• Laser & Optoelectronics Progress
  • Vol. 60, Issue 7, 0723002 (2023)
Fen Wei1、2、3、4, Yi Wu1、3、4、*, and Shiwu Xu1、5
Author Affiliations
  • 1Key Laboratory of Opto-Electronic Science and Technology for Medicine Ministry of Education, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, Fujian, China
  • 2Jinshan College of Fujian Agriculture and Forestry University, Fuzhou 350002, Fujian, China
  • 3Fujian Key Laboratory of Photonics Technology, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, Fujian 350007, China
  • 4Fujian Engineering Technology Research Center of Photoelectric Sensing Application, College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, Fujian, China
  • 5Concord University College, Fujian Normal University, Fuzhou 350117, Fujian, China
  • show less
    DOI: 10.3788/LOP213084 Cite this Article Set citation alerts
    Fen Wei, Yi Wu, Shiwu Xu. Experimental Research on Visible Light Positioning Using Machine Learning and Multi-Photodiode[J]. Laser & Optoelectronics Progress, 2023, 60(7): 0723002 Copy Citation Text show less
    Experimental setup of the VLP system with a multi-PD receiver
    Fig. 1. Experimental setup of the VLP system with a multi-PD receiver
    Time division multiplexing scheme
    Fig. 2. Time division multiplexing scheme
    Single-hidden layer feedforward network with L hidden neurons
    Fig. 3. Single-hidden layer feedforward network with L hidden neurons
    Conceptual architecture of positioning system. (a) 2-D positioning; (b) 3-D positioning
    Fig. 4. Conceptual architecture of positioning system. (a) 2-D positioning; (b) 3-D positioning
    Positioning algorithm flow diagram
    Fig. 5. Positioning algorithm flow diagram
    CDF of positioning error for different algorithms. (a) 2-D positioning; (b) 3-D positioning
    Fig. 6. CDF of positioning error for different algorithms. (a) 2-D positioning; (b) 3-D positioning
    APE of different algorithms. (a) 2-D positioning; (b) 3-D positioning
    Fig. 7. APE of different algorithms. (a) 2-D positioning; (b) 3-D positioning
    Impact of M on APE. (a) 2-D positioning; (b) 3-D positioning
    Fig. 8. Impact of M on APE. (a) 2-D positioning; (b) 3-D positioning
    Impact of N on APE. (a) 2-D positioning; (b) 3-D positioning
    Fig. 9. Impact of N on APE. (a) 2-D positioning; (b) 3-D positioning
    Impact of Pt on APE. (a) 2-D positioning; (b) 3-D positioning
    Fig. 10. Impact of Pt on APE. (a) 2-D positioning; (b) 3-D positioning
    ParameterReference
    Indoor space unit size(L×W×H)/cm100×100×150
    Plane range of receiver /cm(0,0)to(65,70)(resolution:5)
    Transmitter power /W5,6,74558
    Height of the receiver /cm102030
    Position of four LEDs(x yz)/cm

    LED1(-10,-10,120)

    LED2(80,-10,120)

    LED3(80,80,120)

    LED4(-10,80,120)

    Distance between each LED /cm90
    The FOV of LED /(°)60
    Distance between each PD /cm5
    The FOV of PD /(°)120
    The effective area of PD /cm21
    Table 1. Experimental parameter
    AlgorithmParameter
    KNNDistance metric:Euclidean distance;K=3
    ELM

    Number neurons in input,hidden and output:16,

    adaptive and 1;Activation function:Sigmoid

    RFTree number:50;Weak classifier:Decision tree
    AdaBoostLearning cycle:100;Weak classifier:Decision tree
    Table 2. Parameter of the four machine learning algorithms
    AlgorithmS-KNN/KNNS-ELM/ELMS-RF/RFS-AdaBoost/AdaBoost
    2-D positioning APT /s0.01/0.010.01/0.050.72/1.140.98/2.43
    3-D positioning APT /s0.02/0.070.05/0.325.45/6.824.45/18.41
    Table 3. APT of different algorithms
    Fen Wei, Yi Wu, Shiwu Xu. Experimental Research on Visible Light Positioning Using Machine Learning and Multi-Photodiode[J]. Laser & Optoelectronics Progress, 2023, 60(7): 0723002
    Download Citation