High accuracy context recovery using clustering mechanisms

This paper examines the recovery of user context in indoor environmnents with existing wireless infrastructures to enable assistive systems. We present a novel approach to the extraction of user context, casting the problem of context recovery as an unsupervised, clustering problem. A well known den...

Full description

Bibliographic Details
Main Authors: Phung, Dinh, Adams, Brett, Tran, Kha, Venkatesh, Svetha, Kumar, Mohan
Other Authors: Unknown
Format: Conference Paper
Published: IEEE Computer Society 2009
Online Access:http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4912760
http://hdl.handle.net/20.500.11937/32269
_version_ 1848753614361722880
author Phung, Dinh
Adams, Brett
Tran, Kha
Venkatesh, Svetha
Kumar, Mohan
author2 Unknown
author_facet Unknown
Phung, Dinh
Adams, Brett
Tran, Kha
Venkatesh, Svetha
Kumar, Mohan
author_sort Phung, Dinh
building Curtin Institutional Repository
collection Online Access
description This paper examines the recovery of user context in indoor environmnents with existing wireless infrastructures to enable assistive systems. We present a novel approach to the extraction of user context, casting the problem of context recovery as an unsupervised, clustering problem. A well known density-based clustering technique, DBSCAN, is adapted to recover user context that includes user motion state, and significant places the user visits from WiFi observations consisting of access point id and signal strength. Furthermore, user rhythms or sequences of places the user visits periodically are derived from the above low level contexts by employing a state-of-the-art probabilistic clustering technique, the Latent Dirichlet Allocation (LDA), to enable a variety of application services. Experimental results with real data are presented to validate the proposed unsupervised learning approach and demonstrate its applicability.
first_indexed 2025-11-14T08:27:19Z
format Conference Paper
id curtin-20.500.11937-32269
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:27:19Z
publishDate 2009
publisher IEEE Computer Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-322692017-10-02T02:27:47Z High accuracy context recovery using clustering mechanisms Phung, Dinh Adams, Brett Tran, Kha Venkatesh, Svetha Kumar, Mohan Unknown This paper examines the recovery of user context in indoor environmnents with existing wireless infrastructures to enable assistive systems. We present a novel approach to the extraction of user context, casting the problem of context recovery as an unsupervised, clustering problem. A well known density-based clustering technique, DBSCAN, is adapted to recover user context that includes user motion state, and significant places the user visits from WiFi observations consisting of access point id and signal strength. Furthermore, user rhythms or sequences of places the user visits periodically are derived from the above low level contexts by employing a state-of-the-art probabilistic clustering technique, the Latent Dirichlet Allocation (LDA), to enable a variety of application services. Experimental results with real data are presented to validate the proposed unsupervised learning approach and demonstrate its applicability. 2009 Conference Paper http://hdl.handle.net/20.500.11937/32269 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4912760 IEEE Computer Society fulltext
spellingShingle Phung, Dinh
Adams, Brett
Tran, Kha
Venkatesh, Svetha
Kumar, Mohan
High accuracy context recovery using clustering mechanisms
title High accuracy context recovery using clustering mechanisms
title_full High accuracy context recovery using clustering mechanisms
title_fullStr High accuracy context recovery using clustering mechanisms
title_full_unstemmed High accuracy context recovery using clustering mechanisms
title_short High accuracy context recovery using clustering mechanisms
title_sort high accuracy context recovery using clustering mechanisms
url http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4912760
http://hdl.handle.net/20.500.11937/32269