Indoor Localization Using Neural Networks with Location Fingerprints

Laoudias, Christos; Ηλιάδης, Δημήτριος Γ.; Kemppi, Paul; Panayiotou, Christos G.

doi:10.1007/978-3-642-04277-5_96

Cited by 37 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radar represents the fingerprint approach where kNN is used to determine the location. One can also employ other learning methods to relate a fingerprint to a location, such as probabilistically using Bayesian inference [24] or nonprobabilistically using an Artificial Neural Network (ANN) [25] or a Support Vector Machine (SVM) [26].…”

Section: Related Workmentioning

confidence: 99%

Fingerprint-based location tracking with Hodrick-Prescott filtering

Tran

Zhang

2014

2014 7th IFIP Wireless and Mobile Networking Conference (WMNC)

View full text Add to dashboard Cite

Conventional location fingerprint techniques usually require a prebuilt training set of fingerprints sampled at known locations, so that locations of future fingerprints can be determined by comparing to this set. For good accuracy, the training set should be large enough to appropriately cover the area. However, it is not always feasible to obtain a quality training set in practice, and so recent studies have resorted to utilizing fingerprints that are available but without location information. This paper investigates how these so-called unlabeled fingerprints can be useful for location tracking of a mobile device as it is moving. Specifically, we propose a fingerprint-based tracking approach based on Hodrick-Prescott filtering and substantiate its potential via an evaluation study.

show abstract

Section: Related Workmentioning

confidence: 99%

Fingerprint-based location tracking with Hodrick-Prescott filtering

Tran

Zhang

2014

2014 7th IFIP Wireless and Mobile Networking Conference (WMNC)

View full text Add to dashboard Cite

show abstract

“…Machine learning techniques, such as neural networks [36,64,65] or support vector machines (SVMs) [30,38] or genetic algorithms (GAs) [49] may take several hours to even days to converge to solution depending on the training database size. This has a significant impact on the performance of the IPS because it has the risk of running the system built upon a stale database for some period.…”

Section: Latencymentioning

confidence: 99%

A survey of calibration-free indoor positioning systems

Hossain

Soh

2015

Computer Communications

165

View full text Add to dashboard Cite

“…In the online phase, the beacon RSS measured in real-time by a client device is compared to the radio map to infer its location. To date, a wide variety of algorithms have been proposed to infer the user location, such as the nearest neighbor classification [6], Bayesian filtering [5], Bayesian networks [7] and neural networks [8].…”

Section: Introductionmentioning

confidence: 99%

“…In current literature [5][6][7][8][9], indoor localization algorithms are typically evaluated in the following manner. First, beacon RSS at calibration points are collected and processed to create a radio map of the target area.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wilocsim: Simulation Testbed for Wlan Location Fingerprinting Systems

Sapumohotti¹,

Alias²,

Tan³

2013

PIER B

View full text Add to dashboard Cite

Abstract-This paper introduces a novel simulation testbed for investigating WLAN indoor localization systems. This testbed referred to as WiLocSim consists of a novel beacon received signal strength (RSS) simulator which provides realistic modeling of beacon signal characteristics such as multipath propagation, measurement noise and body loss. Each component of the simulator is individually modeled and verified prior to integration. In addition, the capabilities of the testbed are demonstrated using two variants of the nearest neighbor classification based indoor localization algorithm. Unlike conventional measurement based performance evaluation, the proposed testbed provides a reproducible environment for accurate evaluation and analysis of indoor localization systems. More importantly, it significantly reduces the high labor cost typically required in measurement based testbed.

show abstract

Indoor Localization Using Neural Networks with Location Fingerprints

Cited by 37 publications

References 7 publications

Fingerprint-based location tracking with Hodrick-Prescott filtering

Fingerprint-based location tracking with Hodrick-Prescott filtering

A survey of calibration-free indoor positioning systems

Wilocsim: Simulation Testbed for Wlan Location Fingerprinting Systems

Contact Info

Product

Resources

About