Journal Home > Volume 5 , Issue 2
Building Simulation 2012, 5(2): 179-188 https://doi.org/10.1007/s12273-012-0075-6
Research Article | Issue | Published: 09 May 2012

Information-theoretic environment features selection for occupancy detection in open office spaces

Show Author's Information Rui Zhang1( ),  Khee Poh Lam2,  Yun-Shang Chiou3,  Bing Dong4
IBM, T.J. Watson Research Center, Yorktown Heights, NY 10598, USA
Center for Building Performance and Diagnostics, School of Architecture, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Department of Architecture, National Taiwan University of Science and Technologies, Taipei, 106 Taiwan, China
United Technologies Research Center, East Hartford, CT 06108, USA
Keywords:
feature selection, occupancy detection, environmental sensor network, information theory
Cite this article:
Zhang R, Lam KP, Chiou Y-S, et al. Information-theoretic environment features selection for occupancy detection in open office spaces. Building Simulation, 2012, 5(2): 179-188. https://doi.org/10.1007/s12273-012-0075-6
Download citation
EndNote(RIS)
BibTeX

386

Views

10

Downloads

Citations

36

Crossref

N/A

WoS

43

Scopus

0

CSCD

Abstract Full text About this article

Knowing the presence or the actual number of occupants in a space at any given time is essential for the effective management of various building operation functions such as security and environmental control (e.g., lighting, HVAC). As occupants "interact" with the indoor environment, they will affect environmental conditions through the emission of CO2, heat and sound, and relatively little effort has been reported in the literature on utilizing this environmental sensing data for occupancy detection. This paper presents the findings of a study to address this question by exploring the most effective environmental features for occupancy level detection. A sensor network with robust, non-intrusive sensors such as CO2, temperature, relative humidity, and acoustics is deployed in an open-plan office space. Using information theory, the physical correlation between the number of occupants and various combination of features extracted from sensor data has been studied. The results show significant correlation between features extracted from humidity, acoustics, and CO2, while little correlation with temperature data. Using features from multiple sensors increases correlation further, and nearly 90% information gain is acquired when nine of the most informative features are combined.


menu
Abstract
Full text
Outline
About this article

Information-theoretic environment features selection for occupancy detection in open office spaces

Show Author's information Rui Zhang1( ), Khee Poh Lam2, Yun-Shang Chiou3, Bing Dong4
IBM, T.J. Watson Research Center, Yorktown Heights, NY 10598, USA
Center for Building Performance and Diagnostics, School of Architecture, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Department of Architecture, National Taiwan University of Science and Technologies, Taipei, 106 Taiwan, China
United Technologies Research Center, East Hartford, CT 06108, USA

Abstract

Knowing the presence or the actual number of occupants in a space at any given time is essential for the effective management of various building operation functions such as security and environmental control (e.g., lighting, HVAC). As occupants "interact" with the indoor environment, they will affect environmental conditions through the emission of CO2, heat and sound, and relatively little effort has been reported in the literature on utilizing this environmental sensing data for occupancy detection. This paper presents the findings of a study to address this question by exploring the most effective environmental features for occupancy level detection. A sensor network with robust, non-intrusive sensors such as CO2, temperature, relative humidity, and acoustics is deployed in an open-plan office space. Using information theory, the physical correlation between the number of occupants and various combination of features extracted from sensor data has been studied. The results show significant correlation between features extracted from humidity, acoustics, and CO2, while little correlation with temperature data. Using features from multiple sensors increases correlation further, and nearly 90% information gain is acquired when nine of the most informative features are combined.

Keywords: feature selection, occupancy detection, environmental sensor network, information theory

References(22)

B Anderson, A Moore (1998). ADtrees for fast counting and for fast learning of association rules. In: Proceedings of the 4th Inter-national Conference on Knowledge Discovery and Data Mining (pp. 134-138), New York, USA.
P Bauer, M Sichitiu, R Istepanian, K Premaratne (2000). The mobile patient: Wireless distributed sensor networks for patient monitoring and care. In: Proceeding of the IEEE Conference on Information Technology Applications in Biomedicine (pp. 17-21), Arlington, USA.
AD Brona, A Damato (2007). Information entropy of a En: Bernoulli trial X. http://upload.wikimedia.org/wikipedia/commons/2/22/Binary_entropy_plot.svg. Accessed 30 Jan. 2012.
KP Burnham, DR Anderson (1998). Model Selection and Inference: A Practical Information Theoretic Approach. New York: Springer.
DOI
DJ Cook, M Youngblood, EO Heierman III, K Gopalratnam, A Rao, A Litvin, F Khawaja (2003). MavHome: An agent-based smart home. In: Proceedings of the IEEE International Conference on Pervasive Computing and Communications (pp. 521-524), Los Alamitos, USA.
RH Dodier, GP Henze, DK Tiller, X Guo (2006). Building occupancy detection through sensor belief networks. Energy and Buildings, 38: 1033-1043.
DOI Google Scholar
CC Federspiel (1997). Estimating the inputs of gas transport processes in buildings. IEEE Transactions on Control Systems Technology, 5: 480-489.
DOI Google Scholar
A Harter, A Hopper (1994). A distributed location system for the active office. IEEE Network, 8: 62-70.
DOI Google Scholar
B Karp, HT Kung (2000). Greedy perimeter stateless routing for wireless networks. In: Proceedings of the 6th Annual ACM/IEEE International Conference on Mobile Computing and Networking (pp. 243-254), Boston, MA.
S Kumar, A Cengiz, E Deborah (2000). Scalable object-tracking through unattended techniques (SCOUT). In: Proceedings of the 8th International Conference on Network Protocols (ICNP) (pp. 253-262), Osaka, Japan.
CD Laird, LT Biegler, BG van Bloemen Waanders (2007). Real-time, large scale optimization of water network systems using a subdomain approach. In: LT Biegler, O Ghattas, M Heinkenschloss, D Keyes, BG van Bloemen Waanders (eds), Real-Time PDE-Constrained Optimization (pp. 291-308), Philadelphia, USA: SIAM.
DOI Google Scholar
KP Lam, M Höynck, R Zhang, R Andrews, RS Chiou, B Dong (2009). Information-theoretic environmental features selection for occupancy detection in open offices. In: Proceedings of IBPSA Conference 2009 (pp. 1460-1467), Glasgow, UK.
V Lesser, M Atighetchi, A Raja, B Regis,T Wagner, P Xuan, SX Zhang (1999). The intelligent home testbed. In: Proceedings of the Autonomy Control Software Workshop (pp. 40-47), Seattle, USA.
TM Mitchell (1997). Machine Learning. New York: WCB/McGraw-Hill.
A Moore, MS Lee (1998). Cached sufficient statistics for efficient machine learning with large datasets. Journal of Artificial Intelligence Research, 8: 67-91.
DOI Google Scholar
M Mozer (1998). The neural network house: An environment that adapts to its inhabitants. In: Proceedings of AAAI Spring Symposium on Intelligent Environments (pp. 110-114), Stanford, USA.
J Page, D Robinson, N Morel, J-L Scartezzini (2008). A generalised stochastic model for the simulation of occupant presence. Energy and Buildings, 40: 83-98.
DOI Google Scholar
CE Shannon (1948). A mathematical theory of communication. Bell System Technical Journal, 27: 379-423.
DOI Google Scholar
MD Sohn, P Reynolds, AJ Gadgil, RG Sextro (2002). Rapidly locating sources and predicting contaminant dispersion in buildings. In: Proceedings of the 9th International Conference on Indoor Air Quality and Climate (pp. 17-21), Monterey, USA.
MC Torrance (1995). Advances in human-computer interaction: The intelligent room. In: Working Notes of the CHI 95 Research Symposium, Denver, USA.
D Wang, CC Federspiel, F Rubinstein (2005). Modeling occupancy in single person offices. Energy and Buildings, 37: 121-126.
DOI Google Scholar
S Wang, J Burnett, H Chong (1999). Experimental validation of CO2-based occupancy detection for demand-controlled ventilation. Indoor and Built Environment, 8: 377-391.
DOI Google Scholar
Publication history
Copyright
Acknowledgements

Publication history

Received: 08 August 2011
Revised: 10 February 2012
Accepted: 27 February 2012
Published: 09 May 2012
Issue date: June 2012

Copyright

© Tsinghua University Press and Springer-Verlag Berlin Heidelberg 2012

Acknowledgements

This work is supported in part by the Bosch Research and Technology Center, Pittsburgh, PA. The authors would also express sincere gratitude to Andrews Burton from Bosch Research and Technology Center for his comments and revision support on the paper.

Return