2021
DOI: 10.1155/2021/2017208
|View full text |Cite
|
Sign up to set email alerts
|

Fast Construction of the Radio Map Based on the Improved Low‐Rank Matrix Completion and Recovery Method for an Indoor Positioning System

Abstract: With the development of information technology, indoor positioning technology has been rapidly evolving. Due to the advantages of high positioning accuracy, low cost, and wide coverage simultaneously, received signal strength- (RSS-) based WLAN indoor positioning technology has become one of the mainstream technologies. A radio map is the basis for the realization of the WLAN positioning system. However, by reasons of the huge workload of RSS collection, the instability of wireless signal strength, and the dis… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 29 publications
0
5
0
Order By: Relevance
“…Finally, several works have been done using matrix completion for radio map estimation [50], [51], avoiding the training phase with reference maps and where kernel methods are not used. For example, Wang et al [52] used matrix completion for low-ranked matrices to construct radio maps in an indoor system.…”
Section: Neural Network and Matrix Completion Approachmentioning
confidence: 99%
“…Finally, several works have been done using matrix completion for radio map estimation [50], [51], avoiding the training phase with reference maps and where kernel methods are not used. For example, Wang et al [52] used matrix completion for low-ranked matrices to construct radio maps in an indoor system.…”
Section: Neural Network and Matrix Completion Approachmentioning
confidence: 99%
“…To ensure faster and accurate construction of the radio map, a hybrid method integrating the crowd-sourcing approach with some path loss model and interpolation technique is proposed in [22]. In [23], the lowrank matrix completion algorithm is used on the RSS data collected from fewer evenly arranged RPs in the positioning area to construct the radio map. A thorough investigation on how the radio map degrades due to several factors like environmental dynamics, changes in wireless infrastructure and/or indoor layout etc., is carried out by the researchers in [24].…”
Section: Related Workmentioning
confidence: 99%
“…In view of that, it is possible to collect RSS values at only a small number of RPs and to further fill up the RSS values in the radio map in order to convert it into a complete Wi-Fi fingerprinting database using the low-rank matrix completion algorithm with the Frobenius parameter (F-parameter) integrated into it for the stability of the model solution when filling up the data. Apart from that, the low-rank matrix recovery algorithm is also used to suppress noise caused by the environment and equipment [15].…”
Section: Related Workmentioning
confidence: 99%