Artificial neural-network-based visible light positioning algorithm with a diffuse optical channel

Heqing Huang; Aiying Yang; Lihui Feng; Guoqiang Ni; Peng Guo

doi:10.3788/COL201715.050601

Chinese Optics Letters, Volume. 15, Issue 5, 050601(2017)

Artificial neural-network-based visible light positioning algorithm with a diffuse optical channel

Heqing Huang^1,2, Aiying Yang^1、*, Lihui Feng¹, Guoqiang Ni^1,2, and Peng Guo¹

Author Affiliations

¹School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China

²Key Laboratory of Photo-electronic Imaging Technology and System (Beijing Institute of Technology), Ministry of Education of China, Beijing 100081, China

show less

Figures & Tables(11)

Fig. 1. Typical scenario of indoor visible light positioning.

Download full size

View in Article

Fig. 2. Geometry of a diffuse channel.

Download full size

View in Article

Fig. 3. Structure of an artificial neural network.

Download full size

View in Article

Fig. 4. Block diagram of the proposed visible light positioning algorithm.

Download full size

View in Article

Fig. 5. Positioning error at sampled points of (a) typical RSS-based positioning algorithm and (b) proposed neural-network-based positioning algorithm.

Download full size

View in Article

Fig. 6. (a) Distribution of the positioning error on the receiver plane and (b) CDF of the positioning error with different times of iteration.

Download full size

View in Article

Fig. 7. Positioning error with a different number of hidden nodes.

Download full size

View in Article

Fig. 8. Positioning error with a different reflectivity of the wall.

Download full size

View in Article

Fig. 9. Positioning error with a different FOV of the receiver.

Download full size

View in Article

Table 1. Key Parameters Used in Simulation

View table

View in Article

Table 1. Key Parameters Used in Simulation

Symbol	Parameter	Value
$P_{t}$	Optical power of LEDs	1 W
$Φ_{1 / 2}$	LED semi-angle at half-power	60°
$R_{W}$	Reflectivity of the wall	0.7
$R$	Responsivity of the receiver	0.5 A/W
$A_{r}$	Area of the receiver	$1 {cm}^{2}$
$n$	Refractive index	1.5
FOV	Field-of-view of the receiver	70°
$T (φ)$	Transmission of the receiver	1
$G$	Open-loop voltage gain	10
$η$	Fixed capacitance of the PD	$112 pF / {cm}^{2}$
$Γ$	Channel noise factor	1.5
$g_{m}$	FET transconductance	30 mS
$T_{k}$	Absolute temperature	298 K
$B$	Equivalent noise bandwidth	100 MHz
$L$	Number of nodes in the hidden layer	20

Table 2. Average Training Time and Positioning Time with a Different Number of Hidden Nodes
View table
View in Article
Table 2. Average Training Time and Positioning Time with a Different Number of Hidden Nodes
Number of hidden nodes 0 10 15 20 25 30
Average training time 0 3 s 5.3 s 8.4 s 8.8 s 26.3 s
Average positioning time 5.34 ms 75.3 μs 75.1 μs 76.1 μs 77.9 μs 75.5 μs

Tools

Get Citation

Copy Citation Text

Heqing Huang, Aiying Yang, Lihui Feng, Guoqiang Ni, Peng Guo, "Artificial neural-network-based visible light positioning algorithm with a diffuse optical channel," Chin.Opt.Lett. 15, 050601 (2017)

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites