Enhancing WiFi RSS fingerprint positioning accuracy: lobe-forming in radiation pattern enabled by an air-gap

Lembo, Sergio; Horsmanheimo, Seppo; Somersalo, Matti; Laukkanen, Matti; Tuomimäki, Lotta; Huilla, Sami

doi:10.1109/ipin.2019.8911820

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yu et al [20] solved the problem of inaccurate RSS data sources, where a practical algorithm for extracting RSS information is proposed. Besides, experimental results show that the positioning accuracy of the algorithm can reach 1.5 m. Lembo et al [21] gave the detailed analysis on the RSS measurement at the physical structure level and combined the neural network algorithm to improve positioning accuracy, which is proved to meet the needs of ideal positioning errors compared with the typical baselines. In the scenario where a smartphone is used indoors, Guo et al put up an RTT-RSS-based ranking algorithm with WiFi signals, and the experiment results show that the algorithm's accuracy can reach 1.435 m. Shu et al [22] proposed a prediction algorithm based on indoor WiFi data's queuing time, whose experimental results show that the proposed wheel model is consistent with the theoretical analysis and has strong applicability.…”

Section: Introductionmentioning

confidence: 99%

WiFi-Based Indoor Positioning and Communication: Empirical Model and Theoretical Analysis

Han

Wang

Huang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

GPS (Global Positioning System) has been developed more mature and perfect in outdoor positioning. However, because GPS signals cannot be effectively transmitted in a complex indoor environment, positioning and navigation cannot be performed in typical situations such as indoor emergency occurrence location determination, shopping mall guides, and intelligent service robot fixed-point services. With the deepening of related researches, technologies based on ultrasound, WiFi, Bluetooth, radio frequency identification, infrared, etc. have been used to achieve indoor target positioning. The traditional WiFi-based indoor positioning technology uses the RSS value and CSI value of the WiFi signal to build a fingerprint database for positioning. The algorithm is complex and highly cost, and the function is relatively single. In this paper, for the first time, we propose a new algorithm for integrating indoor target positioning and communication based on WiFi signals. Using RSS value of WiFi signal for target location and using CSI value for indoor wireless channel modeling to get the system transmission function to achieve communication purpose, the experimental results show that the positioning algorithm can achieve positioning within the ideal accuracy range, and the communication algorithm part can accurately recover the system function of the wireless multipath channel and finally achieve the goal of integration of positioning and communication based on the WiFi signal level.

show abstract

Section: Introductionmentioning

confidence: 99%

WiFi-Based Indoor Positioning and Communication: Empirical Model and Theoretical Analysis

Han

Wang

Huang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

Jointly beam stealing attackers detection and localization without training: an image processing viewpoint

Yang

Wei²,

Xu³

et al. 2022

Front. Comput. Sci.

View full text Add to dashboard Cite

A survey of deep learning approaches for WiFi-based indoor positioning

Feng

Nguyen

Luo

2021

Journal of Information and Telecommunication

View full text Add to dashboard Cite

One of the most popular approaches for indoor positioning is WiFi fingerprinting, which has been intrinsically tackled as a traditional machine learning problem since the beginning, to achieve a few metres of accuracy on average. In recent years, deep learning has emerged as an alternative approach, with a large number of publications reporting sub-metre positioning accuracy. Therefore, this survey presents a timely, comprehensive review of the most interesting deep learning methods being used for WiFi fingerprinting. In doing so, we aim to identify the most efficient neural networks, under a variety of positioning evaluation metrics for different readers. We will demonstrate that despite the new emerging WiFi signal measures (i.e. CSI and RTT), RSS produces competitive performances under deep learning. We will also show that simple neural networks outperform more complex ones in certain environments.

show abstract

Enhancing WiFi RSS fingerprint positioning accuracy: lobe-forming in radiation pattern enabled by an air-gap

Cited by 4 publications

References 29 publications

WiFi-Based Indoor Positioning and Communication: Empirical Model and Theoretical Analysis

WiFi-Based Indoor Positioning and Communication: Empirical Model and Theoretical Analysis

Jointly beam stealing attackers detection and localization without training: an image processing viewpoint

A survey of deep learning approaches for WiFi-based indoor positioning

Contact Info

Product

Resources

About