑佳辉，杜宇君，李文霞，刘正东，王华平. 分析测试学报），2020，39（11）：1365-1370.

Du W Q. Research on On-line Near-infrared Intelligent Identification and Efficient Sorting Technology of Waste Textiles. Beijing：Beijing Institute of Fashion Technology（杜文倩. 废旧纺织品在线近红外智能识别与高效分选技术研究. 北京：北京服装学院），2021.

Wang Y. Establishment of Online NIR Analysis Model and Prediction Test for Waste Textiles. Beijing：Beijing Institute of Fashion Technology（王悦. 废旧纺织品在线NIR分析模型的建立及预测检验. 北京：北京服装学院），2022.

Ke C Y，Liu L S，Lin H，Zhang R S. J. Fujian Coll. Eng. （柯程扬，刘丽桑，林赫，张荣升．福建工程学院学报），2021，19（6）：568-573.

Ma S P，Ju Z Y，Wang G. J. Xi'an Electron. Sci. Technol. Univ.（马素萍，巨志勇，王告. 西安电子科技大学学报），2019，32（11）：1-6.

FZ/T 01057.8-2012. Test Method for Identification of Textile Fibres. Part 8. Infrared Spectrometry. The People's Republic of China Textile Industry Standard（纺织纤维鉴别试验方法第8部分：红外光谱法. 中华人民共和国纺织行业标准）.

Tian Q，Ma X H，Yuan J J，Long Y，Hong W X，Lu Y Y. Food Ind. Sci. Technol.（田琼，马新华，袁俊杰，龙阳，洪武兴，卢韵宇. 食品工业科技），2021，42（9）：270-274.

Liu Z T，Xu J P，Wu M，Cao W H，Chen L F，Ding X W，Hao M，Xie Q. J. Comput.（刘振焘，徐建平，吴敏，曹卫华，陈略峰，丁学文，郝曼，谢桥. 计算机学报），2018，41（12）：2833-2851.

Yu L，Hong Y S，Geng L，Zhou Y，Zhu Q，Cao J J，Nie Y. Trans. Chin. Soc. Agric. Eng.（于雷，洪永胜，耿雷，周勇，朱强，曹隽隽，聂艳. 农业工程学报），2016，32（13）：95-102.

Li W P，Yang J，Wang G. Microelectron. Comput.（李卫平，杨杰，王钢. 微电子学与计算机），2020，32（4）：56-60.

Xiong Z M，Guo H Y，Wu Y X. Comput. Eng. Appl.（熊中敏，郭怀宇，吴月欣.计算机工程与应用），2021，57（14）：27-38.

Yin A J，Shi B，Tan J，Li H Z. Noise Vib. Control（尹爱军，石波，谭建，李海珠. 噪声与振动控制），2020，40（6）：128-133.

Zhang B H，Xia H X，Zhang Y，Gao Z G. Comput. Syst. Appl.（张碧洪，夏海霞，张宇，高志刚. 计算机系统应用），2023，32（6）：42-50 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Production Traceability and Product Quality Control of Commercially Available Dextromethorphan Hydrobromide Cough Syrup Based on Surface-enhanced Raman Spectroscopy

Related Author

WU Hao-ping

LIU Guo-kun

XU Yong-bin

WANG Ya-jun

TANG Li-chao

ZHENG Shu-feng

LUO Si-heng

XU Jing

Related Institution

College of the Environment and Ecology，Xiamen University

College of Chemistry and Chemical Engineering，Xiamen University

Xiamen Food and Drug Quality Inspection Institute

Address：100 Xianlie Middle Road, Guangzhou Postal code：510070
Tel：020-87684776,37656606 Fax：020-87684776 Email：fxcsxb@china.com
Technical support is provided by Beijing Founder electronics co., LTD 粤ICP备12017312号-3 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰