Research on the Visualization Differentiation of Atractylodes Lancea Granule Manufactures Based on Hyperspectral Imaging Technology Combined With the Selection of Characteristic Wavelengths
HUANG Ye1, LIU Li2, LIANG Jing2, YANG Hong-xia3, LI Xiao-li4, XU Ning2*
1. Department of Pharmacy, Zhejiang Skin Disease Prevention and Treatment Center, Deqing 313200, China
2. College of Pharmacy, Zhejiang University of Technology, Hangzhou 310014, China
3. Huzhou Institute of Food and Drug Inspection, Huzhou 313000, China
4. College of Food and Bioengineering, Zhejiang University, Hangzhou 310058, China
Abstract:In order to provide theoretical guidance for the visualization differentiation of Atractylodes Lancea granules based on hyperspectral imaging, competitive adaptive reweighted sampling (CARS) and correlation analysis (CA) was used to select two characteristic wavelengths. A new method for traceability of Atractylodes Lancea granules using near-infrared hyperspectral imaging technology was proposed. Hyperspectral image of 150 Atractylodes Lancea granules from three manufacturers in the range of 874~1 734 nm, extracting the spectral reflectance value of the region of interest (ROI) as the input variables for the identification model, and using the proximity algorithm (k-nearest neighbor, KNN), back-propagation neural networks (BPNN), partial least squares-discrimination analysis (PLS-DA) and least square support vector machine (LS-SVM) to establish discriminant models of four algorithms (classifiers). The discrimination effect of three different manufacturers of Atractylodes Lancea granules was discriminated by the evaluation criteria of the model effect (predictive set overall discriminant rate and kappa coefficient). Except for the KNN model, the discriminant rate of the prediction set was 100%, and the kappa coefficient was 1. In order to speed up the operation, this study selected the characteristic wavelengths by CARS, random frog (RF), successive projections algorithm (SPA) and sequential forward selection (SFS) algorithm, and used CARS, RF, SFS, and SPA combined with the CA algorithm to achieve four sets of optimal wavelengths. Four (975, 1 220, 1 419, 1 476 nm), two (1 005, 1 442 nm), four (924, 1 005, 1 419, 1 584 nm) and three (948, 1 146, 1 412 nm) optimal wavelengths were obtained respectively, and KNN, BPNN, PLS-DA, and LS-SVM discriminant models were established. Therefore, in the case of screening three optimal algorithms, the best modeling effect that can be obtained with fewer feature wavelengths was: the overall discriminant rate of the prediction set in the CARS-CA-LS-SVM model was 100%, the kappa coefficient was 1. Finally, the spectral data of each pixel of the wavelength variables selected by CARS-CA were input into the LS-SVM model, and the discrimination results were visually displayed in different colors. This study provides a method for the rapid and lossless traceability of Atractylodes Lancea granules product, and provides technical support for the rapid supervision of related organizations in the future.
黄 晔,刘 丽,梁 晶,杨红霞,李晓丽,徐 宁. 高光谱成像技术结合特征波长优化对苍术颗粒剂生产厂家的可视化判别研究[J]. 光谱学与光谱分析, 2020, 40(11): 3567-3572.
HUANG Ye, LIU Li, LIANG Jing, YANG Hong-xia, LI Xiao-li, XU Ning. Research on the Visualization Differentiation of Atractylodes Lancea Granule Manufactures Based on Hyperspectral Imaging Technology Combined With the Selection of Characteristic Wavelengths. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3567-3572.
[1] Wei Y, Sui D J, Xu H M, et al. Chinese Journal of Natural Medicines, 2017, 15(12): 905.
[2] Shi C, Qian J P, Zhu W Y, et al. Food Chemistry 2019, 275: 497.
[3] Zhou X, Sun J, Wu X H, et al. Spectrochimica Acta Part A: Molecular & Biomolecular Spectroscopy, 2019, 206: 378.
[4] Tankeu S, Vermaak I, Chen W Y, et al. Phytochemistry, 2016, 122: 213.
[5] LI Chao, HUANG Xian-zhang, ZHANG Chao-yun, et al(李 超, 黄显章, 张超云, 等). Journal of Chinese Medicinal Materials(中药材), 2019, 42(1): 51.
[6] Chu B Q, Yu K Q, Zhao Y R, et al. Sensors, 2018, 18(4): 1259.
[7] Liang J, Li X L, Zhu P P, et al. Applied Sciences, 2019, 9 (10): 2092.
[8] Zhao Y Y, Zhang C, Zhu S S, et al. Molecules, 2018, 23 (6): 1352.
[9] Zhang C, Liu F, He Y. Scientific Reports, 2018, 8: 2166.
[10] Weng H Y, Lv J W, Cen H Y, et al. Sensors and Actuators B: Chemical, 2018, 275: 50.
[11] Zhang C, Jiang H, Liu F, et al. Food and Bioprocess Technology, 2017, 10(1): 213.
[12] Zhao Y Y, Zhu S S, Zhang C, et al. RSC Advances, 2018, 8(3): 1337.
[13] Wu N, Zhang C, Bai X L, et al. Molecules, 2018, 23(11): 2831.
[14] Feng X P, Yu C L, Shu Z Y, et al. Fuel, 2018, 228: 197.