A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations

E Furey, K Curran, P McKevitt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The arrival of new devices and techniques has brought tracking out of the investigation stage and into the wider world. Using Wi-Fi signals is an attractive and reasonably affordable option to deal with the currently unsolved problem of widespread tracking in an indoor environment. Here we present a system called HABITS (History Aware Based Indoor Tracking System) which aims at overcoming weaknesses in existing Real Time Location Systems (RTLS) by using approach of making educated guesses about future locations of humans. The primary research question that is foremost is whether the tracking capabilities of existing RTLS can be improved automatically by knowledge of previous movement especially in the short term in the case of emergency first responders by the application of a combination of artificial intelligence approaches, a key contributor being Bayesian filters. We conclude that HABITS improves on the standard Ekahau RTLS in term of accuracy (overcoming black spots), latency (giving position fixes when Ekahau cannot), cost (less APs are required than are recommended by Ekahau) and prediction (short term predictions are available from HABITS). These are features that no other indoor tracking system currently provides and could provide crucial in future emergency first responder incidents.
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsF Xhafa, L Barolli, M Koppen
Place of PublicationTokyo, Japan
Pages729-734
Number of pages6
DOIs
Publication statusPublished - Dec 2011
EventThird IEEE International Conference on Intelligent Networking and Collaborative Systems (INCoS-2011) - Fukuoka Institute of Technology (FIT), Kyushu, Japan
Duration: 1 Dec 2011 → …

Conference

ConferenceThird IEEE International Conference on Intelligent Networking and Collaborative Systems (INCoS-2011)
Period1/12/11 → …

Fingerprint

Wi-Fi
Artificial intelligence
Costs

Cite this

Furey, E., Curran, K., & McKevitt, P. (2011). A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations. In F. Xhafa, L. Barolli, & M. Koppen (Eds.), Unknown Host Publication (pp. 729-734). Tokyo, Japan. https://doi.org/10.1109/INCoS.2011.14
Furey, E ; Curran, K ; McKevitt, P. / A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations. Unknown Host Publication. editor / F Xhafa ; L Barolli ; M Koppen. Tokyo, Japan, 2011. pp. 729-734
@inproceedings{eabfd9a28d764c0f9198cf2970c0c119,
title = "A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations",
abstract = "The arrival of new devices and techniques has brought tracking out of the investigation stage and into the wider world. Using Wi-Fi signals is an attractive and reasonably affordable option to deal with the currently unsolved problem of widespread tracking in an indoor environment. Here we present a system called HABITS (History Aware Based Indoor Tracking System) which aims at overcoming weaknesses in existing Real Time Location Systems (RTLS) by using approach of making educated guesses about future locations of humans. The primary research question that is foremost is whether the tracking capabilities of existing RTLS can be improved automatically by knowledge of previous movement especially in the short term in the case of emergency first responders by the application of a combination of artificial intelligence approaches, a key contributor being Bayesian filters. We conclude that HABITS improves on the standard Ekahau RTLS in term of accuracy (overcoming black spots), latency (giving position fixes when Ekahau cannot), cost (less APs are required than are recommended by Ekahau) and prediction (short term predictions are available from HABITS). These are features that no other indoor tracking system currently provides and could provide crucial in future emergency first responder incidents.",
author = "E Furey and K Curran and P McKevitt",
year = "2011",
month = "12",
doi = "10.1109/INCoS.2011.14",
language = "English",
isbn = "978-0-7695-4579-0",
pages = "729--734",
editor = "F Xhafa and L Barolli and M Koppen",
booktitle = "Unknown Host Publication",

}

Furey, E, Curran, K & McKevitt, P 2011, A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations. in F Xhafa, L Barolli & M Koppen (eds), Unknown Host Publication. Tokyo, Japan, pp. 729-734, Third IEEE International Conference on Intelligent Networking and Collaborative Systems (INCoS-2011), 1/12/11. https://doi.org/10.1109/INCoS.2011.14

A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations. / Furey, E; Curran, K; McKevitt, P.

Unknown Host Publication. ed. / F Xhafa; L Barolli; M Koppen. Tokyo, Japan, 2011. p. 729-734.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations

AU - Furey, E

AU - Curran, K

AU - McKevitt, P

PY - 2011/12

Y1 - 2011/12

N2 - The arrival of new devices and techniques has brought tracking out of the investigation stage and into the wider world. Using Wi-Fi signals is an attractive and reasonably affordable option to deal with the currently unsolved problem of widespread tracking in an indoor environment. Here we present a system called HABITS (History Aware Based Indoor Tracking System) which aims at overcoming weaknesses in existing Real Time Location Systems (RTLS) by using approach of making educated guesses about future locations of humans. The primary research question that is foremost is whether the tracking capabilities of existing RTLS can be improved automatically by knowledge of previous movement especially in the short term in the case of emergency first responders by the application of a combination of artificial intelligence approaches, a key contributor being Bayesian filters. We conclude that HABITS improves on the standard Ekahau RTLS in term of accuracy (overcoming black spots), latency (giving position fixes when Ekahau cannot), cost (less APs are required than are recommended by Ekahau) and prediction (short term predictions are available from HABITS). These are features that no other indoor tracking system currently provides and could provide crucial in future emergency first responder incidents.

AB - The arrival of new devices and techniques has brought tracking out of the investigation stage and into the wider world. Using Wi-Fi signals is an attractive and reasonably affordable option to deal with the currently unsolved problem of widespread tracking in an indoor environment. Here we present a system called HABITS (History Aware Based Indoor Tracking System) which aims at overcoming weaknesses in existing Real Time Location Systems (RTLS) by using approach of making educated guesses about future locations of humans. The primary research question that is foremost is whether the tracking capabilities of existing RTLS can be improved automatically by knowledge of previous movement especially in the short term in the case of emergency first responders by the application of a combination of artificial intelligence approaches, a key contributor being Bayesian filters. We conclude that HABITS improves on the standard Ekahau RTLS in term of accuracy (overcoming black spots), latency (giving position fixes when Ekahau cannot), cost (less APs are required than are recommended by Ekahau) and prediction (short term predictions are available from HABITS). These are features that no other indoor tracking system currently provides and could provide crucial in future emergency first responder incidents.

U2 - 10.1109/INCoS.2011.14

DO - 10.1109/INCoS.2011.14

M3 - Conference contribution

SN - 978-0-7695-4579-0

SP - 729

EP - 734

BT - Unknown Host Publication

A2 - Xhafa, F

A2 - Barolli, L

A2 - Koppen, M

CY - Tokyo, Japan

ER -

Furey E, Curran K, McKevitt P. A Bayesian filter approach to modelling human movement patterns for first responders within indoor locations. In Xhafa F, Barolli L, Koppen M, editors, Unknown Host Publication. Tokyo, Japan. 2011. p. 729-734 https://doi.org/10.1109/INCoS.2011.14