首页 > 论文 > 光谱学与光谱分析 > 40卷 > 6期(pp:1763-1768)

基于三维荧光光谱特征的中药药性模式识别研究

Pattern Recognition of Traditional Chinese Medicine Property Based on Three-Dimensional Fluorescence Spectrum Characteristics

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

由于三维荧光光谱技术选择性好、 灵敏度高、 测试快速等优点目前已在众多领域中被广泛应用。 中药药性理论是中药的核心基础理论, 是中药学的特色理论之一, 中药药性的客观化判别是中医药现代化研究的关键问题。 中药中大部分分子具备产生荧光的能力, 因而, 针对中药三维荧光光谱特征, 从中药药性的角度对中药进行分类识别研究。 利用FS920型稳态荧光光谱仪测得5组不同浓度的23味寒温类中药溶液制剂的三维荧光光谱数据, 获取样本的等高线图和三维荧光光谱图; 分析不同样本不同激发波长和发射波长范围存在噪声的基础上, 应用集合经验模态分解算法(EEMD)对光谱图进行降噪预处理; 基于局部线性嵌入算法(LLE)对光谱数据进行特征提取, 分析近邻点数k=12, 本征维数d=7时得到的特征向量, 结果表明不同浓度的寒性药在PC4和PC6的特征值变化明显, 不同浓度的温性药在PC1, PC2, PC4和PC7的特征值变化明显, 且浓度越高特征值都有下降趋势。 将提取的特征向量输入到随机森林(RF)中, 构建LLE-RF分类模型, 分析不同参数时LLE-RF分类模型对寒温类中药荧光光谱数据的分类效果, 设置RF分类器中训练集和测试集的样本比例分别为3∶1和2∶1, 即训练集的比重r分别为3/4和2/3, 分析LLE中近邻点数k取值为7~18, 本征维数d分别取值为6, 7, 8, 9和10时分类正确率。 当近邻点数k=12, 本征维数d=7时LLE-RF模型对中药药性的分类正确率最高, 达到96.6%。 最后比较同一比例r情况下, 采用不同核函数构造SVM分类器对寒温类中药荧光光谱数据分类效果, 当多层感知机作为核函数时, 分类效果最差。 当r=3/4, 径向基作为核函数时, 寒温类中药荧光光谱数据的分类效果最好, 正确率达到82.1%。 分析结果表明, 通过荧光光谱技术与LLE-RF相结合的方法, 能有效的将寒温类中药进行模式识别, 并且分类效果比LLE-SVM更理想。

Abstract

As three-dimensional fluorescence spectroscopy has many advantages, such as good selectivity, high sensitivity, fast analysis, it has been widely used in many fields.As one of the characteristics of traditional Chinese medicine(TCM), Chinese herbal medicine property (CHMP) is the core of TCM. Objective discrimination of the properties of TCM is the key issues of modernization of TCM. The identification of traditional Chinese medicine property is of great significance in the theoretical study of Chinese medicine. Most of the molecules in traditional Chinese medicine have the ability to generate fluorescence. According to the characteristics of the three-dimensional fluorescence spectrum of traditional Chinese medicines, the classification and recognition were studied from the perspective of the properties of traditional Chinese medicines. Firstly, the three-dimensional fluorescence spectral data of 5 different concentrations of 23 cold and warm Chinese medicinal solutions were acquired by FS920 fluorescence spectrometer. Then, the ensemble empirical mode decomposition (EEMD) algorithm is applied to denoise the spectrogram, based on the analysis of noise in different excitation and emission wavelength ranges of different samples. Based on the local linear embedding (LLE) algorithm, feature extraction of spectral data is carried out. The extracted eigenvectors are input into the random forest (RF) to construct LLE-RF classification model. The classification effect of LLE-RF classification model on fluorescence spectrum data of cold and warm Chinese medicines was analyzed under different parameters. The sample ratio of the training set and test set in RF classifier is set to 3∶1 and 2∶1. The correct rate of LLE classification is analyzed when the nearest neighbor points k is 7~18 and the eigenvalue dimension d is 6, 7, 8, 9 and 10. When the nearest neighbor points k is 12 and the eigenvalue dimension d is 7, the accuracy of LLE-RF model for classification of Chinese herbal medicines was 96.6%. Finally, the classification effect of SVM classifier constructed with different kernels on fluorescence spectrum data of cold and warm Chinese medicines was compared under the same ratio of r. When multi-layer perceptron is used as the kernel function, the classification effect is the worst. When r=3/4 and radial basis function is used as the kernel function, the classification accuracy is 82.1%. The results show that the method of combining fluorescence spectroscopy with LLE-RF can effectively recognize cold and warm Chinese medicines, and the classification effect is better than LLE-SVM.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TB96

DOI:10.3964/j.issn.1000-0593(2020)06-1763-06

基金项目:国家自然科学基金项目(61201111), 燕山大学博士基金项目(BL17026)资助

收稿日期:2019-05-23

修改稿日期:2019-09-16

网络出版日期:--

作者单位    点击查看

樊凤杰:燕山大学电气工程学院, 河北 秦皇岛 066004
轩凤来:燕山大学电气工程学院, 河北 秦皇岛 066004
白 洋:燕山大学电气工程学院, 河北 秦皇岛 066004
纪会芳:联勤保障部队第九八四医院, 北京 100094

联系人作者:樊凤杰(ffjmz@126.com)

备注:樊凤杰, 1977年生, 燕山大学电气工程学院副教授

【1】ZHANG Xin-xin, LI Yu, JI Yu-jia, et al(张新新, 李 雨, 纪玉佳, 等). Journal of Shandong University·Health Science(山东大学学报·医学版), 2012, 50(1): 143.

【2】LI Jia-hui, CHEN Ren-shou, LI Lu-jie(李加慧, 陈仁寿, 李陆杰). Journal of Traditional Chinese Medicine(中医杂志), 2019, 60(1): 67.

【3】LIU Min, WU Dong-xue, LI Jing, et al(刘 敏, 吴东雪, 李 晶, 等). China Journal of Chinese Materia Medica(中国中药杂志), 2019, 44(2): 218.

【4】WANG Xiao-yan, LI Feng(王晓燕, 李 峰). Liaoning Journal of Traditional Chinese Medicine(辽宁中医杂志), 2015, 42(6): 1303.

【5】WU Si-yuan, HU You-fen, LIU Xiao-wei, et al(吴思媛, 胡幼芬, 刘晓伟, 等). Software Guide(软件导刊), 2014, 13(10): 71.

【6】CHEN Zhao, CAO Yan-feng, HE Shuai-bing, et al(陈 昭, 曹燕凤, 何帅兵, 等). China Journal of Traditional Chinese Medicine and Pharmacy(中华中医药杂志), 2017, 32(5): 2107.

【7】Henrique Z P, Alonso J B, Ferrer M A, et al. IEEE Transactions on Audio Speech and Language Processing, 2009, 17(6): 1186.

【8】QIN Xi-wen, L Si-qi, LI Qiao-ling(秦喜文, 吕思奇, 李巧玲). Chinese Journal of Biomedical Engineering(中国生物医学工程学报), 2018, 37(6): 665.

【9】Shinnosuke Tomiyama, Mamiko Sakata-yanagimoto, Shigeru Chiba, et al. Electronics and Communications in Japan, 2018, 101(11): 13.

【10】LIU Peng, WU Rui-mei, YANG Pu-xiang, et al(刘 鹏, 吴瑞梅, 杨普香, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(1): 193.

引用该论文

FAN Feng-jie,XUAN Feng-lai,BAI Yang,JI Hui-fang. Pattern Recognition of Traditional Chinese Medicine Property Based on Three-Dimensional Fluorescence Spectrum Characteristics[J]. Spectroscopy and Spectral Analysis, 2020, 40(6): 1763-1768

樊凤杰,轩凤来,白 洋,纪会芳. 基于三维荧光光谱特征的中药药性模式识别研究[J]. 光谱学与光谱分析, 2020, 40(6): 1763-1768

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF