Research on Visible Light Indoor Localization Algorithm Based on Elman Neural Network

Fig. 7. Positioning error distribution before and after correction. (a) Uncorrected positioning error distribution; (b) corrected positioning error distribution

Download full size

Fig. 8. Comparison chart before and after correction. (a) Comparison chart before correction; (b) comparison chart after correction

Download full size

Fig. 9. Cumulative distribution of positioning errors

Download full size

Table 1. Simulation parameters

View table

Table 1. Simulation parameters

Simulation parameter	Simulation value
LED emission power P_t	15 W
Actual receiving area of a single PD	1 cm²
Receiver field of view ψ_c	90 °
Half power angle of LED φ₁_/₂	45 °
Refractive index of the lens n	1.5
Optical concentrator gain g(ψ)	1.5²
Optical filter gain T_S(ψ)	1

Table 2. Neural network training parameters
View table
Table 2. Neural network training parameters
Training parameters Settings
Elman neural networktraining algorithm Gradient descent method
Number of iterations 15000
Target error 1×10^-7

Table 3. Comparison of positioning performance of different algorithms
View table
Table 3. Comparison of positioning performance of different algorithms
Positioningalgorithm Averagepositioningerror /cm Averagepositioningtime /s
BP neural network 15.97 0.176588
Elman neural network 13.95 0.218410
Elman neuralNetwork+WKNN 7.13 0.243774

Tools

Get Citation

Copy Citation Text

Ling Qin, Chongtai Zhang, Ying Guo, Yanhong Xu, Fengying Wang, Xiaoli Hu. Research on Visible Light Indoor Localization Algorithm Based on Elman Neural Network[J]. Acta Optica Sinica, 2022, 42(5): 0506002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites