Identification of Nephrite and Imitations Based on Terahertz Time-Domain Spectroscopy and Pattern Recognition

Hong-mei LIN; Qiu-hong CAO; Tong-jun ZHANG; Zhao-xin LI; Hai-qing HUANG; Xue-min LI; Bin WU; Qing-jian ZHANG; Xin-min LÜ; De-hua LI

doi:10.3964/j.issn.1000-0593(2021)11-3352-05

Spectroscopy and Spectral Analysis, Volume. 41, Issue 11, 3352(2021)

Identification of Nephrite and Imitations Based on Terahertz Time-Domain Spectroscopy and Pattern Recognition

Hong-mei LIN^1、*, Qiu-hong CAO^1、1;, Tong-jun ZHANG^1、1;, Zhao-xin LI^1、1;, Hai-qing HUANG^1、1;, Xue-min LI^1、1;, Bin WU^2、2;, Qing-jian ZHANG^3、3;, Xin-min LÜ^4、4;, and De-hua LI^{1、1; *;}

Author Affiliations

¹1. Qingdao Key Laboratory of Terahertz Technology, College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China

²2. The 41st Research Institute of CETC, Qingdao 266555, China

³3. Technology Center of Qingdao Customs, Qingdao 266002, China

⁴4. Technology Center of Alashankou Customs, Alashankou 833400, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Experimental schematic diagram of THz-TDS

Download full size

View in Article

$(a) Terahertz frequency spectrum, (b) refractive index of glass, marble, raw gemstone and Jades from Afghanistan, China’s Qinghai, Pakistan and China’s Xinjiang$

Fig. 2. (a) Terahertz frequency spectrum, (b) refractive index of glass, marble, raw gemstone and Jades from Afghanistan, China’s Qinghai, Pakistan and China’s Xinjiang

Download full size

View in Article

Fig. 3. Scores of the first and second principal components of jade samples from Afghanistan, China’s Qinghai, Pakistan and China’s Xinjiang and imitations

Download full size

View in Article

Fig. 4. Result of GridSearch-SVM parameter selection(optimal parameter c=2.828 4, g=2)

Download full size

View in Article

Fig. 5. Fitness curve of GA(optimal parameter c=1.740 1, g=4.544 6)

Download full size

View in Article

Fig. 6. Fitness curve of PSO(optimal parameter c=11.287 2, g=1.833 1)

Download full size

View in Article

Table 1. Variance contribution index and cumulative variance contribution index of each principal component of refractive index
View table
View in Article
Table 1. Variance contribution index and cumulative variance contribution index of each principal component of refractive index
成分方差贡献率/% 累计方差贡献率/%
PC1 66.192 66.192
PC2 26.861 93.053
PC3 3.844 96.897
PC4 1.511 98.408

Table 2. Comparison of three optimization methods of SVM combined with Gridsearch, GA and PSO

View table

View in Article

Table 2. Comparison of three optimization methods of SVM combined with Gridsearch, GA and PSO

优化方法	最优参数 c	最优参数 g	种群数量	迭代次数	建模耗时 /s	测试集准确率 /%
网格搜索法	2.828 4	2	20	200	1.39	97.7
遗传算法	1.740 1	4.544 6	20	200	3.60	98.3
粒子群算法	11.287 2	1.833 1	20	200	6.13	98.6

Tools

Get Citation

Copy Citation Text

Hong-mei LIN, Qiu-hong CAO, Tong-jun ZHANG, Zhao-xin LI, Hai-qing HUANG, Xue-min LI, Bin WU, Qing-jian ZHANG, Xin-min LÜ, De-hua LI. Identification of Nephrite and Imitations Based on Terahertz Time-Domain Spectroscopy and Pattern Recognition[J]. Spectroscopy and Spectral Analysis, 2021, 41(11): 3352

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Orginal Article

Received: Oct. 26, 2020

Accepted: --

Published Online: Dec. 17, 2021

The Author Email: LIN Hong-mei (1664741597@qq.com)

DOI:10.3964/j.issn.1000-0593(2021)11-3352-05

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Variance contribution index and cumulative variance contribution index of each principal component of refractive index

Table 1. Variance contribution index and cumulative variance contribution index of each principal component of refractive index

Table 2. Comparison of three optimization methods of SVM combined with Gridsearch, GA and PSO

Table 2. Comparison of three optimization methods of SVM combined with Gridsearch, GA and PSO