<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zhe Wang</style></author><author><style face="normal" font="default" size="100%">Tianzhen Hong</style></author><author><style face="normal" font="default" size="100%">Mary Ann Piette</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Data fusion in predicting internal heat gains for office buildings through a deep learning approach</style></title><secondary-title><style face="normal" font="default" size="100%">Applied Energy</style></secondary-title><short-title><style face="normal" font="default" size="100%">Applied Energy</style></short-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">data fusion</style></keyword><keyword><style  face="normal" font="default" size="100%">deep learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Internal heat gains</style></keyword><keyword><style  face="normal" font="default" size="100%">Miscellaneous electric loads</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupant count</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive control</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">02/2019</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://linkinghub.elsevier.com/retrieve/pii/S0306261919303630</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">240</style></volume><pages><style face="normal" font="default" size="100%">386 - 398</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Heating, Ventilation, and Air Conditioning (HVAC) is a major energy consumer in buildings. The predictive control has demonstrated a potential to reduce HVAC energy use. To facilitate predictive HVAC control, internal heat gains prediction is required. In this study, we applied Long Short-Term Memory Networks, a special form of deep neural network, to predict miscellaneous electric loads, lighting loads, occupant counts and internal heat gains in two United States office buildings. Compared with the predetermined schedules used in American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) standard 90.1, the Long Short-Term Memory Networks method could reduce the prediction errors of internal heat gains from 12% to 8% in Building A, and from 26% to 16% in Building B. It was also found that for internal heat gains prediction, miscellaneous electric loads is a more important feature than occupant counts for two reasons. First, miscellaneous electric loads is the best proxy variable for internal heat gains, as it is the major component of and has the highest correlation coefficient with the internal heat gains. Second, miscellaneous electric loads contain valuable information to predict occupant count, while occupant count could not help improve miscellaneous electric loads prediction. These findings could help researchers and practitioners select the most relevant features to more accurately predict internal heat gains for the implementation of predictive HVAC control in buildings.&lt;/p&gt;</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zhe Wang</style></author><author><style face="normal" font="default" size="100%">Tianzhen Hong</style></author><author><style face="normal" font="default" size="100%">Mary Ann Piette</style></author><author><style face="normal" font="default" size="100%">Marco Pritoni</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Inferring occupant counts from Wi-Fi data in buildings through machine learning</style></title><secondary-title><style face="normal" font="default" size="100%">Building and Environment</style></secondary-title><short-title><style face="normal" font="default" size="100%">Building and Environment</style></short-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Building control</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupancy estimation</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupant count</style></keyword><keyword><style  face="normal" font="default" size="100%">Random forest</style></keyword><keyword><style  face="normal" font="default" size="100%">Wi-Fi data</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">05/2019</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://linkinghub.elsevier.com/retrieve/pii/S0360132319303336</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">158</style></volume><pages><style face="normal" font="default" size="100%">281 - 294</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;An important approach to curtail building energy consumption is to optimize building control based on occupancy information. Various studies proposed to estimate occupant counts through different approaches and sensors. However, high cost and privacy concerns remain as major barriers, restricting the practice of occupant count detection. In this study, we propose a novel method utilizing data from widely deployed Wi-Fi infrastructure to infer occupant counts through machine learning. Compared with the current indirect measurement methods, our method improves the performance of estimating people count: (1) we avoid privacy concerns by anonymizing and reshuffling the MAC addresses on a daily basis; (2) we adopted a heuristic feature engineer approach to cluster connected devices into different types based on their daily connection duration. We tested the method in an office building located in California. In an area with an average occupancy of 22–27 people and a peak occupancy of 48–74 people, the root square mean error on the test set is less than four people. The error is within two people counts for more than 70% of estimations, and less than six counts for more than 90% of estimations, indicating a relatively high accuracy. The major contribution of this study is proposing a novel and accurate approach to detect occupant counts in a non-intrusive way, i.e., utilizing existing Wi-Fi infrastructure in buildings without requiring the installation of extra hardware or sensors. The method we proposed is generic and could be applied to other commercial buildings to infer occupant counts for energy efficient building control.&lt;/p&gt;</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zhe Wang</style></author><author><style face="normal" font="default" size="100%">Tianzhen Hong</style></author><author><style face="normal" font="default" size="100%">Mary Ann Piette</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Predicting plug loads with occupant count data through a deep learning approach</style></title><secondary-title><style face="normal" font="default" size="100%">Energy</style></secondary-title><short-title><style face="normal" font="default" size="100%">Energy</style></short-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">deep learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Long short term memory network</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupant count</style></keyword><keyword><style  face="normal" font="default" size="100%">Plug loads</style></keyword><keyword><style  face="normal" font="default" size="100%">prediction</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive control</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">05/2019</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://linkinghub.elsevier.com/retrieve/pii/S0360544219310205</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">181</style></volume><pages><style face="normal" font="default" size="100%">29 - 42</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Predictive control has gained increasing attention for its ability to reduce energy consumption and improve occupant comfort in buildings. The plug loads prediction is a key component for the predictive building controls, as plug loads is a major source of internal heat gains in buildings. This study proposed a novel method to apply the Long-Short-Term-Memory (LSTM) Network, a special form of Recurrent Neural Network, to predict plug loads. The occupant count and the time have been confirmed to drive the plug load profile and thus selected as the features for the plug load prediction. The LSTM network was trained and tested with ground truth occupant count data collected from a real office building in Berkeley, California. Results from the LSTM network markedly improve the prediction accuracy compared with traditional linear regression methods and the classical Artificial Neural Network. 95% of 1-h predictions from LSTM network are within ±1 kW of the actual plug loads, given the average plug loads during the office hour is 8.6 kW. The CV(RMSE) of the predicted plug load is 11% for the next hour, and 20% for the next 8 h. Lastly, we compared four prediction approaches with the office building we monitored: LSTM vs. ARIMA, with occupant counts vs. without occupant counts. It was found, the prediction error of the LSTM approach is around 4% less than the ARIMA approach. Using occupant counts as an exogenous input could further reduce the prediction error by 5%–6%. The findings of this paper could shed light on the plug load prediction for building control optimizations such as model-predictive control.&lt;/p&gt;</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zhe Wang</style></author><author><style face="normal" font="default" size="100%">Thomas Parkinson</style></author><author><style face="normal" font="default" size="100%">Peixian Li</style></author><author><style face="normal" font="default" size="100%">Borong Lin</style></author><author><style face="normal" font="default" size="100%">Tianzhen Hong</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes</style></title><secondary-title><style face="normal" font="default" size="100%">Building and Environment</style></secondary-title><short-title><style face="normal" font="default" size="100%">Building and Environment</style></short-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">anomaly detection</style></keyword><keyword><style  face="normal" font="default" size="100%">ASHRAE global thermal comfort database</style></keyword><keyword><style  face="normal" font="default" size="100%">K-nearest neighbors</style></keyword><keyword><style  face="normal" font="default" size="100%">Multivariate Gaussian</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupancy responsive controls</style></keyword><keyword><style  face="normal" font="default" size="100%">Subjective votes</style></keyword><keyword><style  face="normal" font="default" size="100%">thermal comfort</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">03/2019</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://linkinghub.elsevier.com/retrieve/pii/S0360132319300861</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">151</style></volume><pages><style face="normal" font="default" size="100%">219 - 227</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Anomalous patterns in subjective votes can bias thermal comfort models built using data-driven approaches. A stochastic-based two-step framework to detect outliers in subjective thermal comfort data is proposed to address this problem. The anomaly detection technique involves defining similar conditions using a k-Nearest Neighbor (KNN) method and then quantifying the dissimilarity of the occupants&#039; votes from their peers under similar thermal conditions through a Multivariate Gaussian approach. This framework is used to detect outliers in the ASHRAE Global Thermal Comfort Database I &amp;amp; II. The resulting anomaly-free dataset produced more robust comfort models avoiding dubious predictions. The proposed method has been proven to effectively distinguish outliers from inter-individual variabilities in thermal demand. The proposed anomaly detection framework could easily be applied to other applications with different variables or subjective metrics. Such a tool holds great promise for use in the development of occupancy responsive controls for automated building HVAC systems.&lt;/p&gt;</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zhe Wang</style></author><author><style face="normal" font="default" size="100%">Tianzhen Hong</style></author><author><style face="normal" font="default" size="100%">Ruoxi Jia</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Buildings.Occupants: a Modelica package for modelling occupant behaviour in buildings</style></title><secondary-title><style face="normal" font="default" size="100%">Journal of Building Performance Simulation</style></secondary-title><short-title><style face="normal" font="default" size="100%">Journal of Building Performance Simulation</style></short-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">modelica</style></keyword><keyword><style  face="normal" font="default" size="100%">Modelica Buildings Library</style></keyword><keyword><style  face="normal" font="default" size="100%">Modelica Occupants Package</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupant Behaviour</style></keyword><keyword><style  face="normal" font="default" size="100%">Occupant behaviour modelling</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year><pub-dates><date><style  face="normal" font="default" size="100%">11/2018</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://www.tandfonline.com/doi/full/10.1080/19401493.2018.1543352https://www.tandfonline.com/doi/pdf/10.1080/19401493.2018.1543352</style></url></web-urls></urls><pages><style face="normal" font="default" size="100%">1 - 12</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Energy-related occupant behaviour is crucial to design and operation of energy and control systems in buildings. Occupant behaviours are often oversimplified as static schedules or settings in building performance simulation ignoring their stochastic nature. The continuous and dynamic interaction between occupants and building systems motivates their simultaneous simulation in an efficient manner. In the past, simultaneous simulation has relied on co-simulation approaches or customized source code changes to building simulation programmes. This paper presents Buildings. Occupants, an open-source package implemented in Modelica, for the simulation of occupant behaviours of lighting, windows, blinds, heating and air conditioning systems in office and residential buildings. Examples were presented to illustrate how the models in the Occupants package are capable to simulate stochastic occupant behaviours. The major contribution of this work is to introduce the equation-based modelling approach to simulate occupant behaviours in buildings and to develop an open-source Occupants package in the Modelica language&lt;/p&gt;</style></abstract></record></records></xml>