基于LLE-RF的中药三维荧光光谱分类识别

doi:10.3969/j.issn.1000-1158.2020.02.23

摘要
图/表
参考文献(13)
相关文章 (15)

全文: PDF (1816 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对中药三维荧光光谱信号非线性问题,应用局部线性嵌入算法(LLE)对补虚类中药三维荧光光谱信号进行特征提取。使用荧光光谱仪测得不同浓度的24味补虚类中药的三维荧光光谱和等高线光谱图,并利用总体平均经验模态分解(EEMD)算法进行降噪处理,在此基础上,采用LLE算法对经过降噪处理后的三维荧光光谱数据进行特征提取; 然后,应用随机森林(RF)算法对提取的特征向量进行分类识别。为了验证LLE算法的有效性,将其与主成分分析(PCA)算法进行比较。实验结果表明: LLE-RF组合算法分类准确率达95%,比PCA-RF算法分类准确率高,从而验证了该算法的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	樊凤杰
	轩凤来
	白洋
	纪会芳

关键词 ：计量学;中药指纹图谱;三维荧光光谱;LLE-RF;分类识别, 特征提取

Abstract：To research the non-linearity of the three dimensional fluorescence spectrum signal of traditional Chinese medicine, locally linear embedding (LLE) algorithm was used to extract the feature of three dimensional fluorescence spectrum signals for tonifying herbs. On the basis of the three dimensional fluorescence spectrum and contour line spectrum of 24 traditional Chinese medicines of different concentrations measured by fluorescence spectrometer,and ensemble empirical mode decomposition (EEMD) algorithm for noise reduction, the LLE algorithm was used to extract the characteristics of the three dimensional fluorescence spectrum data after noisereduction.Then, the extracted features were classified and identified by using random forest (RF) algorithm.In order to verify the effectiveness of LLE algorithm, the principal component analysis (PCA) algorithm was compared. Experimental results showed that the classification accuracy of the LLE-RF combination algorithm was 95%, which was higher than PCA-RF algorithm which proved the effectiveness of the algorithm.

Key words： metrology traditional Chinese medicine fingerprint three dimensional fluorescence spectroscopy LLE-RF classification recognition feature extraction

收稿日期: 2018-09-17 发布日期: 2020-02-17

PACS:

TB99

基金资助:国家自然科学基金(61201111);燕山大学博士基金(BL17026)

通讯作者: 樊凤杰 E-mail: ffjmz@126.com

作者简介: 樊凤杰(1977-),女,河北秦皇岛人,燕山大学副教授,博士,研究方向为数据挖掘、中医药大数据知识发现及模式识别。Email:ffjmz@126.com

引用本文:

樊凤杰,轩凤来,白洋,纪会芳. 基于LLE-RF的中药三维荧光光谱分类识别[J]. 计量学报, 2020, 41(2): 263-268.
FAN Feng-jie,XUAN Feng-lai,BAI Yang,JI Hui-fang. Classification Recognition of Three Dimensional Fluorescence Spectrum Traditional Chinese Medicine Based on LLE-RF. Acta Metrologica Sinica, 2020, 41(2): 263-268.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2020.02.23 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2020/V41/I2/263

［1］李强, 杜思邈, 张忠亮, 等. 中药指纹图谱技术进展及未来发展方向展望［J］. 中草药, 2013, 44(22): 3095-3104.
Li Q, Du S M, Zhang Z L, et al. Progress in fingerprint technology on Chinese materia medica and prospect of its future development［J］.Chinese Traditional and Herbal Drugs, 2013, 44(22): 3095-3104.
［2］盖云, 鲍成满, 叶树明, 等. 化学计量学方法在三维荧光光谱分析中的应用［J］. 光谱学与光谱分析, 2011, 31(7): 1828-1833.
Gai Y, Bao C M, Ye S M, et al. Application of Chemometric Methods in Three-dimensional Fluorescence Spectral Analysis［J］. Spectroscopy and Spectral Analysis, 2011, 31(7): 1828-1833.
［3］胡泽建, 王克闵, 冉绍春. 三维荧光谱参量化方法及其在油种鉴别中的应用［J］. 黄渤海海洋学报, 1998, 16(4): 35-41.
Hu Z J, Wang K M, Ran S C.Paraneterization of Three Dimensional Fluorescence Spectra and Its Application to Oil Identification［J］. Journal of Oceanography of Huanghai & Bohai seas, 1998, 16(4): 35-41.
［4］吴桂芳, 何勇. 应用可见/近红外光谱进行纺织纤维鉴别的研究［J］. 光谱学与光谱分析, 2010, 30(2): 331-335.
Wu G F, He Y. Identification of Varieties of Textile Fibers by Using Vis/NIR Infrared Spectroscopy Technique［J］. Spectroscopy and Spectral Analysis, 2010, 30(2): 331-335.
［5］Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding［J］. Science, 2000, 290(5500): 2323-2326.
［6］朱江淼, 孙盼盼, 高源, 等. 原子钟频差数据去噪算法的研究［J］. 计量学报, 2017, 38(4): 499-503.
Zhu J M,Sun P P, Gao Y, et al. The Denoise of the Atomic Clock Frequency Differences［J］. Acta Metrologica Sinica, 2017, 38(4): 499-503.
［7］段宇飞, 王巧华, 马美湖, 等. 基于LLE-SVR的鸡蛋新鲜度可见/近红外光谱无损检测方法［J］. 光谱学与光谱分析, 2016, 36(4): 981-985.
Duan Y F, Wang Q H, Ma M H, et al. Study on Non-Destructive Detection Method for Egg Freshness Basedon LLE-SVR and Visible/Near-Infrared Spectrum［J］. Spectroscopy and Spectral Analysis, 2016, 36(4): 981-985.
［8］Zhuo L, Cheng B, Zhang J. A comparative study of dimensionality reduction methods for large-scale image retrieval［J］. Neurocomputing, 2014, 141: 202-210.
［9］Demetgul M, Yildiz K, Taskin S, et al. Fault diagnosis on material handling system using feature selection and data mining techniques［J］. Measurement, 2014, 55: 15-24.
［10］Breiman L. Random Forests［J］. Machine Learning, 2001, 45(1): 5-32.
［11］王鹏,龚盼,冯定,等. 基于随机森林算法的井下原油含水率软测量方法［J］. 计量学报, 2019, 40(5): 835-841.
Wang P, Gong P, Feng D, et al. Soft Sensing Method for Water Cut of Crude Oil Based on Random Forest Algorithm［J］. Acta Metrologica Sinica, 2019, 40(5): 835-841.
［12］Ouallouche F, Lazri M, Ameur S. Improvement of rainfall estimation from MSG data using Random Forests classification and regression［J］. Atmospheric Research, 2018, 211: 62-72.
［13］Tomiyama S, Sakata-Yanagimoto M, Chiba S, et al. Development of automatic classification system for leukocyte images using Random Forest［J］. Electronics and Communications in Japan, 2018, 101(11): 13-19.