Convolutional Neural Network and Support Vector Machine Models for Plastic Classification by Near-infrared Spectroscopy

ZHANG Wen-jie; JIAO An-ran; TIAN Jing; WANG Xiao-juan; WANG Bin; XU Xiao-xuan

doi:10.3969/j.issn.1004-4957.2021.07.013

您当前的位置：

首页 >

文章列表页 >

Convolutional Neural Network and Support Vector Machine Models for Plastic Classification by Near-infrared Spectroscopy

Experimental Techniques and Methods

- Convolutional Neural Network and Support Vector Machine Models for Plastic Classification by Near-infrared Spectroscopy
- Journal of Instrumental Analysis Vol. 40, Issue 7, Pages: 1062-1067(2021)
- 作者机构：
  
  1.南开大学物理科学学院弱光非线性光子学教育部重点实验室，天津 300071
  2.江苏大学食品与生物工程学院，江苏镇江 212013
  3.宁波海关技术中心，浙江宁波 315048
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1004-4957.2021.07.013
  CLC：
扫描看全文
张文杰,焦安然,田静等.卷积神经网络和支持向量机算法在塑料近红外光谱分类中的模型应用[J].分析测试学报,2021,40(07):1062-1067.

ZHANG Wen-jie,JIAO An-ran,TIAN Jing,et al.Convolutional Neural Network and Support Vector Machine Models for Plastic Classification by Near-infrared Spectroscopy[J].Journal of Instrumental Analysis,2021,40(07):1062-1067.
张文杰,焦安然,田静等.卷积神经网络和支持向量机算法在塑料近红外光谱分类中的模型应用[J].分析测试学报,2021,40(07):1062-1067. DOI： 10.3969/j.issn.1004-4957.2021.07.013.

ZHANG Wen-jie,JIAO An-ran,TIAN Jing,et al.Convolutional Neural Network and Support Vector Machine Models for Plastic Classification by Near-infrared Spectroscopy[J].Journal of Instrumental Analysis,2021,40(07):1062-1067. DOI： 10.3969/j.issn.1004-4957.2021.07.013.

摘要

机器学习算法的应用使得塑料自动分类成为可能，而废旧塑料的分类回收对保护环境、节约资源有重要意义。该文结合近红外光谱分析技术，比较了使用一维卷积神经网络（1D CNN）和多元散射处理后支持向量机算法（MSC－SVM）建模的效果，及对PP新生料、PP再生料、PE新生料、PE再生料4种塑料分类的准确率。基于100个塑料样本近红外光谱数据的分类结果表明，验证集上1D CNN模型准确率为91.5%，MSC－SVM模型准确率为90.8%。1D CNN模型用于识别PP和PE新生料时，准确率可达100%。证明1D CNN建模方法在小数据集上进行准确塑料分类是可行的。

Abstract

Nowadays it is possible to automatically classify plastic waste by machine learning algorithms， which is of great significance for protecting the natural environment and saving resources. To establish better plastic classification models， the performances of multiplicative scatter correction－support vector machines(MSC－SVM) model and one-dimensional convolutional neural network(1D CNN) model were compared in identifying 4 types of plastic in this paper， as well as the accuracies of NIRS technique for classifying PP new raw material， PP recycled material， PE new raw material and PE recycled material， respectively. Based on the spectra data of 100 plastic samples， the experiment results showed that in validation set， the accuracy for MSC－SVM model is 90.8% while that for 1D CNN model is 91.5%. Particularly， 1D CNN model provided excellent classification results in identifying PE and PP new raw material samples with the accuracies reached up to 100%， which indicated that 1D CNN model is efficient to classify different types of plastic on small dataset.

关键词

近红外光谱卷积神经网络支持向量机塑料分类

Keywords

near-infrared spectroscopyconvolutional neural networksupport vector machineplastic classification

references

European Plastics Converters. EuPC publishes results of its 2nd survey on the use of recycled plastics materials. ［2020－10－26］. ‍https：//www.‍plasticsconverters.‍eu/post/2019/01/10/eupc-publishes-results-of-its-2nd-survey-on-the-use-of-recycled-plastics-materialshttps://www.‍plasticsconverters.‍eu/post/2019/01/10/eupc-publishes-results-of-its-2nd-survey-on-the-use-of-recycled-plastics-materials.

Shent H， Pugh R J， Forssberg E. Resour. Conserv. Recycl.， 1999， 25（2）： 85－109.

Wang C Q， Wang H， Fu J G， Liu Y N. Waste Manage.， 2015， 41： 28－38.

Ruj B， Pandey V， Jash P， Srivastava V K. Int. J. Appl. Sci. Eng. Res.， 2015， 4（4）： 564－571.

Wahab D A， Hussain A， Scavino E， Mustafa M M， Basri H. Am. J. Appl. Sci.， 2006， 3（7）： 1924－1928.

Unnikrishnan V K， Choudhari K S， Kulkarni S D， Nayak R， Kartha V B， Santhosh C. RSC Adv.， 2013， 3（48）： 25872－25880.

Stefas D， Gyftokostas N， Bellou E， Couris S. Atoms， 2019， 7（3）： 79.

Wang Q， Wu X M， Chen L C， Yang Z， Fang Z. Appl. Spectrosc.， 2017， 71（11）： 2538－2548.

Allen V， Kalivas J H， Rodriguez R G. Appl. Spectrosc.， 1999， 53（6）： 672－681.

Bian X H， Yang S， Li L L， Guo Y G， Liu W. China Achiev. Sci. Technol.（卞希慧，杨盛，李露露，郭玉高，刘巍. 中国科技成果）， 2015， 2015（13）：10－12.

Kaihara M， Satoh M， Satoh M. Anal. Sci.， 2007， 23（7）： 921－924.

Wang D J， Zhou X Y， Jin T M， Hu X N， Zhong J E， Wu Q T. Spectrosc. Spectral Anal.（王多加，周向阳，金同铭，胡祥娜，钟娇娥，吴启堂. 光谱学与光谱分析），2004，24（2）： 447－450.

Yin F F， Yan L， Han Q X， Xu Y H. Environ. Eng.（尹凤福，闫磊，韩清新，徐衍辉. 环境工程）， 2017， 35： 134－138.

Zhu S C， Chen H H， Wang M M， Guo X M， Lei L， Jin G. Adv. Ind. Eng. Polym. Res.， 2019， 2： 77－81.

Zhang L， Ding X D， Hou R C. J. Anal. Methods Chem.， 2020， 2020（22）： 1－13.

Chen X Y， Chai Q Q， Lin N， Li X H， Wang W. Anal. Methods， 2019， 11（40）： 5118－5125.

Ng W， Minasny B， Montazerolghaem M， Padarian J， Ferguson R， Bailey S， McBratney A B. Geoderma， 2019， 352： 251－267.

Lu M Y， Yang K， Song P F， Shu R X， Wang L P， Yang Y Q， Liu H， Li J H， Zhao L L， Zhang Y H. Spectrosc. Spectral Anal.（鲁梦瑶，杨凯，宋鹏飞，束茹欣，王萝萍，杨玉清，刘慧，李军会，赵龙莲，张晔晖.光谱学与光谱分析），2018， 38（12）： 3724－3728.

Bakker E J， Rem P C， Fraunholcz N. Waste Manage.， 2009， 29（5）： 1712－1717.

Kumagai M， Suyama H， Sato T， Amano T， Ogawa N. J. Near Infrared Spectrosc.， 2002， 10（4）： 247－255.

Rinnan Å， Van Den Berg F， Engelsen S B. Trends Anal. Chem.， 2009， 28（10）：1201－1222.

Wang H Y， Li J H， Yang F L. Appl. Res. Comput.（汪海燕，黎建辉，杨风雷. 计算机应用研究）， 2014， 31（5）： 1281－1286.

Devos O， Ruckebusch C， Durand A， Duponchel L， Huvenne J P. Chemom. Intell. Lab. Syst.， 2009， 96（1）： 27－33.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods

Rapid Determination of Antioxidant Activity from Sargassum Fusiforme Using Near-infrared Spectroscopy Combined with Chemometrics

Selection of Near Infrared Spectral Wavelength Variables Based on Improved Whale Optimization Algorithm and Its Application

A Variable Selection Method for Near-infrared Spectroscopy Based on Iterative Shrinkage Window Bootstrapping Soft Shrinkage Algorithm

Related Author

No data

Related Institution

Technical Center，China Tobacco Chongqing Industrial Co.，Ltd.

School of Chemistry and Material Science，University of Science and Technology of China

Key Laboratory of Water Environment and Marine Biological Resources Protection of Zhejiang Province

College of Life and Environmental Science，Wenzhou University

Key Laboratory of Advanced Process Control for Light Industry（Ministry of Education），School of Internet of Things Engineering，Jiangnan University

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