Estimating Occupancy In Heterogeneous Sensor Environment

Abstract A general approach is proposed to determine the common sensors that shall be used to estimate and classify the approximate number of people (within a range) in a room. The range is dynamic and depends on the maximum occupancy met in a training data set for instance. Means to estimate occupancy include motion detection, power consumption, CO2 concentration sensors, microphone or door/window positions. The proposed approach is inspired by machine learning. It starts by determining the most useful measurements in calculating information gains. Then, estimation algorithms are proposed: they rely on decision tree learning algorithms because these yield decision rules readable by humans, which correspond to nested if-then-else rules, where thresholds can be adjusted depending on the living areas considered. In addition, the decision tree depth is limited in order to simplify the analysis of the tree rules. Finally, an economic analysis is carried out to evaluate the cost and the most relevant sensor sets, with cost and accuracy comparison for the estimation of occupancy. C45 and random forest algorithms have been applied to an office setting, with average estimation error of 0.19–0.18. Over-fitting issues and best sensor sets are discussed.

[1]  Silvia Santini,et al.  Occupancy Detection from Electricity Consumption Data , 2013, BuildSys@SenSys.

[2]  Andrzej Banaszuk,et al.  Model-based Real-Time Estimation of Building Occupancy During Emergency Egress , 2010 .

[3]  Chenda Liao,et al.  An integrated approach to occupancy modeling and estimation in commercial buildings , 2010, Proceedings of the 2010 American Control Conference.

[4]  Tianzhen Hong,et al.  Advances in research and applications of energy-related occupant behavior in buildings ☆ , 2016 .

[5]  Jie Zhao,et al.  Occupant behavior and schedule modeling for building energy simulation through office appliance power consumption data mining , 2014 .

[6]  Oliver Amft,et al.  Recognizing Energy-related Activities Using Sensors Commonly Installed in Office Buildings , 2013, ANT/SEIT.

[7]  Thomas Weng,et al.  Occupancy-driven energy management for smart building automation , 2010, BuildSys '10.

[8]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[9]  Miguel Á. Carreira-Perpiñán,et al.  OBSERVE: Occupancy-based system for efficient reduction of HVAC energy , 2011, Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks.

[10]  Heshmat A. Aglan.  Predictive model for CO2 generation and decay in building envelopes , 2003 .

[11]  Rui Zhang,et al.  Occupancy detection through an extensive environmental sensor network in an open-plan office building , 2009 .

[12]  Karl Henrik Johansson,et al.  A benchmark for data-based office modeling: challenges related to CO$_2$ dynamics , 2015, ArXiv.

[13]  Darren Robinson,et al.  Interactions with window openings by office occupants , 2009 .

[14]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[15]  Darren Robinson,et al.  Stochastic Simulation of Occupant Presence and Behaviour in Buildings , 2007 .

[16]  Sanjoy Paul,et al.  iSense: a wireless sensor network based conference room management system , 2009, BuildSys '09.

[17]  Vice President,et al.  AMERICAN SOCIETY OF HEATING, REFRIGERATION AND AIR CONDITIONING ENGINEERS INC. , 2007 .

[18]  Context-Aware Computing,et al.  Inferring Activities from Interactions with Objects , 2004 .

[19]  Stéphane Ploix,et al.  Simulating Occupants' Behavior for Energy waste Reduction in dwellings: a Multiagent Methodology , 2013, Adv. Complex Syst..

[20]  Oliver Amft,et al.  An opportunistic activity-sensing approach to save energy in office buildings , 2013, e-Energy '13.

[21]  Tianzhen Hong,et al.  Occupancy schedules learning process through a data mining framework , 2015 .

[22]  Rhys Goldstein,et al.  Real-time occupancy detection using decision trees with multiple sensor types , 2011, SpringSim.

[23]  Marco Aiello,et al.  Beyond Indoor Presence Monitoring with Simple Sensors , 2012, PECCS.

[24]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[25]  J. Ichimura,et al.  Cooperative distributed demand control by environmental sensor network - Estimating the number of people by CO2 concentration - , 2008, 2008 6th IEEE International Conference on Industrial Informatics.

[26]  R. Fritsch,et al.  Stochastic model of inhabitant behavior in regard to ventilation , 1991 .

[27]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[28]  Eric Horvitz,et al.  Layered representations for learning and inferring office activity from multiple sensory channels , 2004, Comput. Vis. Image Underst..

[29]  Rui Zhang,et al.  An information technology enabled sustainability test-bed (ITEST) for occupancy detection through an environmental sensing network , 2010 .

[30]  H. Nishi,et al.  Estimation of the number of people under controlled ventilation using a CO2 concentration sensor , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[31]  Karl Henrik Johansson,et al.  Estimation of building occupancy levels through environmental signals deconvolution , 2013, BuildSys@SenSys.