Indoor high-precision three-dimensional positioning algorithm based on visible light communication and fingerprinting using K-means and random forest

Jiang, Jiajia; Guan, Weipeng; Chen, Zhounan; Chen, Yirong

doi:10.1117/1.oe.58.1.016102

Cited by 15 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that some of the work in the literature considered a small room dimension (e.g. [9, 15]), which tends to improve the accuracy. Though the best performance is achieved in [5], this is largely impractical due to the requirement for a large number of transmitters (16) and receivers (361).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Precision indoor three‐dimensional visible light positioning using receiver diversity and multi‐layer perceptron neural network

Mahmoud

Ahmad

Haas

et al. 2020

IET Optoelectronics

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

“…However, their proposed system required information on the angles of the receiver prior to positioning. In [9], a 3D VLP was proposed based on fingerprinting using K‐means and random forest. However, the process of using the fingerprinting technique is considered labour intensive and time‐consuming with respect to the size of the room.…”

Section: Introductionmentioning

confidence: 99%

Precision indoor three‐dimensional visible light positioning using receiver diversity and multi‐layer perceptron neural network

Mahmoud

Ahmad

Haas

et al. 2020

IET Optoelectronics

View full text Add to dashboard Cite

“…Researchers mainly use traditional machine learning algorithms or deep learning algorithms to realize classification and regression tasks. This paper combines a traditional machine learning [ 34 , 35 , 36 ] algorithm with a deep learning [ 37 , 38 , 39 ] algorithm. It proposes an adaptive multi-type fingerprints indoor positioning and localization method based on MTL and WCKNN to predict the position and location information of multi-type fingerprints.…”

Section: Methodsmentioning

confidence: 99%

Adaptive Multi-Type Fingerprint Indoor Positioning and Localization Method Based on Multi-Task Learning and Weight Coefficients K-Nearest Neighbor

Yuan

Zha

Zhang

2020

Sensors

View full text Add to dashboard Cite

The complex indoor environment makes the use of received fingerprints unreliable as an indoor positioning and localization method based on fingerprint data. This paper proposes an adaptive multi-type fingerprint indoor positioning and localization method based on multi-task learning (MTL) and Weight Coefficients K-Nearest Neighbor (WCKNN), which integrates magnetic field, Wi-Fi and Bluetooth fingerprints for positioning and localization. The MTL fuses the features of different types of fingerprints to search the potential relationship between them. It also exploits the synergy between the tasks, which can boost up positioning and localization performance. Then the WCKNN predicts another position of the fingerprints in a certain class determined by the obtained location. The final position is obtained by fusing the predicted positions using a weighted average method whose weights are the positioning errors provided by positioning error prediction models. Experimental results indicated that the proposed method achieved 98.58% accuracy in classifying locations with a mean positioning error of 1.95 m.

show abstract

“…Although the technique is simple to implement, it provides unreliable positioning as only relative receiver position can be known. On the other hand, the fingerprint scheme exploits the features or characteristics of signals to deduce the user location [14], [15]. This scheme can achieve high positioning accuracy under the assumption that different areas exhibit different signal features, which usually happens in the case of RF-based systems due to signal reflection and interference.…”

Section: Introductionmentioning

confidence: 99%

Design and Performance Evaluation of Large-Scale VLC-Based Indoor Positioning Systems Under Impact of Receiver Orientation

Pham

2020

IEEE Access

View full text Add to dashboard Cite

This paper proposes a complete design, including solutions for both physical (PHY) and link layer, and evaluates the performance of large-scale indoor positioning systems (IPSs) based on visible light communications (VLC). The triangulation method based on received signal strength (RSS) technique is employed for user localization. For the sake of signal separation at the receiver, each LED's position is encoded with a unique location identification (ID) using optical orthogonal codes (OOCs). A code re-use strategy is proposed to efficiently utilize the code resource. A novel enhancement method is also proposed to improve the system performance in terms of localization accuracy taking into account the impact of receiver orientation. Simulation results show that the maximum location error increases twice under the impact of receiver orientation when the polar angle is equal to θ = π/6. The effectiveness of the proposed localization enhancement method in reducing the average location error is also numerically confirmed. For the link layer design, a frame design with a 12-bit ID encoded by the Golay code for error correction is proposed. A simple proof-of-concept is implemented and experiments are conducted to analyze the overall system performance in terms of operation range and ID detectability. INDEX TERMS Indoor positioning system (IPS), visible light communications (VLC), receiver orientation, optical orthogonal codes (OOCs), received signal strength (RSS), triangulation method.

show abstract

Indoor high-precision three-dimensional positioning algorithm based on visible light communication and fingerprinting using K-means and random forest

Cited by 15 publications

References 20 publications

Precision indoor three‐dimensional visible light positioning using receiver diversity and multi‐layer perceptron neural network

Precision indoor three‐dimensional visible light positioning using receiver diversity and multi‐layer perceptron neural network

Adaptive Multi-Type Fingerprint Indoor Positioning and Localization Method Based on Multi-Task Learning and Weight Coefficients K-Nearest Neighbor

Design and Performance Evaluation of Large-Scale VLC-Based Indoor Positioning Systems Under Impact of Receiver Orientation

Contact Info

Product

Resources

About