气候变化领域集成服务门户(CCPortal): Application of PCA-SVM and ANN Techniques for Plastic Identification by Raman Spectroscopy

CCPortal

DOI	10.1109/ICORIS.2019.8874880
	Application of PCA-SVM and ANN Techniques for Plastic Identification by Raman Spectroscopy
	Musu W.; Tsuchida A.; Kawazumi H.; Oka N.
发表日期	2019
起始页码	114
结束页码	118
英文摘要	The mechanical recycling of plastics is one of the most efficient approaches for reducing carbon dioxide emissions. Purification of the plastics from shredded waste materials requires versatile techniques, such as optical identification by Raman spectroscopy. The identification procedure demands the spectroscopy expertise to assign molecular structures from spectral peaks. In this study, we demonstrate applications to classify plastics using machine learning techniques under practical recycling industry conditions. Combining the techniques of principal component analysis (PCA) and support vector machine provides an accurate and robust classification of the valuable plastics of polypropylene, polystyrene, and acrylonitrile-butadiene-styrene copolymer. The identification accuracy remained above 95%, even with noise 3 times larger than the original intensity. For noise 10 times larger, the accuracy was more than 70%. Fast and simple computation is also useful for industrial applications, resulting from dimension reduction of the spectroscopic data by PCA Furthermore, artificial neural networks showed high accuracy, close to 100%, after a few epoch calculations. IEEE.
英文关键词	artificial neural networks; mechanical recycling; optical identification; principal component analysis; support vector machine
scopus关键词	ABS resins; Carbon dioxide; Elastomers; Global warming; Intelligent systems; Neural networks; Plastic products; Plastic recycling; Plastics applications; Plastics industry; Polypropylenes; Polystyrenes; Raman spectroscopy; Spectrum analysis; Styrene; Support vector machines; Acrylonitrile-butadiene-styrene copolymers; Carbon dioxide emissions; Identification accuracy; Identification procedure; Machine learning techniques; Mechanical recycling; Optical identification; Robust classification; Principal component analysis
来源期刊	2019 1st International Conference on Cybernetics and Intelligent System, ICORIS 2019
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/176376
作者单位	Department of Biological and Environmental Chemistry, Kindai University, Iizuka, Japan; Saimu Corporation, Iizuka, Japan
推荐引用方式 GB/T 7714	Musu W.,Tsuchida A.,Kawazumi H.,et al. Application of PCA-SVM and ANN Techniques for Plastic Identification by Raman Spectroscopy[J],2019.
APA	Musu W.,Tsuchida A.,Kawazumi H.,&Oka N..(2019).Application of PCA-SVM and ANN Techniques for Plastic Identification by Raman Spectroscopy.2019 1st International Conference on Cybernetics and Intelligent System, ICORIS 2019.
MLA	Musu W.,et al."Application of PCA-SVM and ANN Techniques for Plastic Identification by Raman Spectroscopy".2019 1st International Conference on Cybernetics and Intelligent System, ICORIS 2019 (2019).