Conditional Random Fields - based approach for real-time building occupancy estimation with multi-sensory networks

Abstract Automated real-time occupancy monitoring in buildings plays an important role in increasing energy efficiency and provides facility managers with useful information about the usage of different spaces. In this paper, a novel approach is proposed for estimating real-time occupancy in buildings, based on Conditional Random Field probabilistic models, utilizing data from different sensor types. Three different types of occupancy information are considered: presence/absence, actual number of occupants and occupancy density. The proposed occupancy estimation method has been applied to four spaces with different characteristics in a real-life testbed environment. Experimental results revealed that the proposed method yielded high accuracy for different sensor combinations in all tested configurations regarding the occupancy granularity and the space type, and outperformed the Hidden Markov Model based method.

[1]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[2]  Mani B. Srivastava,et al.  Inferring occupancy from opportunistically available sensor data , 2014, 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom).

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

[4]  Kamin Whitehouse,et al.  The smart thermostat: using occupancy sensors to save energy in homes , 2010, SenSys '10.

[5]  Kenneth J. Christensen,et al.  Using existing network infrastructure to estimate building occupancy and control plugged-in devices in user workspaces , 2014, Int. J. Commun. Networks Distributed Syst..

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

[7]  Tuan Anh Nguyen,et al.  Energy intelligent buildings based on user activity: A survey , 2013 .

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

[9]  Vivian Loftness,et al.  Behavior Oriented Metrics for Plug Load Energy Savings in Office Environment , 2014 .

[10]  Stan Szpakowicz,et al.  Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation , 2006, Australian Conference on Artificial Intelligence.

[11]  Donatella Sciuto,et al.  Occupancy detection via iBeacon on Android devices for smart building management , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[12]  Burcin Becerik-Gerber,et al.  A systematic approach to occupancy modeling in ambient sensor-rich buildings , 2014, Simul..

[13]  Dimitrios Tzovaras,et al.  Full-automated acquisition system for occupancy and energy measurement data extraction , 2014, ANSS 2014.

[14]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[15]  Tianzhen Hong,et al.  Simulation of occupancy in buildings , 2015 .

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

[17]  Manuela M. Veloso,et al.  Conditional random fields for activity recognition , 2007, AAMAS '07.

[18]  Fernando Pereira,et al.  Shallow Parsing with Conditional Random Fields , 2003, NAACL.

[19]  Ben Kröse,et al.  Conditional Random Fields versus Hidden Markov Models for activity recognition in temporal sensor data , 2008 .

[20]  Neil Brown,et al.  Real-time building occupancy sensing using neural-network based sensor network , 2013, 2013 7th IEEE International Conference on Digital Ecosystems and Technologies (DEST).

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

[22]  Burcin Becerik-Gerber,et al.  Performance-based evaluation of RFID-based indoor location sensing solutions for the built environment , 2011, Adv. Eng. Informatics.

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

[24]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

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

[26]  Jussi Kuutti,et al.  Real time building zone occupancy detection and activity visualization utilizing a visitor counting sensor network , 2014, 2014 11th International Conference on Remote Engineering and Virtual Instrumentation (REV).

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

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

[29]  Oliver Amft,et al.  A Distributed PIR-based Approach for Estimating People Count in Office Environments , 2012, 2012 IEEE 15th International Conference on Computational Science and Engineering.

[30]  Trevor Darrell,et al.  Hidden Conditional Random Fields for Gesture Recognition , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[31]  Neil Brown,et al.  A design model for building occupancy detection using sensor fusion , 2012, 2012 6th IEEE International Conference on Digital Ecosystems and Technologies (DEST).

[32]  Lynne E. Parker,et al.  Using on-line Conditional Random Fields to determine human intent for peer-to-peer human robot teaming , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[33]  Dipanjan Chakraborty,et al.  Occupancy detection in commercial buildings using opportunistic context sources , 2012, 2012 IEEE International Conference on Pervasive Computing and Communications Workshops.

[34]  Dimitrios Tzovaras,et al.  A robust and real-time multi-space occupancy extraction system exploiting privacy-preserving sensors , 2014, 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP).

[35]  P. Smyth,et al.  Modeling Count Data from Multiple Sensors: A Building Occupancy Model , 2007, 2007 2nd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing.