Abstract
The indoor localization method based on the Received Signal Strength (RSS) fingerprint is widely used for its high positioning accuracy and low cost. However, the propagation behavior of radio signals in an indoor environment is complicated and always leads to the existence of outliers and noises that deviate from a normal RSS value in the database. The fingerprint database containing outliers and noises will severely degrade the performance of an indoor localization system. In this paper, an approach to reconstruct the fingerprint database is proposed with the purpose of mitigating the influences of outliers. More specifically, by exploiting the spatial and temporal correlations of RSS data, the database can be transformed into a low-rank matrix. Therefore, the RPCA (Robust Principle Component Analysis) technique can be applied to recover the low-rank matrix from a noisy matrix. In addition, we propose an improved RPCA model which takes advantage of the prior knowledge of a singular value and could remove outliers and structured noise simultaneously. The experimental results show that the proposed method can eliminate outliers and structured noise efficiently.
Highlights
With the rapidly increasing location-based service (LBS) [1], such as positioning, tracking, navigation, and location-based security, the indoor localization has attracted wide attention
We propose a fingerprint database reconstruction framework based on RPCA and present an improved weighted nuclear norm and multi-norm RPCA model, which utilizes the prior knowledge of singular values to enhance the low-rank property and eliminates both the outliers and structured noise in the meantime
DB( pct, d) has the best performance when the percentage of outliers is zero, which shows that this method can distinguish outliers and normal points accurately, but the RPCA-based method has a better performance than DB( pct, d) when the percentage of outliers is more than 10%
Summary
With the rapidly increasing location-based service (LBS) [1], such as positioning, tracking, navigation, and location-based security, the indoor localization has attracted wide attention. Signal Strength (RSS) [6] Concerning factors such as positioning accuracy, technical complexity, electromagnetic interference, and construction cost, the WLAN (Wireless Local Area Networks) indoor positioning technology based on RSS fingerprints has become the principal method with an acceptable positioning accuracy. The fingerprint-based positioning method is implemented in two phases: the off-line training phase and the online positioning phase. In the online positioning phase, the RSS information collected in real time is matched to the fingerprint database and the location can be estimated by many proposed methods, such as k-nearest neighbor. The noise and outliers will affect the accuracy of the fingerprint database and result in incorrect positioning information in the online phase
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have