Orientation-aware indoor localization using affinity propagation and compressive sensing

Abstract

Abstract-The sparse nature of location finding makes it desirable to exploit the theory of compressive sensing for indoor localization. In this paper, we propose a received signal strength (RSS)-based localization scheme in Wireless Local Area Networks (WLANs) using the theory of compressive sensing (CS), which offers accurate recovery of sparse signals from a small number of measurements by solving an ℓ1-minimization problem. In order to mitigate the effects of RSS variations due to channel impediments and mobile device orientation, a two-step localization scheme is proposed by exploiting affinity propagation for coarse localization followed by a CS-based fine localization to further improve the accuracy. We implement the localization algorithm on a WiFi-integrated mobile device to evaluate the performance. Experimental results indicate that the proposed system leads to substantial improvements on localization accuracy and complexity over the widely used traditional fingerprinting methods.

Indoor Localization and Radio Map Estimation Using Unsupervised Manifold Alignment with Geometry Perturbation

“…users are sparse in the spatial domain and compressive sensing is employed for location estimation. The effect of device orientation is also taken into account in [11], [12]. The problem is also treated as sparse in [16], in which the fingerprinting map is constructed by taking into account the cross-correlation information of the signals at different APs.…”

Indoor Localization in the Presence of RSS Variations via Sparse Solution Finding and Dictionary Learning

“…In order to evaluate the performance of the proposed ARSL method and compare it with the ACS approach in [10] and the NN approach in [11], we performed extensive simulations. The localization area of the scene (which is the part of the third floor plane in the electrical engineering department of Nanjing Normal University) is shown in Fig.…”

“…However, the above methods neglected a number of factors that affect the RF signal propagation in an indoor environment including multi-path, channel fading, temperature and humidity variations, opening and closing of doors, and shadowing, etc., which will cause the system failure to achieve a high location accuracy. An affinitybased CS localization scheme (ACS) is proposed by exploiting affinity propagation and cluster matching to reduce the effects of RSS variations in [10]. But this method may result in large positioning bias for the reason that the false cluster matching can take place due to noisy measurements and environmental variations.…”

Online-Calibrated Cs-Based Indoor Localization Over Ieee 802.11 Wireless Infrastructure

“…Although the above methods can achieve better performance for solving the indoor localization problem than the traditional positioning methods, these works neglect a number of factors that affect the signal propagation in indoor environments. An affinity-based CS localization scheme (ACS) was proposed by exploiting affinity propagation and cluster matching to reduce the effects of RSS variations in [11]. However, this method may result in large positioning bias because the false cluster matching can take place due to environmental variations.…”

“…Since targets generally lie at a few points in the discrete spatial domain, this inherent sparsity can be exploited to convert the localization problem into a sparse recovery problem. In recent years, the compressive sensing (CS) theory that receives a great deal of attentions has been successfully applied to outdoor and indoor localization, which results in higher localization accuracy and reduces the dimensions of measurement vectors [7][8][9][10][11][12] Different from that the line-of-sight (LOS) path is dominant in an open outdoor environment, multipath is common in an indoor environment, and thus the change in RSS becomes unpredictable. Although these CS-based efforts are easy to implement, these algorithms ignore the effects of environmental variations, and thus they cannot achieve stable localization performance under complex indoor circumstances.…”