Robust Wi-Fi indoor localization with KPCA feature extraction of dual band signals

Zhao, Linsheng; Wang, Hongpeng; Jiarui, Wang; Gao, Haiming; Liu, Jingtai

doi:10.1109/robio.2017.8324533

Cited by 7 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the poor performance of GPS signals indoors, various wireless technologies have been proposed and studied to solve indoor positioning problems with greater accuracy [ 45 , 46 , 47 ]. Despite advances in the location service industry over the past decades, indoor positioning remains a more complex task than outdoor positioning due to the complex nature of the indoor environment, where radio signals are characterized by NLOS propagation, multipath effects, and a dynamic environment [ 45 , 46 , 47 , 48 ]. Thus, an indoor positioning system should not only have higher positioning accuracy, but also low computational complexity and a short positioning time.…”

Section: Related Workmentioning

confidence: 99%

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection

Gidey

Guo

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper presents the application of heterogeneous transfer learning (HetTL) methods which consider hybrid feature selection to reduce the training calibration effort and the noise generated by fingerprint duplicates obtained from multiple Wi-Fi access points. The Cramer–Rao Lower Bound analysis (CRLB) was also applied to evaluate and estimate a lower limit for the variance of a parameter estimator used to analyze positioning performance. We developed two novel algorithms for feature selection in fingerprint-based indoor positioning problems (IPP) to enhance positioning performance in the target domain with the HetTL. The algorithms comprised two scenarios: (i) a principal component analysis-based approach (PCA-based) and (ii) a hybrid approach that takes both PCA and correlation effect analysis into account (hybrid scenario). Accordingly, a new feature vector was constructed by retaining only the most significant predictors, and the most efficient feature dimensions were also determined by using a hybrid-based approach. Experimental results showed that the hybrid-based proposed algorithm has the minimum mean absolute error. The CRLB analysis also showed that the number of Wi-Fi access points could affect the lower bound location estimation error; however, identifying the most significant predictors is an effective approach to improve positioning performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection

Gidey

Guo

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Some studies used dual-band RSS for fingerprint-based positioning [ 32 , 33 , 34 , 35 , 36 , 37 ]. Consequently, the accuracy of these methods depends on site surveys, and vulnerable to environmental changes.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Approach for Indoor Localization Using Received Signal Strength of Dual-Band Wi-Fi

Lee

Park

Kim

et al. 2021

Sensors

View full text Add to dashboard Cite

In this paper, we propose a hybrid localization algorithm to boost the accuracy of range-based localization by improving the ranging accuracy under indoor non-line-of-sight (NLOS) conditions. We replaced the ranging part of the rule-based localization method with a deep regression model that uses data-driven learning with dual-band received signal strength (RSS). The ranging error caused by the NLOS conditions was effectively reduced by using the deep regression method. As a consequence, the positioning error could be reduced under NLOS conditions. The performance of the proposed method was verified through a ray-tracing-based simulation for indoor spaces. The proposed scheme showed a reduction in the positioning error of at least 22.3% in terms of the median root mean square error compared to the existing methods. In addition, we verified that the proposed method was robust to changes in the indoor structure.

show abstract

“…Specifically, some approaches compensate the lower complexity of the implemented infrastructure with solutions characterized by a higher computational cost enabling accuracy enhancements such as in [4], where likelihood functions are implemented in machine learning (ML) algorithms. Localization methods based on ML are discussed also in [5][6][7], where in the latter such algorithm is applied to a WiFi dual-band-based position system. In this context, processing solutions that can extract the location estimate in the case of limited data availability have also been investigated, as described in [8].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Dual-Band Direction of Arrival Estimation in Multipath Scenarios

et al. 2021

View full text Add to dashboard Cite

The present paper analyzes the performance of localization systems, based on dual-band Direction of Arrival (DoA) approach, in multi-path affected scenarios. The implemented DoA estimation, which belongs to the so-called Space and Frequency Division Multiple Access (SFDMA) technique, takes advantage of the use of two uncorrelated communication carrier frequencies, as already demonstrated by the authors. Starting from these results, this paper provides, first, the methodology followed to describe the localization system in the proposed simulation environment, and, as a second step, describes how multi-path effects may be taken into account through a set of full-wave simulations. The latter follows an approach based on the two-ray model. The validation of the proposed approach is demonstrated by simulations over a wide range of virtual scenarios. The analysis of the results highlights the ability of the proposed approach to describe multi-path effects and confirms enhancements in DoA estimation as experimentally evaluated by the same authors. To further assess the performance of the aforementioned simulation environment, a comparison between simulated and measured results was carried out, confirming the capability to predict DoA performance.

show abstract

Robust Wi-Fi indoor localization with KPCA feature extraction of dual band signals

Cited by 7 publications

References 24 publications

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection

Hybrid Approach for Indoor Localization Using Received Signal Strength of Dual-Band Wi-Fi

Analysis of Dual-Band Direction of Arrival Estimation in Multipath Scenarios

Contact Info

Product

Resources

About