• Spectroscopy and Spectral Analysis
  • Vol. 42, Issue 6, 1774 (2022)
Qing LI1、1; 2;, Li XU1、1; 2;, Shan-gui PENG1、1; 2;, Xiao LUO1、1; 2;, Rong-qin ZHANG1、1; 2;, Zhu-yun YAN3、3;, and Yong-sheng WEN1、1; 2; *;
Author Affiliations
  • 11. Chengdu Institute for Drug Control, Chengdu 610045, China
  • 33. Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2022)06-1774-07 Cite this Article
    Qing LI, Li XU, Shan-gui PENG, Xiao LUO, Rong-qin ZHANG, Zhu-yun YAN, Yong-sheng WEN. Research on Identification of Danshen Origin Based on Micro-Focused Raman Spectroscopy Technology[J]. Spectroscopy and Spectral Analysis, 2022, 42(6): 1774 Copy Citation Text show less
    Optimization results of random forest model parameters(a): The relationship diagram between n_estimator and OOB_SCORE; (b): The relationship diagram between max_features and OOB_SCORE
    Fig. 1. Optimization results of random forest model parameters
    (a): The relationship diagram between n_estimator and OOB_SCORE; (b): The relationship diagram between max_features and OOB_SCORE
    Origins of danshen and their representative samples
    Fig. 1. Origins of danshen and their representative samples
    The relationship between the importance of spectral variables after 1st-d processing and wave numbers
    Fig. 2. The relationship between the importance of spectral variables after 1st-d processing and wave numbers
    Original spectra of surface of danshen with different scanning times and tanshinone components
    Fig. 2. Original spectra of surface of danshen with different scanning times and tanshinone components
    The confusion matrix of the test set of the optimal RF model (a) and the optimal RF-VS model (b)
    Fig. 3. The confusion matrix of the test set of the optimal RF model (a) and the optimal RF-VS model (b)
    采样区域
    (见图1)
    采样点
    (见图1)
    样本数量土壤类型地貌
    a粉色点17沙质平原
    b深蓝色点17沙质平原
    c亮绿色点67黄棕丘陵
    d红色点30黄棕丘陵
    e黄色点19黄棕丘陵
    Table 1. Information of 150 samples of danshen
    扫描次数模型数据前处
    理方法
    训练集测试集变量数
    /个
    界值
    ACCACC
    扫描一次RF-VS1ST-D88871670.009 207
    扫描二次RF-VS3RD-D8987990.013 165
    扫描三次RF-VS3RD-D89873070.008 811
    Table 1. The results of best models under the conditions of different scanning times
    测定次数模型数据前处理方法训练集测试集主成分数变量数/个界值
    ACCACC
    测定一次PLS-DAOriginal data736823 216
    MSC746533 216
    SNV696823 216
    1ST-D746823 215
    2ND-D696823 214
    3RD-D696523 213
    RFOriginal data83873 2160
    MSC86873 2160
    SNV82683 2160
    1ST-D87813 2150
    2ND-D87843 2140
    3RD-D87813 2130
    RF-VSOriginal data8687870.013 837
    MSC86873660.008 228
    SNV81772950.010 197
    1ST-D88871670.009 207
    2ND-D8881290.014 741
    3RD-D88871980.009 325
    测定二次PLS-DAOriginal data716823 216
    MSC746533 216
    SNV706523 216
    1ST-D736823 215
    2ND-D706823 214
    3RD-D696523 213
    RFOriginal data87813 2160
    MSC85843 2160
    SNV82713 2160
    1ST-D88773 2150
    2ND-D88773 2140
    3RD-D88773 2130
    RF-VSOriginal data86843 2150.011 960
    MSC87841010.007 782
    SNV84773190.008 426
    1ST-D87843 2140.009 207
    2ND-D87873 2130.014 382
    3RD-D8987990.013 165
    测定三次PLS-DAOriginal data716823 216
    MSC746543 216
    SNV716523 216
    1ST-D736823 215
    2ND-D696823 214
    3RD-D686833 213
    RFOriginal data85843 2160
    MSC82873 2160
    SNV84743 2160
    1ST-D89843 2150
    2ND-D89813 2140
    3RD-D90773 2130
    RF-VSOriginal data8687780.011 553
    MSC85841560.010 343
    SNV83772180.008 102
    1ST-D89843030.009 168
    2ND-D89841670.017 988
    3RD-D89873070.008 811
    Table 2. The results of the model under the conditions of different determination times
    MemerbersACC/%abcde
    40a00400
    2100b02000
    1283c001020
    9100d00090
    40e02200
    0No class00000
    167.74Total0416110
    Table 3. Test set confusion matrix of PLS-DA model after MSC processing
    Qing LI, Li XU, Shan-gui PENG, Xiao LUO, Rong-qin ZHANG, Zhu-yun YAN, Yong-sheng WEN. Research on Identification of Danshen Origin Based on Micro-Focused Raman Spectroscopy Technology[J]. Spectroscopy and Spectral Analysis, 2022, 42(6): 1774
    Download Citation