A modular classification model for received signal strength based location systems

Ahmad, Uzair; Gavrilov, A. V.; Lee, Sungyoung; Lee, Young-Koo

doi:10.1016/j.neucom.2007.11.045

Cited by 29 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most articles included in this section propose the localization of mobile targets using a two stage process [98,17,64,66,42,53,9,57,92,43,79,22,96,18,67,4,95,83]. The first stage consists of an off-line radio scene analysis (i.e., performed prior to localization) in which a www.intechopen.com…”

Section: Fingerprinting-based Localization Solutionsmentioning

confidence: 99%

“…The on-line stage comprises the active localization process where the mobile receiver extracts a fingerprint of the radio signal at an unknown location. Localization is commonly achieved by proximity techniques, i.e., finding the closest match between the features of the received radio signal and those stored in the radio map [98,17,64,66,42,22,18,67,4,57,92]. More accurate localization can be achieved using a triangulation-like process, in which several candidate locations (each with a fingerprint bearing some resemblance to that of the received signal) are geometrically combined to provide an estimate of the receiver location in space [43,53,79,67,95,83,9].…”

Section: Ambient Intelligence 56mentioning

confidence: 99%

“…More accurate localization can be achieved using a triangulation-like process, in which several candidate locations (each with a fingerprint bearing some resemblance to that of the received signal) are geometrically combined to provide an estimate of the receiver location in space [43,53,79,67,95,83,9]. Algorithms deployed in the selection of the closest match or matches from the radio map include: 1) nearest neighbours techniques and variations thereof [17,95,9]; 2) Bayesian statistical matching [98,92,43,64,66,67,83,57]; 3) maximum likelihood estimation [79,22]; 4) correlation discriminant kernel selection [42,53]; and neural networks [18,4]. Some fingerprinting techniques also provide coarse estimates of orientation, for example, 4 different orientations [92,9].…”

Section: Ambient Intelligence 56mentioning

confidence: 99%

See 2 more Smart Citations

A Review of Indoor Localization Technologies: towards Navigational Assistance for Topographical Disorientation

Torres-Solis¹,

Falk²,

Chau³

2010

Ambient Intelligence

100

View full text Add to dashboard Cite

Indoor localization technologies hold promise for many ambient intelligence applications, including in-situ navigational assistance for individuals with wayfinding difficulties. Given that the literature on indoor localization is vast and spans many different disciplines, we conducted a comprehensive review of the dominant technologies. We propose a taxonomy of localization technologies on the basis of the measured physical quantity. In particular, we identified, radio frequency, photonic, sonic and inertial localization technologies as leading solutions in the field. For each selected technology, the fundamental scientific mechanisms for localization are explained, key recent literature appraised and the merits and limitations are discussed. Recommendations are made regarding the creation of context-aware systems that can be used to enhance a user's topographical orientation skills.

show abstract

Section: Fingerprinting-based Localization Solutionsmentioning

confidence: 99%

Section: Ambient Intelligence 56mentioning

confidence: 99%

Section: Ambient Intelligence 56mentioning

confidence: 99%

See 1 more Smart Citation

A Review of Indoor Localization Technologies: towards Navigational Assistance for Topographical Disorientation

Torres-Solis¹,

Falk²,

Chau³

2010

Ambient Intelligence

100

View full text Add to dashboard Cite

show abstract

“…28 WLAN fingerprint localization algorithm is divided into two stages, ie, offline sampling stage and online positioning stage. 28 WLAN fingerprint localization algorithm is divided into two stages, ie, offline sampling stage and online positioning stage.…”

Section: Establishment Of Measurement Equation For Wlan Subsystemmentioning

confidence: 99%

Integrated positioning algorithm based on GPS/WLAN

Zheng

Zhao

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

In complex urban environment, GPS signals are susceptible to occlusion and interference; the positioning accuracy will be reduced or even impossible to locate. Today, Wireless Local Area Network (WLAN) localization technology can effectively supplement the blind spot of GPS signals. However, due to the instability of received signal strength (RSS), the positioning accuracy of WLAN is seriously affected. To solve the aforementioned problems, a GPS/WLAN integrated location algorithm based on particle filter is proposed. In our method, the federated Kalman filter is used to fuse the location information of GPS and WLAN, and then the important sampling function of the particle filter is generated by the fusion result. The updating of the particle weights is accomplished by the results of federated Kalman filter and map information. With the complementary characteristics of GPS and WLAN positioning technology, the experimental results show that our algorithm can effectively improves the coverage rate of GPS and the positioning accuracy of pedestrians in complex urban environment. Compared with GPS and WLAN single system and traditional fusion algorithm, the positioning accuracy of the proposed algorithm is significantly improved. KEYWORDSFederated Kalman filter, GPS/WLAN, information fusion, particle filter INTRODUCTIONGPS is an all-weather, full time satellite navigation system that developed by the US Department of defense. With the good positioning performance, GPS is the essential around the world. However, It shows that when users are in hot spots such as urban canyons, buildings, and other activities, terrible positioning accuracy will occur. 1 It means that the navigation technology are facing the following challenges: (1) GPS signal is susceptible to interference.(2) Its number of visible satellites is small.With the rapid development of wireless network technology and pervasive computing, Location-Based Services (LBS) is attracting more and more attention from industry and academia. Obviously, positioning technology is the key to LBS. Therefore, with the boom of LBS and the urgent need for location services in urban environments, wireless location technology has developed rapidly. It includes WLAN, RFID, UWB, Zigbee, Bluetooth, Infrared, and other positioning methods. 2 However, a single signal often cannot cover all the space in an urban environment, so wireless positioning technology is required to be combined with GPS.In order to further improve the positioning accuracy of the combined system while expanding the coverage of the positioning system, and considering the extensive laying of WLAN, this paper proposes a GPS/WLAN combinatorial positioning algorithm based on improved particle filter algorithm. In the particle filtering process, which is fused with GPS and WLAN, the importance sampling function is generated by the federated Kalman filter. The weight of the particle is determined by the building map information and the distance between each particle and the positioning result. The simulation and exp...

show abstract

“…It is noticed that there is a trade-off between cost and performance, and researchers try to find the balance between them. There has been research on measurements and propagation modeling [5]- [8], some of which pays more attention to estimation of position [4], [5], [9], while others focus on the services based on location [10].…”

Section: Introductionmentioning

confidence: 99%

A New Indoor Localization Method Based on Inversion Propagation Model

Xie

Wang

Xue

2010

2010 International Conference on Computational Intelligence and Software Engineering

View full text Add to dashboard Cite

The popularity of WLAN and mobile devices makes the development and widely use of location-aware systems and services possible. Since the Received Signal Strength Indication (RSSI) can be obtained by most mobile devices, the fingerprinting method based on RSSI becomes a simple and efficient method of Indoor Location (IL). This method needs to use the empirical measurements, propagation modeling or their combination to build the fingerprinting map in the offline phase, and the map plays an important role in the location process. The inversion propagation model can predict the propagation loss between any two points along the virtual propagation path from the basestation to the mobile-station, which precision has been presented in [1], [2]. In this paper, the algorithm of Inversion Propagation Model is used to build the fingerprinting map in order to find a new method that can keep a high degree of accuracy as well as simplify the process and improve the efficiency of map building.

show abstract

A modular classification model for received signal strength based location systems

Cited by 29 publications

References 23 publications

A Review of Indoor Localization Technologies: towards Navigational Assistance for Topographical Disorientation

A Review of Indoor Localization Technologies: towards Navigational Assistance for Topographical Disorientation

Integrated positioning algorithm based on GPS/WLAN

A New Indoor Localization Method Based on Inversion Propagation Model

Contact Info

Product

Resources

About