Title :
Building an occupancy model from sensor networks in office environments
Author :
Castanedo, F. ; Lopez-de-Ipina, D. ; Aghajan, H. ; Kleihorst, R.
Author_Institution :
DeustoTech, Univ. of Deusto, Bilbao, Spain
Abstract :
The work presented here aims to answer this question: Using just binary occupancy sensors is it possible to build a behaviour occupancy model over long-term logged data? Sensor measurements are grouped to form artificial words (activities) and documents (set of activities). The goal is to infer the latent topics which are assumed to be the common routines from the observed data. An unsupervised probabilistic model, namely the Latent Dirichlet Allocation (LDA), is applied to automatically discover the latent topics (routines) in the data. Experimental results using real logged data of 24 weeks from an office building, with different number of topics, are shown. The results show the power of the LDA model in extracting relevant patterns from sensor network data.
Keywords :
document handling; probability; sensors; LDA model; artificial document; artificial word; behaviour occupancy model; binary occupancy sensor measurement; latent Dirichlet allocation; long term logged data; office building; office environment; pattern extraction; real logged data; sensor network data; unsupervised probabilistic model; Buildings; Data models; Document handling; Probabilistic logic; Resource management; Sensors;
Conference_Titel :
Distributed Smart Cameras (ICDSC), 2011 Fifth ACM/IEEE International Conference on
Conference_Location :
Ghent
Print_ISBN :
978-1-4577-1708-6
Electronic_ISBN :
978-1-4577-1706-2
DOI :
10.1109/ICDSC.2011.6042929
