“…Learning such a model is performed using a feed-forward NNet in [13] or kernel-based machine learning methods, such as support vector machines (SVM) in [10] or ridge regression (RR) in [28]. Reference [23] proposes an analytical localization method (AL), that uses the distances between the offline positions and the anchors to generate the fingerprinting database, instead of measuring RSSIs. Then the node while moving uses its collected RSSIs to generate a characteristic vector, which would be compared with the fingerprints to localize itself.…”
Section: F Comparison With Fingerprint-based Methodsmentioning
confidence: 99%
“…Anchors could be fixed, or mobile but equipped with GPS, while nodes are mainly mobile having uncontrolled mobility and they exchange information with anchors for localization. This kind of method is called anchor-based localization [22,23].…”
Section: Introductionmentioning
confidence: 99%
“…However, this method has low accuracy compared with methods using RSSI-fingerprints. In [23], the authors propose to build the fingerprinting database by using interpolation while having very low measurements. Localization could then be performed using different techniques.…”
This paper considers the problem of decentralized localization in wireless sensor networks (WSNs). The problem is set by combining both radio-fingerprints and accelerometer information. It is then resolved in a decentralized manner where the surveillance area is divided into several zones equipped with calculators. The proposed algorithm consists of computing first estimates using received signal strength indicator (RSSI)-fingerprints, then correcting them using accelerometer information leading to more accurate estimates. Computations are performed using the interval analysis and the Kalman filter in a simulated environment.
“…Learning such a model is performed using a feed-forward NNet in [13] or kernel-based machine learning methods, such as support vector machines (SVM) in [10] or ridge regression (RR) in [28]. Reference [23] proposes an analytical localization method (AL), that uses the distances between the offline positions and the anchors to generate the fingerprinting database, instead of measuring RSSIs. Then the node while moving uses its collected RSSIs to generate a characteristic vector, which would be compared with the fingerprints to localize itself.…”
Section: F Comparison With Fingerprint-based Methodsmentioning
confidence: 99%
“…Anchors could be fixed, or mobile but equipped with GPS, while nodes are mainly mobile having uncontrolled mobility and they exchange information with anchors for localization. This kind of method is called anchor-based localization [22,23].…”
Section: Introductionmentioning
confidence: 99%
“…However, this method has low accuracy compared with methods using RSSI-fingerprints. In [23], the authors propose to build the fingerprinting database by using interpolation while having very low measurements. Localization could then be performed using different techniques.…”
This paper considers the problem of decentralized localization in wireless sensor networks (WSNs). The problem is set by combining both radio-fingerprints and accelerometer information. It is then resolved in a decentralized manner where the surveillance area is divided into several zones equipped with calculators. The proposed algorithm consists of computing first estimates using received signal strength indicator (RSSI)-fingerprints, then correcting them using accelerometer information leading to more accurate estimates. Computations are performed using the interval analysis and the Kalman filter in a simulated environment.
“…The remaining RP RSS values are estimated mathematically. Linear and exponential taper functions are used by [ 24 ]; the Motley–Keenan model [ 25 ] and a semi-supervised manifold learning technique [ 26 ] are also used by researchers [ 27 ]. Liqun Li propose Modellet [ 28 ] to approximate the actual radio map by unifying model-based and fingerprint-based approaches.…”
Indoor localization using Received Signal Strength Indication (RSSI) fingerprinting has been extensively studied for decades. The positioning accuracy is highly dependent on the density of the signal database. In areas without calibration data, however, this algorithm breaks down. Building and updating a dense signal database is labor intensive, expensive, and even impossible in some areas. Researchers are continually searching for better algorithms to create and update dense databases more efficiently. In this paper, we propose a scalable indoor positioning algorithm that works both in surveyed and unsurveyed areas. We first propose Minimum Inverse Distance (MID) algorithm to build a virtual database with uniformly distributed virtual Reference Points (RP). The area covered by the virtual RPs can be larger than the surveyed area. A Local Gaussian Process (LGP) is then applied to estimate the virtual RPs’ RSSI values based on the crowdsourced training data. Finally, we improve the Bayesian algorithm to estimate the user’s location using the virtual database. All the parameters are optimized by simulations, and the new algorithm is tested on real-case scenarios. The results show that the new algorithm improves the accuracy by 25.5% in the surveyed area, with an average positioning error below 2.2 m for 80% of the cases. Moreover, the proposed algorithm can localize the users in the neighboring unsurveyed area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.