Spectroscopy and Spectral Analysis, Volume. 41, Issue 9, 2742(2021)

Research of Parameter Optimization of Preprocessing and Feature Extraction for NIRS Qualitative Analysis Based on PSO Method

Hao-guang LI*, Yun-hua YU1; 2;, Yan PANG1;, and Xue-feng SHEN1; 2;
Author Affiliations
  • 1. College of Mechanical and Control Engineering, Shandong Institute of Petrochemical and Chemical Technology, Dongying 257061, China
  • show less
    Figures & Tables(9)
    Flow chart of Pretreatment and extraction parameters combination search based on PSO method
    Flow chart of fitness function of PSO algorithm
    Recognition rate curve with particle population size changing
    Curve of convergence time with particle populationsize changing
    Flow chart of loop nesting optimization method
    • Table 1. Recognition rate and its corresponding parameter list (PSO method)

      View table
      View in Article

      Table 1. Recognition rate and its corresponding parameter list (PSO method)

      序号SPFDPPLSOLDA平均识别率/%
      111711596.2
      21399496.5
      39911496.9
      411137497.0
      511119596.3
    • Table 2. Recognition rate and its corresponding parameter list (multiple loop nesting method)

      View table
      View in Article

      Table 2. Recognition rate and its corresponding parameter list (multiple loop nesting method)

      序号SPFDPPLSOLDA平均识别率/%
      113711496.9
      21399496.6
      39911597.2
      411119496.8
      511119596.4
    • Table 3. Recognition results of optimal parameter combination tested with other data sets

      View table
      View in Article

      Table 3. Recognition results of optimal parameter combination tested with other data sets

      测试集T1T2T3T4T5
      正确识别率/%96.295.695.296.294.6
      正确拒识率/%97.495.294.893.494.0
      平均识别率/%96.995.495.094.994.3
    • Table 4. Comparison of program consumption time

      View table
      View in Article

      Table 4. Comparison of program consumption time

      方法多重循环嵌套方法PSO方法
      时间2 825 s586 s
    Tools

    Get Citation

    Copy Citation Text

    Hao-guang LI, Yun-hua YU, Yan PANG, Xue-feng SHEN. Research of Parameter Optimization of Preprocessing and Feature Extraction for NIRS Qualitative Analysis Based on PSO Method[J]. Spectroscopy and Spectral Analysis, 2021, 41(9): 2742

    Download Citation

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

    Category: Research Articles

    Received: Jan. 20, 2021

    Accepted: --

    Published Online: Oct. 29, 2021

    The Author Email: Hao-guang LI (lihaoguang@upc.edu.cn)

    DOI:10.3964/j.issn.1000-0593(2021)09-2742-06

    Topics