ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization

Artyom Nikitin; Christos Laoudias; Georgios Chatzimilioudis; Panagiotis Karras; Demetrios Zeinalipour-Yazti

doi:10.1109/MDM.2017.61

ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization

Artyom Nikitin, Christos Laoudias, Georgios Chatzimilioudis, Panagiotis Karras, Demetrios Zeinalipour-Yazti

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

1 Citation (Scopus)

475 Downloads (Pure)

Abstract

In this demonstration we present ACCES, a novel framework that enables quality assessment of arbitrary fingerprint maps and offline accuracy estimation for the task of fingerprint-based indoor localization. Our framework considers collected fingerprints disregarding the physical origin of the data. First, it applies a widely used statistical instrument, namely Gaussian Process Regression (GPR), for interpolation of the fingerprints. Then, to estimate the best possibly achievable localization accuracy at any location, it utilizes the Cramer-Rao Lower Bound (CRLB) with interpolated data as an input. Our demonstration entails a standalone version of the popular and open-source Anyplace Internet-based indoor navigation service in which the software modules of ACCES are integrated. At the conference, we will present the utility of our method in two modes: (i) Collection Mode, where attendees will be able to use our service directly to collect signal measurements over the venue using an Android smartphone; and (ii) Reflection Mode, where attendees will be able to observe the collected measurements and the respective ACCES accuracy estimations in the form of an overlay heatmap.

Original language	English
Title of host publication	18th IEEE International Conference on Mobile Data Management (MDM)
Number of pages	2
Publisher	IEEE
Publication date	30 May 2017
Pages	358-359
ISBN (Electronic)	978-1-5386-3932-0
DOIs	https://doi.org/10.1109/MDM.2017.61
Publication status	Published - 30 May 2017
Event	18th IEEE International Conference on Mobile Data Management - KAIST, Daejeon, Korea, Republic of Duration: 29 May 2017 → 1 Jun 2017 Conference number: 18 http://mdmconferences.org/mdm2017/

Conference

Conference	18th IEEE International Conference on Mobile Data Management
Number	18
Location	KAIST
Country/Territory	Korea, Republic of
City	Daejeon
Period	29/05/2017 → 01/06/2017
Internet address	http://mdmconferences.org/mdm2017/

Series	IEEE International Conference on Mobile Data Management (MDM)
ISSN	2375-0324

Access to Document

10.1109/MDM.2017.61

mdm17-acces-demoAccepted author manuscript, 1.3 MBLicence: Unspecified

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{4a997321ef774a1097f65c9d93faa456,

title = "ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization",

abstract = "In this demonstration we present ACCES, a novel framework that enables quality assessment of arbitrary fingerprint maps and offline accuracy estimation for the task of fingerprint-based indoor localization. Our framework considers collected fingerprints disregarding the physical origin of the data. First, it applies a widely used statistical instrument, namely Gaussian Process Regression (GPR), for interpolation of the fingerprints. Then, to estimate the best possibly achievable localization accuracy at any location, it utilizes the Cramer-Rao Lower Bound (CRLB) with interpolated data as an input. Our demonstration entails a standalone version of the popular and open-source Anyplace Internet-based indoor navigation service in which the software modules of ACCES are integrated. At the conference, we will present the utility of our method in two modes: (i) Collection Mode, where attendees will be able to use our service directly to collect signal measurements over the venue using an Android smartphone; and (ii) Reflection Mode, where attendees will be able to observe the collected measurements and the respective ACCES accuracy estimations in the form of an overlay heatmap.",

author = "Artyom Nikitin and Christos Laoudias and Georgios Chatzimilioudis and Panagiotis Karras and Demetrios Zeinalipour-Yazti",

year = "2017",

month = may,

day = "30",

doi = "10.1109/MDM.2017.61",

language = "English",

series = "IEEE International Conference on Mobile Data Management (MDM)",

publisher = "IEEE",

pages = "358--359",

booktitle = "18th IEEE International Conference on Mobile Data Management (MDM)",

address = "United States",

note = "18th IEEE International Conference on Mobile Data Management, MDM ; Conference date: 29-05-2017 Through 01-06-2017",

url = "http://mdmconferences.org/mdm2017/",

}

Nikitin, A, Laoudias, C, Chatzimilioudis, G, Karras, P & Zeinalipour-Yazti, D 2017, ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization. in 18th IEEE International Conference on Mobile Data Management (MDM). IEEE, IEEE International Conference on Mobile Data Management (MDM), pp. 358-359, 18th IEEE International Conference on Mobile Data Management, Daejeon, Korea, Republic of, 29/05/2017. https://doi.org/10.1109/MDM.2017.61

ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization. / Nikitin, Artyom; Laoudias, Christos; Chatzimilioudis, Georgios et al.
18th IEEE International Conference on Mobile Data Management (MDM). IEEE, 2017. p. 358-359 (IEEE International Conference on Mobile Data Management (MDM)).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - ACCES

T2 - 18th IEEE International Conference on Mobile Data Management

AU - Nikitin, Artyom

AU - Laoudias, Christos

AU - Chatzimilioudis, Georgios

AU - Karras, Panagiotis

AU - Zeinalipour-Yazti, Demetrios

N1 - Conference code: 18

PY - 2017/5/30

Y1 - 2017/5/30

N2 - In this demonstration we present ACCES, a novel framework that enables quality assessment of arbitrary fingerprint maps and offline accuracy estimation for the task of fingerprint-based indoor localization. Our framework considers collected fingerprints disregarding the physical origin of the data. First, it applies a widely used statistical instrument, namely Gaussian Process Regression (GPR), for interpolation of the fingerprints. Then, to estimate the best possibly achievable localization accuracy at any location, it utilizes the Cramer-Rao Lower Bound (CRLB) with interpolated data as an input. Our demonstration entails a standalone version of the popular and open-source Anyplace Internet-based indoor navigation service in which the software modules of ACCES are integrated. At the conference, we will present the utility of our method in two modes: (i) Collection Mode, where attendees will be able to use our service directly to collect signal measurements over the venue using an Android smartphone; and (ii) Reflection Mode, where attendees will be able to observe the collected measurements and the respective ACCES accuracy estimations in the form of an overlay heatmap.

AB - In this demonstration we present ACCES, a novel framework that enables quality assessment of arbitrary fingerprint maps and offline accuracy estimation for the task of fingerprint-based indoor localization. Our framework considers collected fingerprints disregarding the physical origin of the data. First, it applies a widely used statistical instrument, namely Gaussian Process Regression (GPR), for interpolation of the fingerprints. Then, to estimate the best possibly achievable localization accuracy at any location, it utilizes the Cramer-Rao Lower Bound (CRLB) with interpolated data as an input. Our demonstration entails a standalone version of the popular and open-source Anyplace Internet-based indoor navigation service in which the software modules of ACCES are integrated. At the conference, we will present the utility of our method in two modes: (i) Collection Mode, where attendees will be able to use our service directly to collect signal measurements over the venue using an Android smartphone; and (ii) Reflection Mode, where attendees will be able to observe the collected measurements and the respective ACCES accuracy estimations in the form of an overlay heatmap.

UR - http://mdmconferences.org/mdm2017/program.html

U2 - 10.1109/MDM.2017.61

DO - 10.1109/MDM.2017.61

M3 - Article in proceeding

T3 - IEEE International Conference on Mobile Data Management (MDM)

SP - 358

EP - 359

BT - 18th IEEE International Conference on Mobile Data Management (MDM)

PB - IEEE

Y2 - 29 May 2017 through 1 June 2017

ER -

ACCES: Offline Accuracy Estimation for Fingerprint-Based Localization

Abstract

Conference

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this