High accuracy indoor visible light positioning using a long short term memory-fully connected network based algorithm

Chen, Hongyao; Han, Wei; Wang, Jianping; Lu, Huimin; Chen, Danyang; Jin, Jianli; Feng, Lifang

doi:10.1364/oe.445389

Cited by 18 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This Work K-means-DNN Medium 0.78 cm [12] Luminance Distribution Model Medium 7 cm [13] Cramer-Rao Bound Medium 7 cm [14] Maximum Likelihood Medium 10 cm [15] Pilot Signals Low 3.9 cm [16] Cayley-Menger Medium 10.5 cm [17] LSTM-FCN Low 0.92 cm [18] ARWKNN Medium 3.8 cm [19] GRNN Low 0.96 cm [20] BR-DNN Medium 4.5 cm…”

Section: References Methodology Complexity Positioning Accuracymentioning

confidence: 98%

“…These samples are then utilized as training data to construct a model that can accurately estimate the position of PD from the new RSS samples received during online positioning, achieving a positioning accuracy of 10.5 cm. A new positioning algorithm based on a long short-term memory fully connected network (LSTM-FCN) has been proposed in [17], for enhanced positioning accuracy in scenarios with multiple LEDs and a single PD in VLP. The approach achieves considerable complexity, albeit with a positioning accuracy of less than 5 cm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

K-Means-Based DNN Algorithm for a High Accuracy VLP System

Jin,

Wang,

Yang

et al. 2024

Photonics

Self Cite

View full text Add to dashboard Cite

In this paper, a positioning algorithm based on the combination of K-means clustering and deep neural networks (DNNs) is first presented for multiple light emitting diodes (LEDs) integrated with visible light positioning (VLP) systems. We extracted the maximum value from the collected optical power of LEDs, utilizing the ratio of each optical power to this maximum optical power as the input training data. The experimental results demonstrate that the proposed algorithm outperformed the conventional DNN algorithm in terms of anti-jamming capability and positioning accuracy. In addition, the positioning accuracy of the proposed system reached a millimeter level, which is the highest experimental VLP accuracy, to the best of our knowledge.

show abstract

Section: References Methodology Complexity Positioning Accuracymentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

K-Means-Based DNN Algorithm for a High Accuracy VLP System

Jin,

Wang,

Yang

et al. 2024

Photonics

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to the required number of lamps, RSS based VLP technology can be further classified into multi-lamps positioning schemes [14], [15] and single-lamp positioning schemes [16], where the lamp is utilized as the anchor node for positioning. However, the multi-lamps positioning schemes in general require at least three anchors for effective localization, which is hard to implement in many practical VLC applications area.…”

Section: Introductionmentioning

confidence: 99%

Centimeter-Level 3-D Mobile Online Visible Light Positioning System With Single LED Lamp

Zhang

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

In this paper, we consider a practical indoor 3D mobile online visible light positioning (VLP) system, where the orientation of the UE is arbitrary. Based on the received signal strength (RSS) of multiple photo-detectors (PDs), we formulate the 3D VLP problem as a non-linear least squares (NLS) optimization problem, and then propose a sequential quadratic programming (SQP) positioning algorithm to efficiently calculate UE's location. To obtain more accurate positioning solutions, we further leverage the advantages of deep learning and develop a stochastic gradient descent (SGD) based VLP algorithm, and achieve an average positioning error of 1.77cm, which significantly outperforms existing RSS VLP localization methods. Moreover, we design a 3D mobile online VLP system prototype by using a portable RaspberryPi 4 Model B as the positioning signal processor and data memory, and establish the first publicly available 3D VLP measured dataset including both RSS and orientation. The proposed positioning schemes are implemented and evaluated via the designed prototype system, which can achieve centimeter-level positioning accuracy (below 1 cm in certain condition).

show abstract

“…The prosperity of machine learning (ML) provides many data-driven methods to solve nonlinear problems, including VLP. The methods based on regression [ 22 ], reinforcement learning [ 23 ], and neural networks (NNs) [ 24 , 25 ] typically obtain higher accuracy and stability than the traditional ones. However, they require offline progress to collect data sets or fingerprints to train models.…”

Section: Introductionmentioning

confidence: 99%

High-Accuracy Height-Independent 3D VLP Based on Received Signal Strength Ratio

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

Visible light positioning (VLP) has attracted intensive attention from both academic and industrial communities thanks to its high accuracy, immunity to electromagnetic interference, and low deployment cost. In general, the receiver in a VLP system determines its own position by exploring the received signal strength (RSS) from the transmitter according to a pre-built RSS attenuation model. In such model-based methods, the LED’s emission power and the receiver’s height are usually required known and constant parameters to obtain reasonable positioning accuracy. However, the LED’s emission power is normally time-varying due to the fact that the LED’s optical output power is prone to changing with the LED’s temperature, and the receiver’s height is random in a realistic application scenario. To this end, we propose a height-independent three-dimensional (3D) VLP scheme based on the RSS ratio (RSSR), rather than only using RSS. Unlike existing RSS-based VLP methods, our method is able to independently find the horizontal coordinate, i.e., two-dimensional (2D) position, without a priori height information of the receiver, and also avoids the negative effect caused by fluctuation of the LED’s emission power. Moreover, we can further infer the height of the receiver to achieve three-dimensional (3D) positioning by iterating the 2D results back into positioning equations. To quickly verify the proposed scheme, we conduct theoretical analysis with mathematical proof and experimental results with real data, which confirm that the proposed scheme can achieve high position accuracy without known information of the receiver’s height and LED’s emission power. We also implement a VLP prototype with five LED transmitters, and experimental results show that the proposed scheme can achieve very low average errors of 2.73 cm in 2D and 7.20 cm in 3D.

show abstract

High accuracy indoor visible light positioning using a long short term memory-fully connected network based algorithm

Cited by 18 publications

References 36 publications

K-Means-Based DNN Algorithm for a High Accuracy VLP System

K-Means-Based DNN Algorithm for a High Accuracy VLP System

Centimeter-Level 3-D Mobile Online Visible Light Positioning System With Single LED Lamp

High-Accuracy Height-Independent 3D VLP Based on Received Signal Strength Ratio

Contact Info

Product

Resources

About