Fingerprint-based Wi-Fi indoor localization using map and inertial sensors

Wang, Xingwang; Wei, Xiaohui; Liu, Yuanyuan; Yang, Kun; Du, Xuan

doi:10.1177/1550147717749817

Cited by 16 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Available walking paths abstracted from a floor plan are represented as a graph in Ref. [27]. This approach assumes that users move only along edges in the graph that form Markov chains.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-User Personal Indoor Localization System Employing Graph-Based Optimization

Nowicki

Skrzypczyński

2019

Sensors

View full text Add to dashboard Cite

Personal indoor localization with smartphones is a well-researched area, with a number of approaches solving the problem separately for individual users. Most commonly, a particle filter is used to fuse information from dead reckoning and WiFi or Bluetooth adapters to provide an accurate location of the person holding a smartphone. Unfortunately, the existing solutions largely ignore the gains that emerge when a single localization system estimates locations of multiple users in the same environment. Approaches based on filtration maintain only estimates of the current poses of the users, marginalizing the historical data. Therefore, it is difficult to fuse data from multiple individual trajectories that are usually not perfectly synchronized in time. We propose a system that fuses the information from WiFi and dead reckoning employing the graph-based optimization, which is widely applied in robotics. The presented system can be used for localization of a single user, but the improvement is especially visible when this approach is extended to a multi-user scenario. The article presents a number of experiments performed with a smartphone inside an office building. These experiments demonstrate that graph-based optimization can be used as an efficient fusion mechanism to obtain accurate trajectory estimates both in the case of a single user and in a multi-user indoor localization system. The code of our system together with recorded dataset will be made available when the paper gets published.

show abstract

“…Available walking paths abstracted from a floor plan are represented as a graph in Ref. [27]. This approach assumes that users move only along edges in the graph that form Markov chains.…”

Section: Related Workmentioning

confidence: 99%

“…To compute the absolute location from the matching of fingerprints we employ the WKNN approach [47], which proved to be reliable in a number of other positioning systems [17,27]. At first, WKNN finds the k most similar scans applying the chosen similarity norm s .…”

Section: Constraints In the Graph-based Optimizationmentioning

confidence: 99%

A Multi-User Personal Indoor Localization System Employing Graph-Based Optimization

Nowicki

Skrzypczyński

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Also, WLS is formulating for indoor localization [14]. To boost position systems supported RSS, LAN fingerprint conjointly has already been projected in [15]. One of the most important parts of the localization system is to axis points that are used in the target areas in order to achieve full coverage required for building a localization system.…”

Section: Introductionmentioning

confidence: 99%

Improving Indoor Localization System Using a Partitioning Technique Based on RSS and ToA

Mosleh

Abed

Hamza

2021

View full text Add to dashboard Cite

Designing a localization system for an indoor environment faces more challenges because of multipath and interference problems. In this field, the most important techniques used for such environment, are RSS and ToA which need to be improved especially from more interference because of the huge multipath problems. In this paper, a case study of a selected building is chosen in order to apply the proposed technique of this research. Such proposal is based on the PT ‎ of the area in the case study into MZ. Each zone is allocated special values for the parameters used to estimate the target positions. WI package is used to simulate the case study area and apply such proposal based on RSS and ToA. The results confirm that the estimated locations are close to the real locations by the average error of (2.8) meter and (0.192) meter for ToA corresponding one zone and four zones ‎respectively. ‎ In contrast, the results of our experiment show that the accuracy is improved from an average error of (2.4) meter and (0.217) meter for RSS corresponding one zone and four zones ‎respectively‎. Such results confirm that dividing the case study area into more zones leads to more accuracy.

show abstract

“…Also, Maximum Likelihood (ML) and weighted least-squares (WLS) have been formulating for indoor localization [23], [24]. To improve position systems based on RSS, Wi-Fi fingerprint also has already been proposed in [25], [26]. In this paper, the Multi-Zone technique will propose to mitigate the NLOS phenomenon and complexity into a crowded building.…”

Section: Introductionmentioning

confidence: 99%

Indoor Localization Based on Time of Arrival Using Multi-Zone Technique

Mosleh¹,

Mohammad²,

Daraj³

2020

Proceedings of the Proceedings of the 1st International Multi-Disciplinary Conference Theme: Sustainable Development and Smart

View full text Add to dashboard Cite

Indoor position localization suffers from the regressive signal when the system implement based on Receive Signal Strength (RSS) and time synchronization when implement based on Time of Arrival (ToA). Those problems lead to high error in terms of position localization. To mitigate those errors many techniques and methods are deployed such as NLOS identification, Maximum Likelihood (ML), and weighted least-squares (WLS). In this paper, a new technique based on optimization of transmitter location has been proposed by separating the case study building into multi-zone, each zone having specific parameters which defer from other ones. The deployed receivers were 8 for the zones (A-F) and 20 into the zone G to be 68 for the whole system. There are three transmitters deployed with a changeable position to select a better one. The results confirm that the error improved from (0.638m) based on individual TOA to (0.136m) by using propose Multi-zone ToA, while improved from (0.756m) rely on individual RSS to (0.1223m) based on Multi-Zone RSS.

show abstract

Fingerprint-based Wi-Fi indoor localization using map and inertial sensors

Cited by 16 publications

References 32 publications

A Multi-User Personal Indoor Localization System Employing Graph-Based Optimization

A Multi-User Personal Indoor Localization System Employing Graph-Based Optimization

Improving Indoor Localization System Using a Partitioning Technique Based on RSS and ToA

Indoor Localization Based on Time of Arrival Using Multi-Zone Technique

Contact Info

Product

Resources

About