Skip to main content

Research Repository

Advanced Search

Unsupervised labelling of sequential data for location identification in indoor environments

Pérez López, Iker; Pinchin, James; Brown, Michael; Blum, Jesse; Sharples, Sarah

Authors

Iker Pérez López iker.perez@nottingham.ac.uk

Michael Brown michael.brown@nottingham.ac.uk

Jesse Blum jesse.blum@nottingham.ac.uk



Abstract

In this paper we present indoor positioning within unknown environments as an unsupervised labelling task on sequential data. We explore a probabilistic framework relying on wireless network radio signals and contextual information, which is increasingly available in large environments. Thus, we form an informative spatial classifier without resorting to a pre-determined map, and show the potential of the approach using both simulated and real data sets. Results demonstrate the ability of the procedure to segregate structures of radio signal observations and form clustered regions in association to areas of interest to the user; thus, we show it is possible to differentiate location between closely spaced zones of variable size and shape.

Citation

Pérez López, I., Pinchin, J., Brown, M., Blum, J., & Sharples, S. (in press). Unsupervised labelling of sequential data for location identification in indoor environments. Expert Systems with Applications, https://doi.org/10.1016/j.eswa.2016.06.003

Journal Article Type Article
Acceptance Date Jun 2, 2016
Online Publication Date Jun 3, 2016
Deposit Date Jun 6, 2016
Publicly Available Date Jun 6, 2016
Journal Expert Systems with Applications
Print ISSN 0957-4174
Electronic ISSN 0957-4174
Publisher Elsevier
Peer Reviewed Peer Reviewed
DOI https://doi.org/10.1016/j.eswa.2016.06.003
Keywords Unsupervised Labelling; Sequential Data; Indoor Positioning; Ubiquitous Computing; Graphical Models
Public URL http://eprints.nottingham.ac.uk/id/eprint/33787
Publisher URL http://www.sciencedirect.com/science/article/pii/S0957417416302846
Copyright Statement Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf

Files


DraftPositioning labelling.pdf (1 Mb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf





You might also like



Downloadable Citations