• Laser & Optoelectronics Progress
  • Vol. 59, Issue 3, 0304002 (2022)
Ling Qin, Dongxing Wang, Fengying Wang, and Xiaoli Hu*
Author Affiliations
  • School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou , Inner Mongolia 014010, China
  • show less
    DOI: 10.3788/LOP202259.0304002 Cite this Article Set citation alerts
    Ling Qin, Dongxing Wang, Fengying Wang, Xiaoli Hu. Indoor Visible Light Positioning Method Based on Extreme Learning Machine Neural Network[J]. Laser & Optoelectronics Progress, 2022, 59(3): 0304002 Copy Citation Text show less
    Model of the indoor VLP
    Fig. 1. Model of the indoor VLP
    Structure of the ELM neural network
    Fig. 2. Structure of the ELM neural network
    RMSE of the ELM prediction model
    Fig. 3. RMSE of the ELM prediction model
    Positioning error of the ELM method
    Fig. 4. Positioning error of the ELM method
    Positioning results of different methods. (a) ELM method; (b) SVM method; (c) BP method; (d) GA-BP method
    Fig. 5. Positioning results of different methods. (a) ELM method; (b) SVM method; (c) BP method; (d) GA-BP method
    Cumulative probability distribution of positioning errors
    Fig. 6. Cumulative probability distribution of positioning errors
    Number of neuronsRMSE
    2402.36
    2452.47
    2502.13
    2531.75
    2551.36
    2601.17
    2611.30
    2631.48
    2651.65
    2701.42
    Table 1. RMSE of models with different number of hidden layer neuronsunit: cm
    ParameterValue
    Pt /W10
    ψc /(°)90
    Ts1
    g10
    A /cm21
    ϕ1/2 /(°)30
    Table 2. Simulation parameters

    method

    Positioning

    Max positioning errorAverage positioning error
    ELM6.441.17
    SVM16.893.74
    BP63.6021.23
    GA-BP10.292.72
    Table 3. Positioning errors of different methodsunit: cm
    Positioning methodTraining time of fingerprint dataAverage positioning time
    ELM0.06870.03594
    SVM0.10940.09375
    BP44.07030.09063
    GA-BP74.93750.09562
    Table 4. Positioning time of different methodsunit: s
    Ling Qin, Dongxing Wang, Fengying Wang, Xiaoli Hu. Indoor Visible Light Positioning Method Based on Extreme Learning Machine Neural Network[J]. Laser & Optoelectronics Progress, 2022, 59(3): 0304002
    Download Citation