基于拉曼光谱和DCGAN数据增强的珍珠粉掺伪检测研究

doi:10.3964/j.issn.1000-0593(2022)03-0769-07

摘要
参考文献
相关文章 (15)

全文: PDF (3617 KB)
输出: BibTeX | EndNote (RIS)

摘要：珍珠粉和珍珠层粉化学成分相似，但是珍珠层粉的药用价值远低于珍珠粉，并且珍珠层粉制备容易，成本底，常被不法商家用于冒充或掺入珍珠粉中流入市场，谋取利益。因此，对珍珠粉掺伪鉴别和纯度检测具有重要的意义。采用激光拉曼光谱结合深度学习研究珍珠粉掺伪快速鉴别和纯度分析。将纯珍珠粉和珍珠层粉按一定比例混合，制成珍珠粉质量百分数分别为0%，25%，50%，75%，80%，85%，90%，95%与100%共9种纯度270个模拟掺伪珍珠粉样本。然后对样本进行拉曼光谱采集，参数设置如下：分辨率为4.5 cm^-1，积分时间为3 000 ms，激光功率为20 mW。搭建了深度卷积生成式对抗神经网络(DCGAN)模型，对样本拉曼光谱进行数据增强；在此基础上，结合K近邻（K-nearest neighbor）、随机森林（random forest）、决策树（decision tree）、一维卷积神经网络(1D-CNN)4种分类器，对纯度为85%，90%，95%与100%的小比例掺伪样本进行真伪鉴别分析；同时，结合一维卷积神经网络对9种纯度的珍珠粉掺伪样本建立纯度预测的定量模型。结果表明：基于DCGAN数据增强方法所生成的拉曼光谱，与原始光谱相比，在峰值信噪比和结构相似度两个评价指标上均明显优于传统数据增强方法；在珍珠粉掺伪定性鉴别方面，DCGAN增强后的数据分别送入4种分类器，对4种小比例掺杂样本的真伪鉴别正确率均达到100%；在对9种掺伪纯度样本纯度检测方面，对测试集样本，DCGAN-1DCNN方法所建纯度定量预测模型性能最优，其决定系数R²为0.988 4，预测均方根误差RMSEP为0.034 8，一维卷积神经网络的损失值Loss为0.001 2，定量模型拟合最好。拉曼光谱结合DCGAN算法为珍珠粉掺伪鉴别及纯度检测提供一种快速简便的方法。深度卷积生成式对抗网络的数据增强方法在光谱分析技术领域具有重要的研究意义和应用价值。

关键词：生成式对抗网络；拉曼光谱；深度学习；珍珠粉掺伪；一维卷积神经网络

Abstract：The chemical composition of pearl powder and nacre powder is similar, However, the medicinal value of nacre powder is far lower than that of nacre powder, and nacre powder is easier to prepare at low cost, which is often used by illegal businesses to fake or mix into nacre powder to enter the market and seek illegal interests. Therefore, identifying pearl powder adulteration and purity analysis is of great significance. This paper used Raman spectroscopy combined with deep learning technology to study the rapid identification and purity analysis of pearl powder adulteration. The pure pearl powder and nacre powder were mixed according to a certain proportion to make 270 samples with 9 kinds of purity of 0%, 25%, 50%, 75%, 80%, 85%, 90%, 95% and 100% respectively. Then the Raman spectrum of the samples was collected, and the parameters were set as follows: the resolution is 4.5 cm^-1, the integration time is 3 000 ms, and the laser power is 20 mW. A Deep Convolutional Generative Adversarial Network (DCGAN) model was built to enhance the Raman spectra of the samples. Furthermore, K-nearest neighbor, Random forest, Decision tree, and one-dimensional convolution neural network (1DCNN) classifiers were used to identify the authenticity of a small proportion of adulterated samples with the purity of 85%, 90%, 95% and 100%. At the same time, a quantitative model for the purity prediction of 9 kinds of adulterated pearl powder samples was established by using a one-dimensional convolutional neural network. The results showed as follows: compared with the original spectral data, the Raman spectral data generated by the DCGAN data enhancement method was significantly better than the traditional data enhancement methods in the two evaluation indexes of peak signal-to-noise ratio and structural similarity. For the identification of pearl powder adulteration, the accuracies of the qualitative models established by DCGAN data enhancement method combing with four different classifiers have all reached 100%. For the quantitative detection of the purity of the pearl powders, the model established by DCGAN-1DCNN method has achieved the best performance. For the test set, the determination coefficient (R²) was 0.988 4 and the prediction root mean square error (RMSEP) was 0.034 8 as the loss value of 1DCNN network was 0.001 2. Raman spectroscopy combined with the DCGAN method provides a rapid and simple method for identifying and purity analysis of pearl powder adulteration. The data enhancement method of deep convolution generation countermeasure network has important research significance and application value in spectral analysis technology.

Key words：Generative adversarial network; Raman spectroscopy; Deep learning; Adulteration of pearl powder; One-dimensional convolutional neural networks

收稿日期: 2021-02-07 修订日期: 2021-04-19

中图分类号:

O657.3

基金资助: 国家重点研发计划项目（2019YFC1407904），河北省自然科学基金项目（2020203010）和国家自然科学基金项目（61971373）资助

通讯作者: 赵勇 E-mail: zhaoyong@ysu.edu.cn

作者简介: 谈爱玲，1978年生，燕山大学信息科学与工程学院副教授 e-mail: tanailing@ysu.edu.cn

引用本文:

谈爱玲，楚振原，王晓斯，赵勇. 基于拉曼光谱和DCGAN数据增强的珍珠粉掺伪检测研究[J]. 光谱学与光谱分析, 2022, 42(03): 769-775.
TAN Ai-ling, CHU Zhen-yuan, WANG Xiao-si, ZHAO Yong. Detection of Pearl Powder Adulteration Based on Raman Spectroscopy and DCGAN Data Enhancement. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 769-775.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2022)03-0769-07 或 https://www.gpxygpfx.com/CN/Y2022/V42/I03/769

[1] Chinese Pharmacopoeia Commission(国家药典委员会). Pharmacopoeia of the People’s Republic of China（Volume 1）(中华人民共和国药典(1部)). Beijing: Chemical Industry Press(北京: 化学工业出版社)，2018. 159.
[2] PU Yue-hua, HE Jin-feng, GAO Zhen-sheng, et al(蒲月华, 何锦锋, 高振声, 等). Food Research and Development(食品研究与开发), 2016, 37(16): 125.
[3] QIAO Yi-han, SUO Ya-ran, MENG Xue-dan, et al(乔艺涵，索亚然，孟雪丹，等). Chinese Journal of Pharmaceutical Analysis(药物分析杂志), 2019, 39(5): 911.
[4] Liu S Q, Wei W, Bai Z Y, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2018, 189(189): 265.
[5] Weng S Z, Zhu W X, Zhang X Y, et al. Artificial Intelligence in Agriculture, 2019, 3(9): 1.
[6] Meikun Fan, Gustavo F S. Andrade, et al. Analytica Chimica Acta, 2020, 1097: 1.
[7] Wang Dongqi, He Peisheng, Wang Zijian, et al. Current Opinion in Biotechnology, 2020, 64: 218.
[8] MING Jing, CHEN Long, CHEN Ke-li, et al(明晶, 陈龙, 陈科力, 等). China Journal of Traditional Chinese Medicine and Pharmacy(中华中医药杂志), 2017, 32(3): 1340.
[9] WANG Qing-rong, LI Xiao-yan, SUN Ying, et al(王清蓉, 李晓艳, 孙莹, 等). The Journal of Light Scattering(光散射学报), 2018, 30(4): 351.
[10] Félix Lussier, Vincent Thibault, Benjamin Charron, TrAC Trends in Analytical Chemistry, 2020, 124: 115796.
[11] Esben Jannik Bjerrum, Mads Glahder，Thomas Skov. arXiv: 2017, 1710. 01927v1.
[12] Frédéric Jamme, Ludovic Duponchel. Journal of Chemometrics, 2017, 31(5): e2882.
[13] ZHAO Yong, RONG Kang, TAN Ai-ling(赵勇, 荣康, 谈爱玲). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(12): 3755.
[14] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Advances in Neural Information Processing Systems, 2014, 27: 2672.