• Laser & Optoelectronics Progress
  • Vol. 57, Issue 20, 203001 (2020)
Mengran Zhou, Jinguo Wang*, Hongping Song, Feng Hu, Wenhao Lai, and Kai Bian
Author Affiliations
  • College of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan, Anhui 232001, China
  • show less
    DOI: 10.3788/LOP57.203001 Cite this Article Set citation alerts
    Mengran Zhou, Jinguo Wang, Hongping Song, Feng Hu, Wenhao Lai, Kai Bian. Application of Kernel Extreme Learning Machine and Laser Induction Fluorescence Technique in Edible Oil Identification[J]. Laser & Optoelectronics Progress, 2020, 57(20): 203001 Copy Citation Text show less
    Oil sample detection experiment system diagram
    Fig. 1. Oil sample detection experiment system diagram
    Network structure of ELM
    Fig. 2. Network structure of ELM
    Algorithm flowchart
    Fig. 3. Algorithm flowchart
    Original fluorescence spectra of five oil samples
    Fig. 4. Original fluorescence spectra of five oil samples
    Figure of cumulative contribution rate
    Fig. 5. Figure of cumulative contribution rate
    Test classification accuracy of MFO algorithm
    Fig. 6. Test classification accuracy of MFO algorithm
    Comparison of test classification accuracy of three algorithms
    Fig. 7. Comparison of test classification accuracy of three algorithms
    Statistics of classification accuracy and training time of three models. (a) KELM model; (b) ELM model; (c) BP model
    Fig. 8. Statistics of classification accuracy and training time of three models. (a) KELM model; (b) ELM model; (c) BP model
    Comparison of average training time and classification accuracy of three models. (a) Average training time; (b) classification accuracy
    Fig. 9. Comparison of average training time and classification accuracy of three models. (a) Average training time; (b) classification accuracy
    TypeBrandLevelProduction processProducing areaProduction time
    Peanut oilLuhuaAPressShandong2019-07-31
    Soybean oilFulinmenBLeachJiangsu2019-07-31
    Corn oilChangshouhuaAPressShandong2019-06-06
    Rapeseed oilTuoniaoDLeachJiangsu2019-01-25
    Sunflower seed oilLuhuaAPressInner Mongolia2018-08-24
    Table 1. Types and parameters of edible oils
    AlgorithmModel practicaltime /sAverage recognitionrate /%
    MFO196.4395.33
    GWO195.2995.33
    PSO194.7791.16
    Table 2. Performance comparison of three algorithms
    ModelModel practical time /sAverage recognition rate /%Recognition rate standard deviation
    KELM0.025595.620.0157
    ELM0.002595.166.5940
    BP0.213794.770.0640
    Table 3. Performance comparison of three classification models
    Mengran Zhou, Jinguo Wang, Hongping Song, Feng Hu, Wenhao Lai, Kai Bian. Application of Kernel Extreme Learning Machine and Laser Induction Fluorescence Technique in Edible Oil Identification[J]. Laser & Optoelectronics Progress, 2020, 57(20): 203001
    Download Citation