[Back]

F. Tahmasebi, A. Mahdavi:
"Exploring the predictive Potential of probabilistic occupancy models";
Talk: BauSim2014 - Human-centred building(s), Aachen, Deutschland; 2014-09-22 - 2014-09-24; in: "BauSim2014 - Gabäude für Menschen", C. van Treeck, D. Müller (ed.); Eigenauflage mit wissenschaftlichem Lektorat, (2014), ISBN: 978-3-00-047160-5; 5 pages.

Building performance is influenced by occupants'
presence and actions. Knowledge of occupants' future
presence and behavior in buildings is of central
importance to the implementation efforts concerning
predictive building systems control strategies.
Specifically, prediction of occupants' presence in
buildings represents a necessary condition for
predicting their interactions with building systems. In
the present contribution, we focus on evaluation of
probabilistic occupancy models to explore the
potential of using past monitored data in predicting
future presence of occupants. Toward this end, we
selected a university campus office area, which is
equipped with a monitoring infrastructure and
includes a number of open and closed offices. For the
purpose of this study, we used monitored occupancy
data and two previously developed stochastic
occupancy models to predict the occupancy profiles
on a daily basis. The predictions were then evaluated
via comparison with monitored daily occupancy
profiles. To conduct the model evaluation in a
rigorous manner, a number of specific evaluation
statistics were deployed. Thus, the results facilitate a
discussion of the potential and limitations of
predicting building occupants' future presence
patterns based on past monitoring data.

none - see english version