Near-Infrared Spectral Characteristic Extraction and Qualitative Analysis Method for Complex Multi-Component Mixtures Based on TRPCA-SVM

被引:7
作者
Zhang, Guiyu [1 ,2 ,3 ]
Tuo, Xianguo [2 ,3 ]
Zhai, Shuang [2 ]
Zhu, Xuemei [2 ]
Luo, Lin [2 ]
Zeng, Xianglin [2 ]
机构
[1] Southwest Univ Sci & Technol, Sch Informat Engn, 59 Qinglong Rd, Mianyang 621010, Sichuan, Peoples R China
[2] Sichuan Univ Sci & Engn, Sch Automat & Informat Engn, 1 Baita Rd, Yibin 644000, Peoples R China
[3] Artificial Intelligence Key Lab Sichuan Prov, 1 Baita Rd, Yibin 644000, Peoples R China
关键词
multi-component; near-infrared spectroscopy; characteristic extraction; difference spectrum; qualitative analysis; QUANTITATIVE DETECTION; VOLATILE COMPOUNDS; NIR SPECTROSCOPY; WINE; IDENTIFICATION; QUANTIFICATION; FEASIBILITY; CHEMOSENSOR; DESIGN;
D O I
10.3390/s22041654
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Quality identification of multi-component mixtures is essential for production process control. Artificial sensory evaluation is a conventional quality evaluation method of multi-component mixture, which is easily affected by human subjective factors, and its results are inaccurate and unstable. This study developed a near-infrared (NIR) spectral characteristic extraction method based on a three-dimensional analysis space and establishes a high-accuracy qualitative identification model. First, the Norris derivative filtering algorithm was used in the pre-processing of the NIR spectrum to obtain a smooth main absorption peak. Then, the third-order tensor robust principal component analysis (TRPCA) algorithm was used for characteristic extraction, which effectively reduced the dimensionality of the raw NIR spectral data. Finally, on this basis, a qualitative identification model based on support vector machines (SVM) was constructed, and the classification accuracy reached 98.94%. Therefore, it is possible to develop a non-destructive, rapid qualitative detection system based on NIR spectroscopy to mine the subtle differences between classes and to use low-dimensional characteristic wavebands to detect the quality of complex multi-component mixtures. This method can be a key component of automatic quality control in the production of multi-component products.
引用
收藏
页数:14
相关论文
共 35 条
[1]   Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE) [J].
Anowar, Farzana ;
Sadaoui, Samira ;
Selim, Bassant .
COMPUTER SCIENCE REVIEW, 2021, 40
[2]  
Bai J.S., 2019, ARXIV190208735V2
[3]   Tensor Robust Principal Component Analysis via Non-Convex Low Rank Approximation [J].
Cai, Shuting ;
Luo, Qilun ;
Yang, Ming ;
Li, Wen ;
Xiao, Mingqing .
APPLIED SCIENCES-BASEL, 2019, 9 (07)
[4]   Feasibility study on qualitative and quantitative analysis in tea by near infrared spectroscopy with multivariate calibration [J].
Chen, Quansheng ;
Zhao, Jiewen ;
Zhang, Haidong ;
Wang, Xinyu .
ANALYTICA CHIMICA ACTA, 2006, 572 (01) :77-84
[5]   Non-invasive detection of medicines and edible products by direct measurement through vials using near-infrared spectroscopy: A review [J].
Cui, Pengdi ;
Zhao, Jing ;
Liu, Ming ;
Qi, Minghui ;
Wang, Qiuyue ;
Li, Zheng ;
Suo, Tongchuan ;
Li, Gang .
INFRARED PHYSICS & TECHNOLOGY, 2021, 115
[6]   Quantitative spectral quality assessment technique validated using intraoperative in vivo Raman spectroscopy measurements [J].
Dallaire, Frederick ;
Picot, Fabien ;
Tremblay, Jean-Philippe ;
Sheehy, Guillaume ;
Lemoine, Emile ;
Agarwal, Rajeev ;
Kadoury, Samuel ;
Trudel, Dominique ;
Lesage, Frederic ;
Petrecca, Kevin ;
Leblond, Frederic .
JOURNAL OF BIOMEDICAL OPTICS, 2020, 25 (04)
[7]   Multiproduct, Multicomponent and Multivariate Calibration: a Case Study by Using Vis-NIR Spectroscopy [J].
dos Santos, Dayane Aparecida ;
de Lima, Karen Priscila ;
Cavalcante, Vinicius ;
Coqueiro, Aline ;
Barriquello Consolin, Marcilene Ferrari ;
Consolin Filho, Nelson ;
Marco, Paulo Henrique ;
Valderrama, Patricia .
FOOD ANALYTICAL METHODS, 2018, 11 (07) :1915-1919
[8]  
Driggs D., 2019, ARXIV190110991V1
[9]   Analysis of volatile compounds in Chinese Laobaigan liquor using headspace solid-phase microextraction coupled with GC-MS [J].
Du, Liping ;
He, Tingting ;
Li, Wei ;
Wang, Ruoyu ;
Xiao, Dongguang .
ANALYTICAL METHODS, 2015, 7 (05) :1906-1913
[10]   A feasibility study on the use of a miniature fiber optic NIR spectrometer for the prediction of volumic mass and reducing sugars in white wine fermentations [J].
Fernandez-Novales, Juan ;
Lopez, Maria-Isabel ;
Sanchez, Maria-Teresa ;
Garcia, Jose-Antonio ;
Morales, Jose .
JOURNAL OF FOOD ENGINEERING, 2008, 89 (03) :325-329