Acta Optica Sinica, Volume. 40, Issue 7, 0730002(2020)

Application of XGBoost in Gas Infrared Spectral Recognition

Mengqi Tao1,2, Jiaxiang Liu1, Yue Wu1,2, Zhiqiang Ning1,2, and Yonghua Fang1,2、*
Author Affiliations
  • 1Key Laboratory of Environmental Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei, Anhui 230031, China
  • 2University of Science and Technology of China, Hefei, Anhui 230026, China
  • show less
    Figures & Tables(7)
    Flow chart of XGBoost algorithm
    Schematic of XGBoost algorithm[13]
    Comparison before and after spectral pretreatment. (a)(b) Trichloromethane; (c)(d) paraxylene; (e)(f) tetrachloroethylene
    Flow chart of XGBoost model training
    • Table 1. Features for gas spectral data classification

      View table

      Table 1. Features for gas spectral data classification

      FeatureMeaning
      WidthFull width at half maximum of characteristic peak
      KurtosisSharpness of characteristic peak
      SkewnessSymmetry of characteristic peak
      CorrelationCorrelation coefficient with standard spectrum on NIST
      SNRSignal to noise ratio of characteristic peak
    • Table 2. Classification error matrix for three kinds of gases

      View table

      Table 2. Classification error matrix for three kinds of gases

      Gas nameTrichloromethaneParaxyleneTetrachloroethylene
      Trichloromethane887155
      Paraxylene3181411
      Tetrachloroethylene913799
    • Table 3. Classification accuracy for five models

      View table

      Table 3. Classification accuracy for five models

      ModelAccuracy /%
      RF96.35
      SVM79.48
      CNN80.37
      FNN95.61
      XGBoost96.75
    Tools

    Get Citation

    Copy Citation Text

    Mengqi Tao, Jiaxiang Liu, Yue Wu, Zhiqiang Ning, Yonghua Fang. Application of XGBoost in Gas Infrared Spectral Recognition[J]. Acta Optica Sinica, 2020, 40(7): 0730002

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Spectroscopy

    Received: Dec. 3, 2019

    Accepted: Dec. 30, 2019

    Published Online: Apr. 15, 2020

    The Author Email: Fang Yonghua (yhfang@aiofm.ac.cn)

    DOI:10.3788/AOS202040.0730002

    Topics