A realistic evaluation of indoor positioning systems based on Wi-Fi fingerprinting: The 2015 EvAAL-ETRI competition

@article{TorresSospedra2017ARE,
  title={A realistic evaluation of indoor positioning systems based on Wi-Fi fingerprinting: The 2015 EvAAL-ETRI competition},
  author={Joaqu{\'i}n Torres-Sospedra and Adriano J. C. Moreira and Stefan Knauth and Rafael Berkvens and Ra{\'u}l Montoliu and {\'O}scar Belmonte and Sergi Trilles and Maria Jo{\~a}o Nicolau and Filipe Meneses and Ant{\'o}nio D. Costa and Athanasios Koukofikis and Maarten Weyn and Herbert Peremans},
  journal={J. Ambient Intell. Smart Environ.},
  year={2017},
  volume={9},
  pages={263-279}
}
This paper presents results from comparing different Wi-Fi fingerprinting algorithms on the same private dataset. The algorithms where realized by independent teams in the frame of the off-site track of the EvAAL-ETRI Indoor Localization Competition which was part of the Sixth International Conference on Indoor Positioning and Indoor Navigation (IPIN 2015). Competitors designed and validated their algorithms against the publicly available UJIIndoorLoc database which contains a huge referenceand… 
A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting
TLDR
A comprehensive comparative study of existing methods to reduce the complexity and size of the radio map used at the operational stage and introduces a new evaluation framework with multiple datasets, aiming at getting more general results and contributing to a better reproducibility of new proposed solutions in the future.
Machine Learning applied to Wi-Fi fingerprinting: The experiences of the Ubiqum Challenge
TLDR
The results show that state-of-art Machine Learning methods provide good positioning results, but expertise on the problem is still needed.
Analysis of Sources of Large Positioning Errors in Deterministic Fingerprinting
TLDR
This paper investigates why large positioning errors occur in Wi-Fi fingerprinting and how to detect them by using the received signal strength intensities.
Comparing the Performance of Indoor Localization Systems through the EvAAL Framework
TLDR
The general lines of the EvAAL benchmarking framework are introduced, aimed at a fair comparison of indoor positioning systems through a challenging competition under complex, realistic conditions, and shows how it was used in the 2016 IPIN Competition.
IndoorLoc platform: A public repository for comparing and evaluating indoor positioning systems
TLDR
The proposed web platform can be used to download datasets, learn how some well-known algorithms work, study the implementation of those algorithms, test the methods, and even upload indoor positioning estimations of the user's methods to check the accuracy when comparing against the results provided by other methods already included in a ranking.
Wi-Fi Crowdsourced Fingerprinting Dataset for Indoor Positioning
TLDR
A new openly available Wi-Fi fingerprint dataset, comprised of 4648 fingerprints collected with 21 devices in a university building in Tampere, Finland, is presented and some benchmark indoor positioning results using these data are presented.
Indoor Fingerprint Positioning Based on Wi-Fi: An Overview
TLDR
An overview of indoor fingerprint positioning based on Wi-Fi is provided and it is hoped that this research will serve as a stepping stone for those interested in advancing indoor positioning.
Ensembling Multiple Radio Maps with Dynamic Noise in Fingerprint-based Indoor Positioning
TLDR
A novel approach to add random noise to the radio map which will be used in combination with an ensemble model to improve the baseline method results in around 10% on average.
IndoorLoc Platform: A Web Tool to Support the Comparison of Indoor Positioning Systems
TLDR
This chapter shows a comparative study of the accuracy of two well-known fingerprinting-based indoor localization algorithms using the datasets included in the IndoorLoc Platform, a web tool to support the comparison and the evaluation of indoor positioning algorithms.
The Smartphone-Based Offline Indoor Location Competition at IPIN 2016: Analysis and Future Work
TLDR
The competition permits a coherent evaluation method of the competitors’ estimations, where inside information to fine-tune their systems is not offered, and thus provides a good starting point to introduce a fair comparison between the smartphone-based systems found in the literature.
...
1
2
3
4
...

References

SHOWING 1-10 OF 78 REFERENCES
Wi-Fi fingerprinting in the real world - RTLS@UM at the EvAAL competition
TLDR
The experience of the RTLS@UM team in participating in track 3 of the EvAAL competition is described, which describes the performance, in the real world, of the several existing solutions based on Wi-Fi fingerprinting.
Comprehensive analysis of distance and similarity measures for Wi-Fi fingerprinting indoor positioning systems
TLDR
The results shown in this paper demonstrate that researchers and developers should take into account the conclusions arisen in this work in order to improve the accuracy of their systems.
Combining similarity functions and majority rules for multi-building, multi-floor, WiFi positioning
TLDR
The proposed fingerprint method uses a previously stored map of the signal strength at several positions and determines the position using similarity functions and majority rules, and compares different similarity functions to understand their impact on the accuracy of the positioning system.
Wi-Fi multi-floor indoor positioning considering architectural aspects and controlled computational complexity
TLDR
The authors apply two combined techniques that improve localization accuracy: unsupervised clustering (K-medians and Kohonen layer) and majority voting committees of backpropagation artificial neural networks (ANNs).
Platform for benchmarking of RF-based indoor localization solutions
TLDR
The EVARILOS Benchmarking Platform is presented, which enables automated evaluation and comparison of multiple solutions in different environments using multiple evaluation metrics, and demonstrates the need for objective evaluation methods that consider multiple evaluation criteria inDifferent environments.
Efficient Techniques and Algorithms for Improving Indoor Localization Precision on WLAN Networks Applications
TLDR
This paper compares the use of radio frequency power levels and relative time delays based on ray-tracing as detection methods to estimate the localization of a set of mobile station using the fingerprint technique and shows that more precision can be obtained in the localization process by means of relative delay instead of RF power detection method.
Fingerprint calibrated centroid and scalar product correlation RSSI positioning in large environments
TLDR
The design and result of a fingerprint calibrated weighted centroid localization (FCWC) algorithm is outlined, discussed and evaluated against the UJIIndoorLoc data set and a scalar product correlation fingerprinting (SPCF) algorithm has been implemented.
Indoor Localization Using FM Signals
TLDR
FM radio signal RSSI values can be used to achieve room-level indoor localization with similar or better accuracy to the one achieved by WiFi signals, and the localization accuracy increases as much as 83 percent when FM and WiFi signals are combined to generate wireless fingerprints.
Influence of human absorption of Wi-Fi signal in indoor positioning with Wi-Fi fingerprinting
For outdoors, Global Network Navigation Systems have become the standard mechanism of positioning; but for indoor environments, there is still no standard system. Several mechanisms have been
A survey of experimental evaluation in indoor localization research
TLDR
This work looks at the articles published in the proceedings of IPIN by IEEE Xplore from 2010 to 2014, and analyzes the development of evaluation methods.
...
1
2
3
4
5
...