Enhanced Radio Map Interpolation Methods Based on Dimensionality Reduction and Clustering

Khoo, Hui Wen; Ng, Yin Hoe; Tan, Chee Keong

doi:10.3390/electronics11162581

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, another commercial indoor localization system, HORUS [17], is presented in 2005 and it adopts a probabilistic strategy in which spatial and temporal RSS modellings are carried out. Since the introduction of RADAR and HORUS, numerous other fingerprint-based indoor positioning systems [18]- [21] have been developed, each with its own improvements and innovations. The field of indoor localization has continued to evolve, and new technologies and techniques have emerged, making indoor positioning systems more accurate, efficient, and widely used for various indoor applications.…”

Section: Related Workmentioning

confidence: 99%

Robust Access Points Selection Strategies for Dynamic Indoor Localization

Mazlan,

2024

IEEE Access

View full text Add to dashboard Cite

The proliferation of mobile devices has fueled the demand for indoor location-based services. Consequently, a plethora of techniques have emerged to facilitate object and device localization in indoor environments. Among these, fingerprint-based indoor localization systems, which leverage machine learning, stand out as a promising solution for providing accurate localization. Nonetheless, their performance is inherently reliant on the accuracy of the underlying database, and any changes in the indoor layout can significantly impact the wireless signals, subsequently affecting the localization accuracy. To circumvent this issue, this work proposes a novel access point (AP) selection framework to enhance the robustness of fingerprint-based indoor positioning systems in dynamic indoor environments. More specifically, a hybrid Wi-Fi and BLE fingerprint database is constructed by collecting received signal strength (RSS) from the predefined reference points (RPs). To ensure that the fingerprint database remains relevant over time, some RPs are designated as known points so that the system can periodically collect new RSS at the known points. Subsequently, the proposed scheme computes the differences between the RSS of the database and the updated RSS from the new layout to account for the changes occurred. The building-based, floor-based, and zone-based implementation modes determine which APs are reliable to be utilized during localization based on the RSS discrepancies observed in building, floor, and zone, respectively. Results demonstrate that the proposed building-based, floor-based, and zone-based AP selection schemes could achieve reduction in positioning error up to 28.86%, 33.53%, and 39.66%, respectively, compared to the baseline technique without AP selection schemes.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Access Points Selection Strategies for Dynamic Indoor Localization

Mazlan,

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [9], the authors use an optimal transport technique to find interpolations of histograms on arbitrary positions. With only one value on a position instead of a histogram, the interpolation techniques are countless, such as dimensionality reduction and clustering methods [15], Gaussian process regression [16], or more advanced techniques like BERT [17].…”

Section: Introductionmentioning

confidence: 99%

Practical and Parameterized Fingerprinting Through Maximal Filtering for Indoor Positioning

Daniş

2023

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

Fingerprinting techniques are known to perform better for radio-frequency based indoor positioning compared to the lateration-based techniques. However, accurate fingerprinting depends on a thorough prior scene analysis, in which the area should be described in terms of the signal parameters the positioning system deploys. This requires a heavy workload to build accurate systems, causing a trade-off between the accuracy and the practicality. In this work, we propose a chain of subsequent preprocessing techniques for generating accurate radio-frequency maps (RM). The techniques consiste of filtering the received signal strength indicator (RSSI) and interpolating the local probability distribution parameters. The proposed subsequent techniques generate smoother RMs and describe these maps with only two parameters per position. By plugging an adaptive particle filter as the position estimation algorithm, we show that the generated RMs increase the positioning accuracy significantly. We also investigate the relation between the practicality and the accuracy in terms of the invested time in the process of fingerprinting and the stored data to represent the RM. Alongside the increased accuracy of the proposed system, the approach allows a dramatic increase in the practicality of the fingerprinting technique.

show abstract

“…Devising new solutions to overcome radio map degradation. Significant efforts have been made in the past to develop methods to keep the radio maps up to date using interpolation, e.g., considering techniques such as Log-distance Path Loss (LDPL) [15][16][17], Radial Basis Functions (RBF) [18], Inverse Distance Weighted (IDW) [19,20], Voronoi tesselation [21], and Kriging [22,23].…”

mentioning

confidence: 99%

Collection of a Continuous Long-Term Dataset for the Evaluation of Wi-Fi-Fingerprinting-Based Indoor Positioning Systems

Silva

Pendão

Moreira

2022

Sensors

View full text Add to dashboard Cite

Indoor positioning and navigation have been attracting interest from the research community for quite some time. Nowadays, new fields, such as the Internet of Things, Industry 4.0, and augmented reality, are increasing the demand for indoor positioning solutions capable of delivering specific positioning performances not only in simulation but also in the real world; hence, validation in real-world environments is essential. However, collecting real-world data is a time-consuming and costly endeavor, and many research teams lack the resources to perform experiments across different environments, which are required for high-quality validation. Publicly available datasets are a solution that provides the necessary resources to perform this type of validation and to promote research work reproducibility. Unfortunately, for different reasons, and despite some initiatives promoting data sharing, the number and diversity of datasets available are still very limited. In this paper, we introduce and describe a new public dataset which has the unique characteristic of being collected over a long period (2+ years), and it can be used for different Wi-Fi-based positioning studies. In addition, we also describe the solution (Wireless Sensor Network (WSN) + mobile unit) developed to collect this dataset, allowing researchers to replicate the method and collect similar datasets in other spaces.

show abstract

Enhanced Radio Map Interpolation Methods Based on Dimensionality Reduction and Clustering

Cited by 6 publications

References 22 publications

Robust Access Points Selection Strategies for Dynamic Indoor Localization

Robust Access Points Selection Strategies for Dynamic Indoor Localization

Practical and Parameterized Fingerprinting Through Maximal Filtering for Indoor Positioning

Collection of a Continuous Long-Term Dataset for the Evaluation of Wi-Fi-Fingerprinting-Based Indoor Positioning Systems

Contact Info

Product

Resources

About