A Fast Single-Site Fingerprint Localization Method in Massive MIMO System

Wang, Xiaojun; Liu, Lin; Lin, Yan; Chen, Xiaoshu

doi:10.1109/wcsp.2019.8927853

Cited by 14 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The operating principle of CSI-based fingerprinting is the same as for RSSI-based fingerprinting; yet much more accurate fingerprinting can be established because of the richer information contained in the CSI. For example, it is possible to obtain localization from the CSI of the link between target and a single anchor, as was done in [57], [58], [60], [77], [174], [208], [209]. Note that such an approach is not practical for RSSI-based fingerprinting because the same RSSI can occur at multiple locations around an anchor; after all RSSI is only a single scalar.…”

Section: A Feature Typementioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

Burghal,

Ravi,

Rao

et al. 2020

Preprint

View full text Add to dashboard Cite

The last few decades have witnessed a growing interest in location-based services. Using localization systems based on Radio Frequency (RF) signals has proven its efficacy for both indoor and outdoor applications. However, challenges remain with respect to both complexity and accuracy of such systems. Machine Learning (ML) is one of the most promising methods for mitigating these problems, as ML (especially deep learning) offers powerful practical data-driven tools that can be integrated into localization systems. In this paper, we provide a comprehensive survey of ML-based localization solutions that use RF signals. The survey spans different aspects, ranging from the system architectures, to the input features, the ML methods, and the datasets.A main point of the paper is the interaction between the domain knowledge arising from the physics of localization systems, and the various ML approaches. Besides the ML methods, the utilized input features play a major role in shaping the localization solution; we present a detailed discussion of the different features and what could influence them, be it the underlying wireless technology or standards or the preprocessing techniques. A detailed discussion is dedicated to the different ML methods that have been applied to localization problems, discussing the underlying problem and the solution structure. Furthermore, we summarize the different ways the datasets were acquired, and then list the publicly available ones. Overall, the survey categorizes and partly summarizes insights from almost 400 papers in this field.This survey is self-contained, as we provide a concise review of the main ML and wireless propagation concepts, which shall help the researchers in either field navigate through the surveyed solutions, and suggested open problems.

show abstract

Section: A Feature Typementioning

confidence: 99%

“…The advent of 5G has triggered interest in large antenna systems. Thus, many recent works proposed localization for massive MIMO [208], [209], [212]- [220].…”

Section: B Wireless Technologymentioning

confidence: 99%

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

Burghal,

Ravi,

Rao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, location-based services have attracted widespread attention in various industries. Different from the traditional positioning algorithm, the fingerprint positioning algorithm uses some corresponding characteristics generated during the signal transmission to achieve positioning [1][2][3]. In the process of wireless signal transmission, due to the influence of multipath effects, the channel characteristics at different physical locations will reflect some unique characteristics, which called the fingerprints of the signal.…”

Section: Introductionmentioning

confidence: 99%

Research on 3D Fingerprint Positioning Based on MIMO Base Station

Chen

Ren

Wang

et al. 2021

Proceedings of CECNet 2021

Self Cite

View full text Add to dashboard Cite

The aim of this article is to solve the problem that the accuracy of traditional positioning algorithm decreases in complex environment and to provide some ideas for the few researches of fingerprint localization algorithm in three-dimensional space. This paper builds a system model in a three-dimensional space, provides three reference point distribution methods, and discusses the positioning performance under these distribution methods. After that, based on the high base station deployment density, multi-point fusion positioning method is used to locate the target, which further improves the positioning accuracy and makes more effective use of reference point resources. Finally, a backward-assisted positioning method is proposed, which uses the position information of the positioned points to assist the positioning of the current point. Research shows that this method can improve the positioning accuracy and has good versatility. (Foundation items: Social Development Projects of Jiangsu Science and Technology Department (No.BE2018704).)

show abstract

“…Through the above-mentioned series of processing, the fingerprint positioning algorithm transforms a positioning problem into a pattern recognition problem. Literature [3][4] use channel state information to achieve reliable fingerprint positioning, and literature [5][6] combine the 5th Generation (5G) massive multiple-in multiple-out (MIMO) scenarios to explore the application prospects of fingerprint positioning in the new context. The flow chart of the fingerprint location algorithm is shown in Figure .1 [7][8].…”

Section: Introductionmentioning

confidence: 99%

Scattering Clustering Method for Terminal Fingerprint Positioning Based on MIMO Base Station

Tang

Ren

Wang

et al. 2021

Proceedings of CECNet 2021

Self Cite

View full text Add to dashboard Cite

With the rapid development of wireless communication technology, location-based services are playing an increasingly important role in people’s lives. However, as the living environment becomes more and more complex, the existence of obstructions and various scatterers makes the accuracy of traditional positioning algorithms decrease, thus, fingerprint positioning has gradually become a research hotspot in the field of positioning. This paper researches the 5th Generation (5G) fingerprint location method based on machine learning. A massive multiple-in multiple-out (MIMO) channel is constructed on the MATLAB simulation platform, from which the fingerprint information is extracted to establish a fingerprint database. Considering the huge amount of data in the fingerprint database, and under the multipath effect, the channel characteristics are mainly affected by the scatterers near the point to be located. This paper proposes a scattering-based clustering method that combines the particularity of multipath propagation for clustering. Research shows that this method has excellent clustering effects, which can effectively improve algorithm efficiency and reduce data storage pressure on the base station side. (Foundation items: Social Development Projects of Jiangsu Science and Technology Department (No.BE2018704).)

show abstract

A Fast Single-Site Fingerprint Localization Method in Massive MIMO System

Cited by 14 publications

References 14 publications

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

Research on 3D Fingerprint Positioning Based on MIMO Base Station

Scattering Clustering Method for Terminal Fingerprint Positioning Based on MIMO Base Station

Contact Info

Product

Resources

About