Light Sensor Based Occupancy Estimation via Bayes Filter With Neural Networks

Building occupancy estimation holds great promise for building control systems to save energy and provide a comfortable indoor environment. Existing solutions turn out to be lacking in practice due to their specific hardware requirements and/or poor performances. Recently, an light-emitting diode (LED) light sensor based occupancy estimation system, which is nonintrusive and does not require any additional hardware, has been proposed. However, the performance of the system is limited, especially in a complicated dynamic scenario. In this article, a Bayes filter with neural networks is proposed for the optimal estimation of occupancy based on light sensor data. Specifically, based on the formulation of Bayes filter, the posterior probability of the building occupancy can be decoupled into three components: The prior, likelihood, and evidence. The prior and likelihood are, respectively, estimated from a Markov model and an efficient single-hidden layer feedforward neural network (SLFN). Finally, the evidence can be obtained by the results of prior and likelihood. Real experiments have been conducted to verify the effectiveness of the proposed approach in two complicated scenarios, i.e., dynamic and regular. Results indicate that the proposed Bayes filter outperforms all the benchmark approaches. The impacts of the number of LED sensing units and the number of hidden layers for neural networks are also evaluated. The results manifest that the number of sensing units should be chosen based on the required performance and the SLFN is sufficient for this application.

[1]  Alberto E. Cerpa,et al.  POEM: Power-efficient occupancy-based energy management system , 2013, 2013 ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[2]  L. H. Koh,et al.  An energy-efficient low voltage DC grid powered smart LED lighting system , 2011, IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society.

[3]  Rachel Cardell-Oliver,et al.  Occupancy Estimation Using a Low-Pixel Count Thermal Imager , 2016, IEEE Sensors Journal.

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

[5]  Pascal Fua,et al.  Multicamera People Tracking with a Probabilistic Occupancy Map , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  W Wim Zeiler,et al.  Occupancy measurement in commercial office buildings for demand-driven control applications : a survey and detection system evaluation , 2015 .

[7]  Jun Luo,et al.  Counting via LED sensing: Inferring occupancy using lighting infrastructure , 2018, Pervasive Mob. Comput..

[8]  Cuntai Guan,et al.  Bayesian Learning for Spatial Filtering in an EEG-Based Brain–Computer Interface , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Saandeep Depatla,et al.  Occupancy Estimation Using Only WiFi Power Measurements , 2015, IEEE Journal on Selected Areas in Communications.

[10]  Hua Li,et al.  Sensor Placement by Maximal Projection on Minimum Eigenspace for Linear Inverse Problems , 2015, IEEE Transactions on Signal Processing.

[11]  Han Zou,et al.  FreeCount: Device-Free Crowd Counting with Commodity WiFi , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[12]  Yeng Chai Soh,et al.  Building Occupancy Estimation with Environmental Sensors via CDBLSTM , 2017, IEEE Transactions on Industrial Electronics.

[13]  Luis M. Candanedo,et al.  Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models , 2016 .

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

[15]  Lihua Xie,et al.  Building occupancy estimation and detection: A review , 2018, Energy and Buildings.

[16]  Zhenghua Chen,et al.  Modeling regular occupancy in commercial buildings using stochastic models , 2015 .

[17]  Stefan Schmid,et al.  LED-to-LED visible light communication networks , 2013, MobiHoc '13.

[18]  Jun Luo,et al.  CeilingSee: Device-free occupancy inference through lighting infrastructure based LED sensing , 2017, 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[19]  Dimitrios Tzovaras,et al.  Conditional Random Fields - based approach for real-time building occupancy estimation with multi-sensory networks , 2016 .

[20]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[21]  Hua Li,et al.  Indoor occupancy estimation from carbon dioxide concentration , 2016, ArXiv.

[22]  Pengcheng Liu,et al.  Occupancy Inference Using Pyroelectric Infrared Sensors Through Hidden Markov Models , 2016, IEEE Sensors Journal.

[23]  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.

[24]  Hao Jiang,et al.  Non-intrusive occupancy sensing in commercial buildings , 2017 .

[25]  Darren Leigh,et al.  Very Low-Cost Sensing and Communication Using Bidirectional LEDs , 2003, UbiComp.

[26]  Nan Li,et al.  Measuring and monitoring occupancy with an RFID based system for demand-driven HVAC operations , 2012 .

[27]  Zhenghua Chen,et al.  A fusion framework for occupancy estimation in office buildings based on environmental sensor data , 2016 .

[28]  Masahiro Yoshida,et al.  Indoor Occupancy Estimation via Location-Aware HMM: An IoT Approach , 2018, 2018 IEEE 19th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).

[29]  Qianchuan Zhao,et al.  Occupancy detection in the office by analyzing surveillance videos and its application to building energy conservation , 2017 .

[30]  Zhenghua Chen,et al.  Occupancy estimation with environmental sensing via non-iterative LRF feature learning in time and frequency domains , 2017 .

[31]  Kevin Weekly,et al.  Occupancy Detection via Environmental Sensing , 2018, IEEE Transactions on Automation Science and Engineering.

[32]  Dieter Fox,et al.  Bayesian Filtering for Location Estimation , 2003, IEEE Pervasive Comput..

[33]  Yeng Chai Soh,et al.  Real-time occupancy estimation using environmental parameters , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[34]  Alessandro A. Nacci,et al.  BlueSentinel: a first approach using iBeacon for an energy efficient occupancy detection system , 2014, BuildSys@SenSys.

[35]  Yeng Chai Soh,et al.  Environmental Sensors-Based Occupancy Estimation in Buildings via IHMM-MLR , 2017, IEEE Transactions on Industrial Informatics.

[36]  Ponnuthurai N. Suganthan,et al.  Ensemble Classification and Regression-Recent Developments, Applications and Future Directions [Review Article] , 2016, IEEE Computational Intelligence Magazine.

[37]  Stéphane Ploix,et al.  Estimating Occupancy In Heterogeneous Sensor Environment , 2016 .

[38]  Changjian Chen,et al.  An Interactive Method to Improve Crowdsourced Annotations , 2019, IEEE Transactions on Visualization and Computer Graphics.

[39]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[40]  Jun Luo,et al.  Visible Light Based Occupancy Inference Using Ensemble Learning , 2018, IEEE Access.

[41]  A. Florita,et al.  Occupancy sensing in buildings: A review of data analytics approaches , 2019, Energy and Buildings.

[42]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[43]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[44]  Rajesh Gupta,et al.  Sentinel: occupancy based HVAC actuation using existing WiFi infrastructure within commercial buildings , 2013, SenSys '13.