• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 10, 3240 (2021)
Wen YOU1、*, Yang-peng XIA1、1;, Yu-tao HUANG1、1;, Jing-jun LIN2、2; *;, and Xiao-mei LIN3、3; *;
Author Affiliations
  • 11. Department of Electronics and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
  • 22. Department of Mechanical and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
  • 33. Jilin University of Architecture and Technology, Changchun 130012, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)10-3240-05 Cite this Article
    Wen YOU, Yang-peng XIA, Yu-tao HUANG, Jing-jun LIN, Xiao-mei LIN. Research on Selection Method of LIBS Feature Variables Based on CART Regression Tree[J]. Spectroscopy and Spectral Analysis, 2021, 41(10): 3240 Copy Citation Text show less
    Schematic diagram of experimental device
    Fig. 1. Schematic diagram of experimental device
    Single variable calibration curve of CaⅡ 393.366 nm
    Fig. 2. Single variable calibration curve of CaⅡ 393.366 nm
    Partial least squares regression calibration curve
    Fig. 3. Partial least squares regression calibration curve
    The importance distribution of feature variables
    Fig. 4. The importance distribution of feature variables
    CART regression tree calibration curve
    Fig. 5. CART regression tree calibration curve
    Sample numberConcentration of Ca/Wt%
    1#0.02
    2#0.05
    3#0.08
    4#0.1
    5#0.15
    6#0.2
    7#0.25
    Table 1. The concentration of Ca in standard samples
    模型R2RMSEC
    /Wt%
    RMSEP
    /Wt%
    ARE
    /%
    单变量0.933 20.019 20.017 711.604
    PLSR0.975 30.010 80.013 07.490
    CART回归树0.997 50.003 50.006 12.500
    Table 2. Comparison of calibration model parameters
    Wen YOU, Yang-peng XIA, Yu-tao HUANG, Jing-jun LIN, Xiao-mei LIN. Research on Selection Method of LIBS Feature Variables Based on CART Regression Tree[J]. Spectroscopy and Spectral Analysis, 2021, 41(10): 3240
    Download Citation