Nondestructive detection for adulteration of panax notoginseng powder based on hyperspectral imaging combined with arithmetic optimization algorithm-support vector regression

作     者：Zhang, Fujie Shi, Lei Li, Lixia Zhou, Yufeng Tian, Liquan Cui, Xiuming Gao, Yongping 

作者机构：Kunming Univ Sci & Technol Fac Modern Agr Engn Kunming 650500 Yunnan Peoples R China Key Lab Crop Harvesting Equipment Technol Zhejian Jinhua Zhejiang Peoples R China Yunnan Prov Key Lab Panaxnotoginseng Kunming Yunnan Peoples R China Yixintang Pharmaceut Grp Ltd Kunming Yunnan Peoples R China 

出 版 物：《JOURNAL OF FOOD PROCESS ENGINEERING》 (食品加工工程杂志)

年 卷 期：2022年第45卷第9期

页      面：e14096-e14096页

核心收录：

学科分类：0832[工学-食品科学与工程（可授工学、农学学位）] 0817[工学-化学工程与技术] 08[工学] 

基　　金：National Key Research and Development Program of China [2017YFC1702503] Major Science and Technology Project of Yunnan Province [202102AA310048] Project of Cloud Medicine Hometown [202102AA310045] Open project of Zhejiang Key Laboratory of crop harvesting equipment technology [2021KY05] 

主　　题：adulteration detection arithmetic optimization algorithm hyperspectral imaging Panax notoginseng powder support vector regression 

摘      要：Illegal merchants adulterate the powder of panax notoginseng rhizome and main root with the powder of panax notoginseng fibrous root, which reduces the efficacy and hygiene of panax notoginseng powder. To detect the adulteration of panax notoginseng powder nondestructively and rapidly, in this study, the hyperspectral images of 80 samples of adulterated rhizome powder and adulterated main root powder (AR & AM) were collected by using a hyperspectral image acquisition system (400-1000 nm). Then, Savitzky-Golay and standard normalized variable (SG-SNV) were used to preprocess the spectrum and improve the signal-to-noise ratio of the data. Next, competitive adaptive reweighed sampling (CARS) and iteratively retains informative variables (IRIV) methods were respectively adopted to select feature wavelengths from the spectra data after pretreatment. Subsequently, support vector regression (SVR) was used to establish the prediction models based on the selected variables and the full spectra data. Also, the arithmetic optimization algorithm (AOA) was used to optimize the parameters of the SVR model. The results showed that CARS-AOA-SVR was the optimal model for AR & AM, achieving RP2$$ {\mathrm{R}}_{\mathrm{P}}2 $$ of .9693 and .9667, RMSEP of .0266 and .0264, respectively. Therefore, the hyperspectral imaging combined with the CARS-AOA-SVR is a feasible method to detect the adulteration concentration of panax notoginseng powder. Practical Applications The traditional detection methods for adulteration of panax notoginseng powder depended on manual detection and chemical analysis. In order to detect the adulterated concentration of panax notoginseng powder rapidly and accurately, the adulterated panax notoginseng powder was studied based on hyperspectral imaging. The results showed that hyperspectral imaging combined with CARS-AOA-SVR model could be used to quantitatively detect the adulteration concentration of panax notoginseng powder, which could be a fast, accurate,