Indoor localization based on response rate of bluetooth inquiries

Bargh, Mortaza S.; Groote, Robert de

doi:10.1145/1410012.1410024

Cited by 105 publications

(43 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paschalidis et al (2009) use a Kullback-Leibler-based statistical framework for Wireless Sensor Networks localisation (consisting in null hypothesis testing for each fingerprint). Bargh et al (2008) use the Kullback-Leibler (KL) divergence to find the (single) nearest neighbour in the space of multinomial counts of Bluetooth dongles. Milioris et al (2010) also perform nearest neighbour matching by resorting to KL divergence, this time on RSSI from WiFi data, but they assume that the RSSI from multiple APs is simply a multivariate Gaussian, a hypothesis that is not always true, as pointed out in Section 1.1.…”

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

Probability kernel regression for WiFi localisation

Mirowski¹,

Whiting²,

Steck³

et al. 2012

Journal of Location Based Services

View full text Add to dashboard Cite

Various methods have been developed for indoor localisation using WLAN signals. Algorithms that fingerprint the Received Signal Strength Indication (RSSI) of WiFi for different locations can achieve tracking accuracies of the order of a few meters. RSSI fingerprinting suffers though from two main limitations: first, as the signal environment changes, so does the fingerprint database, which requires regular updates; second, it has been reported that, in practice, certain devices record more complex (e.g bimodal) distributions of WiFi signals, precluding algorithms based on the mean RSSI. Mirowski et al. (2011) have recently introduced a simple methodology that takes into account the full distribution for computing similarities among fingerprints using Kullback-Leibler divergence, and then performs localisation through kernel regression. Their algorithm provides a natural way of smoothing over time and motion trajectories and can be applied directly to histograms of WiFi connections to access points, ignoring RSSI distributions, hence removing the need for fingerprint recalibration. It has been shown to outperform nearest neighbours or Kalman and particle filters, achieving up to 1m accuracy in office environments. In this paper, we focus on the relevance of Gaussian or non-Gaussian distributions for modeling RSSI distributions by considering additional probabilistic kernels for comparing Gaussian distributions and by evaluating them on three contrasting datasets. We discuss their limitations and formulate how the KL-divergence kernel regression algorithm bridges the gap with other WiFi localisation algorithms, notably Bayesian networks, SVMs and K nearest neighbours. Finally, we revisit the assumptions on the fingerprint maps and overview practical WiFi localisation software implementation.

show abstract

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

Probability kernel regression for WiFi localisation

Mirowski¹,

Whiting²,

Steck³

et al. 2012

Journal of Location Based Services

View full text Add to dashboard Cite

show abstract

“…For instance, Bargh et al presented location fingerprinting at room-level accuracy, using response rates of Bluetooth dongles [13]. Denby et al compared Gaussian processes, knearest neighbors, and support vector machines (SVMs) for full-band GSM fingerprinting in a city flat at room-level accuracy [14].…”

Section: Related Workmentioning

confidence: 99%

Efficient self-adjusting, similarity-based location fingerprinting with passive UHF RFID

Vorst

Koch

Zell

2011

2011 IEEE International Conference on RFID-Technologies and Applications

View full text Add to dashboard Cite

Abstract-In this paper we present extensive experimental results of location fingerprinting with passive UHF radio-frequency identification (RFID). As recent passive RFID hardware provides information about received signal strength (RSS), we evaluate its usefulness in the context of fingerprinting based on classical vector similarity measures. We analyze the impact of decisive parameters of the applied approach and also select them automatically via cross-validation, including the most appropriate similarity measure. A further novelty is an RSS thresholding mechanism which reduces the computational demands of comparing fingerprints. This technique is especially useful in surroundings which are densely equipped with RFID tags, such as future supermarkets or logistic centers. We conducted realworld experiments with a mobile robot and two different RFID readers. Results are reported both for global localization in each time frame and for time-filtered position tracking. We provide the experimental data of this work for download.

show abstract

“…Indoor localization algorithms based on ZigBee, Bluetooth [5] [6] and WiFi [3] [7] almost use RSSI technology which needs to add some infrastructure and their accuracy is similar, about 2 meters [3] [4] [5]. Positioning accuracies employing of RFID [8] [9], UWB [10] [11] and ultrasonic [12] [13] are much higher, but they require increasing emission and receiving equipment which also cost much more.…”

Section: Introductionmentioning

confidence: 99%

Robust Local Weighted Regression for Magnetic Map-Based Localization on Smartphone Platform

Meng¹,

Wang²,

Wang³

et al. 2017

JCC

View full text Add to dashboard Cite

The magnetic information measured on the smartphone platform has a large fluctuation and the research of indoor localization algorithm based on smartphone platform is less. Indoor localization algorithm on smartphone platform based on particle filter is studied. Robust local weighted regression is used to smooth the original magnetic data in the process of constructing magnetic map. Use moving average filtering model to filter the online magnetic observation data in positioning process. Compare processed online magnetic data with processed magnetic map collected by smartphone platform and the average matching error is 0.3941uT. Average positioning error is 0.229 meter when using processed online and map data.

show abstract

Indoor localization based on response rate of bluetooth inquiries

Cited by 105 publications

References 10 publications

Probability kernel regression for WiFi localisation

Probability kernel regression for WiFi localisation

Efficient self-adjusting, similarity-based location fingerprinting with passive UHF RFID

Robust Local Weighted Regression for Magnetic Map-Based Localization on Smartphone Platform

Contact Info

Product

Resources

About