Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Spectroscopy and Spectral Analysis, Volume. 41, Issue 10, 3032(2021)

Near Infrared Spectral Wavelength Selection Based on Improved Team Progress Algorithm

Mei-feng GAO* and Huan-ming TAO
Author Affiliations
  • Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (7)
    Equations (0)
    References (13)
    Tools
    Paper Information
    Topics
    Figures & Tables(7)
    Mahalanobis distance distribution of samples

    Fig. 1. Mahalanobis distance distribution of samples

    Download full size
    View in Article
    Spectra of abnormal samples removed

    Fig. 2. Spectra of abnormal samples removed

    Download full size
    View in Article
    Prediction RMSEP values of starch (a) and protein (b) after running TPA and iTPA for 50 times

    Fig. 3. Prediction RMSEP values of starch (a) and protein (b) after running TPA and iTPA for 50 times

    Download full size
    View in Article
    Frequencies of spectral variable selections for starch (a) and protein (b) after running iTPA for 50 times

    Fig. 4. Frequencies of spectral variable selections for starch (a) and protein (b) after running iTPA for 50 times

    Download full size
    View in Article

    • Table 1. Statistics of starch and protein contents in correction set and prediction set

      View table
      View in Article

      Table 1. Statistics of starch and protein contents in correction set and prediction set

      最大值最小值平均值标准差
      淀粉校正集66.472 062.826 064.809 90.799 7
      淀粉预测集65.841 063.099 064.432 30.813 3
      蛋白质校正集9.595 07.654 08.569 20.485 2
      蛋白质预测集9.711 08.112 08.848 80.498 0

    • Table 2. Prediction results of corn starch content by different variable screening methods

      View table
      View in Article

      Table 2. Prediction results of corn starch content by different variable screening methods

      波长数RcRMSECRpRMSEPT/s
      F-PLS7000.905 70.335 70.871 70.391 40.028
      GA-PLS3500.958 20.226 40.926 20.300 621.980
      TPA-PLS17.640.945 30.258 10.901 30.345 30.680
      iTPA-PLS17.550.944 10.260 90.907 90.334 40.676
      PCA200.899 60.377 00.792 70.438 30.467

    • Table 3. Prediction results of corn protein content by different variable screening methods

      View table
      View in Article

      Table 3. Prediction results of corn protein content by different variable screening methods

      波长数RcRMSECRpRMSEPT/s
      F-PLS7000.951 70.147 40.930 70.178 90.028
      GA-PLS3460.979 10.097 80.973 50.111 422.120
      TPA-PLS19.640.975 50.105 60.969 60.119 30.678
      iTPA-PLS19.600.975 90.101 90.970 40.117 70.666
      PCA200.956 90.141 70.891 60.236 20.469
    Tools

    Get Citation

    Copy Citation Text

    Mei-feng GAO, Huan-ming TAO. Near Infrared Spectral Wavelength Selection Based on Improved Team Progress Algorithm[J]. Spectroscopy and Spectral Analysis, 2021, 41(10): 3032

    Download Citation

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

    Category: Research Articles

    Received: Aug. 28, 2020

    Accepted: --

    Published Online: Oct. 29, 2021

    The Author Email: Mei-feng GAO (mfgao@jiangnan.edu.cn)

    DOI:10.3964/j.issn.1000-0593(2021)10-3032-07

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology