Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks

Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Building and environment Ročník 219; s. 109207
Hlavní autoři:	Zhuang, Chaoqun, Choudhary, Ruchi, Mavrogianni, Anna
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.07.2022 The Authors. Published by Elsevier Ltd
Témata:	Autoencoder Bayesian deep neural network COVID-19 Occupancy prediction Ventilation Occupancy prediction COVID-19 Ventilation Bayesian deep neural network Autoencoder
ISSN:	0360-1323, 1873-684X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization. oDeveloped autoencoder Bayesian deep learning models for probabilistic occupancy forecasting.oTook account of model misspecification, epistemic uncertainty and aleatoric uncertainty.oAchieved 5.8% mean absolute percentage error reduction than the baseline model in the test period.oDeveloped risk-aware decision-making schemes for energy conservation and infection prevention.
AbstractList	Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization. Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization.Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization. Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization. oDeveloped autoencoder Bayesian deep learning models for probabilistic occupancy forecasting.oTook account of model misspecification, epistemic uncertainty and aleatoric uncertainty.oAchieved 5.8% mean absolute percentage error reduction than the baseline model in the test period.oDeveloped risk-aware decision-making schemes for energy conservation and infection prevention.
ArticleNumber	109207
Author	Choudhary, Ruchi Mavrogianni, Anna Zhuang, Chaoqun
Author_xml	– sequence: 1 givenname: Chaoqun orcidid: 0000-0002-4050-3740 surname: Zhuang fullname: Zhuang, Chaoqun email: czhuang@turing.ac.uk, cz378@cam.ac.uk organization: Data-centric Engineering, The Alan Turing Institute, London, United Kingdom – sequence: 2 givenname: Ruchi surname: Choudhary fullname: Choudhary, Ruchi organization: Data-centric Engineering, The Alan Turing Institute, London, United Kingdom – sequence: 3 givenname: Anna orcidid: 0000-0002-5104-1238 surname: Mavrogianni fullname: Mavrogianni, Anna organization: Institute for Environmental Design and Engineering, Bartlett Faculty of the Built Environment, University College London, London, United Kingdom
BookMark	eNqFkU9v1DAQxS3USmxbvgLykUsW_0ucSAgBVWmRKpUDSNwsx57sepu1g-1s2W-Pl20P9NKT7fH8nt7MO0MnPnhA6C0lS0po836z7Gc3WvC7JSOMlWLHiHyFFrSVvGpa8esELQhvSEU546_RWUobUsCOiwX68z2GXvdudCk7g4Mx86S92eMhRDC6FP3qcMfRpftKP-gIOEzZbfWId-CzG3V2weO8jmFerbGecwBvgoWIv-g9JKc9tgAT9jDHAnnIDyHepwt0OugxwZvH8xz9_Hr14_Kmur27_nb5-bYyQrS5aiXU1jDRDJoQ2bWt7Ia6H4YaeD90lgory6vpu9rQnsmWdrYeDDDKhDCEAz9HH4-609xvwZriudhQUywjxL0K2qn_f7xbq1XYqa6uuZCkCLx7FIjh9wwpq61LBsZRewhzUkyyWghey660fji2mhhSijAo4_K__RRlNypK1CExtVFPialDYuqYWMGbZ_iTyxfBT0cQyiJ3DqJKxpUUwLoSYlY2uJck_gK41Ly1
CitedBy_id	crossref_primary_10_1016_j_buildenv_2023_110808 crossref_primary_10_1016_j_buildenv_2023_110807 crossref_primary_10_1016_j_apenergy_2022_120288 crossref_primary_10_1016_j_aei_2025_103654 crossref_primary_10_1016_j_autcon_2024_105894 crossref_primary_10_1109_JSEN_2023_3287565 crossref_primary_10_3390_buildings15050816 crossref_primary_10_1016_j_buildenv_2023_110233 crossref_primary_10_1016_j_buildenv_2023_110375 crossref_primary_10_1016_j_enbuild_2025_115468 crossref_primary_10_5334_bc_497 crossref_primary_10_1016_j_apenergy_2023_120889 crossref_primary_10_1108_DTA_03_2023_0063 crossref_primary_10_1007_s12273_025_1292_0 crossref_primary_10_1016_j_enbuild_2025_115352 crossref_primary_10_1016_j_jobe_2023_107109
Cites_doi	10.1016/S0360-1323(97)00075-9 10.1016/j.enbuild.2021.110860 10.1016/j.enbuild.2017.05.031 10.1016/j.scs.2018.09.031 10.1016/j.buildenv.2018.07.006 10.1016/j.enbuild.2017.04.014 10.1016/j.scs.2021.103256 10.1016/j.energy.2020.118100 10.1016/j.buildenv.2019.01.052 10.1016/j.enbuild.2019.06.043 10.1016/j.enbuild.2021.110883 10.1016/j.scs.2020.102390 10.1109/HPCC-SmartCity-DSS.2017.7 10.1016/j.enbuild.2018.09.002 10.1177/0143624420911810 10.1016/j.enbuild.2018.11.025 10.1016/j.enbuild.2011.12.029 10.3390/sym11080956 10.1016/j.buildenv.2021.107588 10.1109/FIIW.2011.6476826 10.1111/j.1600-0668.2009.00623.x 10.1016/j.enbuild.2021.111345 10.1016/j.apenergy.2014.02.057 10.1080/19401493.2011.577810 10.3390/app112110291 10.1007/978-1-4842-3516-4_2 10.1109/TITS.2011.2165705 10.1016/j.apenergy.2021.118297 10.1007/s00521-020-04926-3 10.1002/we.1798 10.1016/j.enbuild.2016.12.056 10.1016/j.energy.2019.05.138 10.1016/j.buildenv.2015.06.009 10.1016/j.ins.2013.07.030 10.1016/j.enbuild.2014.11.065 10.1177/1420326X9900800605 10.1016/j.buildenv.2017.08.003 10.1093/japr/2.4.314 10.1016/j.enbuild.2021.110826 10.1016/j.apenergy.2019.114451 10.1016/j.apenergy.2017.12.002 10.1177/0011392121990030 10.1007/s12206-021-0140-0 10.1016/j.buildenv.2016.01.026 10.1016/j.scs.2022.103719 10.1016/j.enbuild.2020.109965 10.1016/j.enbuild.2014.11.078
ContentType	Journal Article
Copyright	2022 The Authors 2022 The Authors. 2022 The Authors 2022
Copyright_xml	– notice: 2022 The Authors – notice: 2022 The Authors. – notice: 2022 The Authors 2022
DBID	6I. AAFTH AAYXX CITATION 7X8 5PM
DOI	10.1016/j.buildenv.2022.109207
DatabaseName	ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic
Database_xml	– sequence: 1 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1873-684X
EndPage	109207
ExternalDocumentID	PMC9553470 10_1016_j_buildenv_2022_109207 S0360132322004437
GroupedDBID	--K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 23N 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAFTH AAHCO AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AARJD AAXUO ABFNM ABFYP ABJNI ABLST ABMAC ABYKQ ACDAQ ACGFS ACIWK ACRLP ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AHIDL AHJVU AIEXJ AIKHN AITUG AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BJAXD BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE JJJVA KCYFY KOM LY6 LY7 LY9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 PC. Q38 RNS ROL RPZ SDF SDG SDP SEN SES SPC SPCBC SSJ SSR SST SSZ T5K ~G- 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADMUD ADNMO AEGFY AEIPS AEUPX AFJKZ AFPUW AGQPQ AI. AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HMC HVGLF HZ~ R2- SAC SET SEW VH1 WUQ ZMT ~HD 7X8 5PM
ID	FETCH-LOGICAL-c448t-87e5dc246fa00798879f5bff5e3bf9d14d7bff6b95c1b27819d5fce21244c03e3
ISICitedReferencesCount	21
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000808297800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0360-1323
IngestDate	Tue Sep 30 17:19:32 EDT 2025 Sun Sep 28 09:42:02 EDT 2025 Sat Nov 29 07:21:48 EST 2025 Tue Nov 18 21:33:56 EST 2025 Fri Feb 23 02:40:05 EST 2024
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	Occupancy prediction COVID-19 Ventilation Bayesian deep neural network Autoencoder
Language	English
License	This is an open access article under the CC BY license. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c448t-87e5dc246fa00798879f5bff5e3bf9d14d7bff6b95c1b27819d5fce21244c03e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-4050-3740 0000-0002-5104-1238
OpenAccessLink	https://pubmed.ncbi.nlm.nih.gov/PMC9553470
PQID	2725443579
PQPubID	23479
PageCount	1
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_9553470 proquest_miscellaneous_2725443579 crossref_citationtrail_10_1016_j_buildenv_2022_109207 crossref_primary_10_1016_j_buildenv_2022_109207 elsevier_sciencedirect_doi_10_1016_j_buildenv_2022_109207
PublicationCentury	2000
PublicationDate	2022-07-01
PublicationDateYYYYMMDD	2022-07-01
PublicationDate_xml	– month: 07 year: 2022 text: 2022-07-01 day: 01
PublicationDecade	2020
PublicationTitle	Building and environment
PublicationYear	2022
Publisher	Elsevier Ltd The Authors. Published by Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd – name: The Authors. Published by Elsevier Ltd
References	Heo, Choudhary, Augenbroe (bib69) 2012; 47 Kim, Srebric (bib33) 2017; 138 Chan, Burnett, Chow (bib63) 1998; 33 Jiefan, Peng, Zhihong, Yongbao, Ying, Zhe (bib22) 2018; 180 Ng, Persily, Emmerich (bib55) 2015; 88 Candanedo, Feldheim, Deramaix (bib15) 2017; 148 Scott, Brush, Krumm, Meyers, Hazas, Hodges (bib19) 2011 Qolomany B, Al-Fuqaha A, Benhaddou D, Gupta A. Role of Deep LSTM Neural Networks and Wi-Fi Networks in Support of Occupancy Prediction in Smart Buildings. Proc - 2017 IEEE 19th Intl Conf High Perform Comput Commun HPCC 2017, 2017 IEEE 15th Intl Conf Smart City, SmartCity 2017 2017 IEEE 3rd Intl Conf Data Sci Syst DSS 2017 2018;2018-Janua:50–7. (bib2) 2012 Simmons, Lott (bib64) 1993; 2 (bib11) 2020 (bib13) 2019 Salimi, Liu, Hammad (bib16) 2019; 152 Zhuang, Wang (bib30) 2020; 261 D'Oca, Hong (bib25) 2015; 88 Joshi, Owens, Shah, Munasinghe (bib51) 2021 Chang, Chen, Lai, Lin, Pai (bib27) 2021; 11 Sha, Zhang, Qi (bib5) 2021; 74 Dong, Lam (bib32) 2011; 4 Li, Han, Zhao, Gao (bib70) 2021; 39 Wang, Huang, Feng, Cao, Haghighat (bib31) 2021; 240 Guzman, Rueda, Romero, Biscans, Agbossou, Cardenas (bib36) 2018; 2018 Park, Lee, Kang, Choi, Lee (bib47) 2021; 35 Sun, Hao, Chen, Liu (bib20) 2020; 206 Gal, Ghahramani (bib48) 2016; 3 Jain, Smith, Culligan, Taylor (bib24) 2014; 123 Wang, Feng, Chen, Zhao, Cheng, Zou (bib41) 2017; 145 . bib9 Ekwevugbe, Brown, Pakka, Fan (bib35) 2013 Roselyn, Uthra, Raj, Devaraj, Bharadwaj, Krishna Kaki (bib66) 2019; 44 Peng, Rysanek, Nagy, Schlüter (bib21) 2018; 211 Chao, Chen (bib43) 2014; 2014 (bib1) 2016 Xu, Hu, Fan (bib49) 2022; 46 Gupta, Lin, Chen (bib60) 2010; 20 Nguyen, Michaelis, Al-Hamadi, Tornow, Meinecke (bib42) 2012; 13 Office for National Statistics (bib61) 2021 Deng, Chen (bib38) 2021; 238 Jin, Yan, Chong, Dong, An (bib14) 2021; 251 Kim, Kang, Ryu, Song (bib28) 2019; 199 Burak Gunay, O'Brien, Beausoleil-Morrison (bib17) 2015; 93 Fugate D, Fuhr P, Kuruganti T. Instrumentation systems for commercial building energy efficiency. 2011 Futur Instrum Int Work FIIW 2011 - Proc 2011:21–4. Sun, Zhai (bib4) 2020; 62 bib12 bib10 Mtibaa, Nguyen, Azam, Papachristou, Venne, Cheriet (bib46) 2020; 32 Pedersen, Demurtas, Zahle (bib57) 2015; 18 Nerlich, Jaspal (bib59) 2021; 69 (bib8) 2020 Wang, Hong, Piette (bib34) 2019; 181 Ng (bib56) 2016; 56 Zhuang, Shan, Wang (bib3) 2021; 191 Senge, Bösner, Dembczyński, Haasenritter, Hirsch, Donner-Banzhoff (bib44) 2014; 255 Sun, Zhao, Zou (bib65) 2020; 216 Chen, Piedad, Kuo (bib26) 2019; 11 Manaswi (bib52) 2018 Gkantonas, de Oliveira, Mesquita, Zabotti, Mastorakos (bib62) 2020 Wang, Huang, Fu, Gao, Chen (bib6) 2022; 80 Ward, Wong, Chong, Choudhary, Ramasamy (bib39) 2021; 237 Men, Wang, Zou (bib67) 2020; 41 Wang, Chen, Song (bib53) 2017; 124 Zaatari, Novoselac, Siegel (bib58) 2016; 100 Razavi, Gharipour, Fleury, Akpan (bib23) 2019; 183 Wang, Burnett, Chong (bib40) 2003; 8 Li, Wu, Peng, Cai (bib7) 2022; 307 (bib54) 2014 Liu, Lin, Liu, Zhang, Rong, Yang (bib68) 2018; 143 Kendall, Gal (bib50) 2017 Li, Han, Zhao, Zhang, Xue (bib18) 2021; 33 Zhu, Laptev (bib45) 2017; 2017- Novem Razavi (10.1016/j.buildenv.2022.109207_bib23) 2019; 183 Sha (10.1016/j.buildenv.2022.109207_bib5) 2021; 74 Kim (10.1016/j.buildenv.2022.109207_bib33) 2017; 138 Li (10.1016/j.buildenv.2022.109207_bib70) 2021; 39 Sun (10.1016/j.buildenv.2022.109207_bib20) 2020; 206 Men (10.1016/j.buildenv.2022.109207_bib67) 2020; 41 (10.1016/j.buildenv.2022.109207_bib8) 2020 Simmons (10.1016/j.buildenv.2022.109207_bib64) 1993; 2 Peng (10.1016/j.buildenv.2022.109207_bib21) 2018; 211 Chen (10.1016/j.buildenv.2022.109207_bib26) 2019; 11 Nguyen (10.1016/j.buildenv.2022.109207_bib42) 2012; 13 Sun (10.1016/j.buildenv.2022.109207_bib65) 2020; 216 Salimi (10.1016/j.buildenv.2022.109207_bib16) 2019; 152 Liu (10.1016/j.buildenv.2022.109207_bib68) 2018; 143 Nerlich (10.1016/j.buildenv.2022.109207_bib59) 2021; 69 Wang (10.1016/j.buildenv.2022.109207_bib6) 2022; 80 D'Oca (10.1016/j.buildenv.2022.109207_bib25) 2015; 88 Wang (10.1016/j.buildenv.2022.109207_bib41) 2017; 145 Manaswi (10.1016/j.buildenv.2022.109207_bib52) 2018 Senge (10.1016/j.buildenv.2022.109207_bib44) 2014; 255 10.1016/j.buildenv.2022.109207_bib29 Kendall (10.1016/j.buildenv.2022.109207_bib50) 2017 Roselyn (10.1016/j.buildenv.2022.109207_bib66) 2019; 44 Gal (10.1016/j.buildenv.2022.109207_bib48) 2016; 3 Jain (10.1016/j.buildenv.2022.109207_bib24) 2014; 123 Zhuang (10.1016/j.buildenv.2022.109207_bib3) 2021; 191 Li (10.1016/j.buildenv.2022.109207_bib7) 2022; 307 Wang (10.1016/j.buildenv.2022.109207_bib31) 2021; 240 Sun (10.1016/j.buildenv.2022.109207_bib4) 2020; 62 Ng (10.1016/j.buildenv.2022.109207_bib55) 2015; 88 Kim (10.1016/j.buildenv.2022.109207_bib28) 2019; 199 Wang (10.1016/j.buildenv.2022.109207_bib34) 2019; 181 Zaatari (10.1016/j.buildenv.2022.109207_bib58) 2016; 100 Jin (10.1016/j.buildenv.2022.109207_bib14) 2021; 251 Wang (10.1016/j.buildenv.2022.109207_bib53) 2017; 124 Ekwevugbe (10.1016/j.buildenv.2022.109207_bib35) 2013 Chang (10.1016/j.buildenv.2022.109207_bib27) 2021; 11 Dong (10.1016/j.buildenv.2022.109207_bib32) 2011; 4 Guzman (10.1016/j.buildenv.2022.109207_bib36) 2018; 2018 Zhu (10.1016/j.buildenv.2022.109207_bib45) 2017; 2017- Novem Office for National Statistics (10.1016/j.buildenv.2022.109207_bib61) 2021 Chao (10.1016/j.buildenv.2022.109207_bib43) 2014; 2014 (10.1016/j.buildenv.2022.109207_bib2) 2012 Candanedo (10.1016/j.buildenv.2022.109207_bib15) 2017; 148 Burak Gunay (10.1016/j.buildenv.2022.109207_bib17) 2015; 93 Wang (10.1016/j.buildenv.2022.109207_bib40) 2003; 8 Jiefan (10.1016/j.buildenv.2022.109207_bib22) 2018; 180 Joshi (10.1016/j.buildenv.2022.109207_bib51) 2021 Ng (10.1016/j.buildenv.2022.109207_bib56) 2016; 56 Park (10.1016/j.buildenv.2022.109207_bib47) 2021; 35 Ward (10.1016/j.buildenv.2022.109207_bib39) 2021; 237 Chan (10.1016/j.buildenv.2022.109207_bib63) 1998; 33 (10.1016/j.buildenv.2022.109207_bib1) 2016 Gupta (10.1016/j.buildenv.2022.109207_bib60) 2010; 20 Xu (10.1016/j.buildenv.2022.109207_bib49) 2022; 46 Deng (10.1016/j.buildenv.2022.109207_bib38) 2021; 238 (10.1016/j.buildenv.2022.109207_bib54) 2014 Gkantonas (10.1016/j.buildenv.2022.109207_bib62) 2020 Zhuang (10.1016/j.buildenv.2022.109207_bib30) 2020; 261 Heo (10.1016/j.buildenv.2022.109207_bib69) 2012; 47 (10.1016/j.buildenv.2022.109207_bib13) 2019 Mtibaa (10.1016/j.buildenv.2022.109207_bib46) 2020; 32 Li (10.1016/j.buildenv.2022.109207_bib18) 2021; 33 Scott (10.1016/j.buildenv.2022.109207_bib19) 2011 10.1016/j.buildenv.2022.109207_bib37 Pedersen (10.1016/j.buildenv.2022.109207_bib57) 2015; 18
References_xml	– volume: 88 start-page: 395 year: 2015 end-page: 408 ident: bib25 article-title: Occupancy schedules learning process through a data mining framework publication-title: Energy Build. – volume: 41 start-page: 745 year: 2020 end-page: 757 ident: bib67 article-title: Experimental study on tracer gas method for building infiltration rate measurement publication-title: Build. Serv. Eng. Technol. – volume: 191 year: 2021 ident: bib3 article-title: Coordinated demand-controlled ventilation strategy for energy-efficient operation in multi-zone cleanroom air-conditioning systems publication-title: Build. Environ. – volume: 88 start-page: 316 year: 2015 end-page: 323 ident: bib55 article-title: Improving infiltration modeling in commercial building energy models publication-title: Energy Build. – volume: 80 start-page: 103719 year: 2022 ident: bib6 article-title: Metabolism-based ventilation monitoring and control method for COVID-19 risk mitigation in gymnasiums and alike places publication-title: Sustain. Cities Soc. – volume: 240 start-page: 110883 year: 2021 ident: bib31 article-title: Occupant-density-detection based energy efficient ventilation system: prevention of infection transmission publication-title: Energy Build. – volume: 2017- Novem year: 2017 ident: bib45 article-title: Deep and confident prediction for time series at uber publication-title: IEEE Int. Conf. Data Min. Work. ICDMW – year: 2020 ident: bib8 publication-title: Chartered Institution of Building Services Engineers (CIBSE). Coronavirus, SARS-CoV-2, COVID-19 and HVAC Systems – volume: 152 start-page: 1 year: 2019 end-page: 16 ident: bib16 article-title: Occupancy prediction model for open-plan offices using real-time location system and inhomogeneous Markov chain publication-title: Build. Environ. – volume: 2018 year: 2018 ident: bib36 article-title: Enabling winter behavior analysis on electrically heated residential buildings by smart sub-metering publication-title: Proc. IEEE Int. Conf. Ind. Technol. – volume: 148 start-page: 327 year: 2017 end-page: 341 ident: bib15 article-title: A methodology based on Hidden Markov Models for occupancy detection and a case study in a low energy residential building publication-title: Energy Build. – volume: 11 start-page: 956 year: 2019 ident: bib26 article-title: Energy consumption load forecasting using a level-based random forest classifier publication-title: Symmetry (Basel) – year: 2014 ident: bib54 article-title: Guideline 14-2014 -- Measurement of Energy, Demand, and Water Savings – volume: 255 start-page: 16 year: 2014 end-page: 29 ident: bib44 article-title: Reliable classification: learning classifiers that distinguish aleatoric and epistemic uncertainty publication-title: Inf. Sci. – volume: 181 start-page: 29 year: 2019 end-page: 42 ident: bib34 article-title: Predicting plug loads with occupant count data through a deep learning approach publication-title: Energy – volume: 183 start-page: 195 year: 2019 end-page: 208 ident: bib23 article-title: Occupancy detection of residential buildings using smart meter data: a large-scale study publication-title: Energy Build. – volume: 216 year: 2020 ident: bib65 article-title: A review of building occupancy measurement systems publication-title: Energy Build. – year: 2019 ident: bib13 article-title: Ventilation in Buildings – volume: 11 year: 2021 ident: bib27 article-title: Forecasting hotel room occupancy using long short-term memory networks with sentiment analysis and scores of customer online reviews publication-title: Appl. Sci. – year: 2017 ident: bib50 article-title: What uncertainties do we need in Bayesian deep learning for computer vision? publication-title: Adv. Neural Inf. Process. Syst. – volume: 199 start-page: 216 year: 2019 end-page: 222 ident: bib28 article-title: Real-time occupancy prediction in a large exhibition hall using deep learning approach publication-title: Energy Build. – volume: 8 start-page: 377 year: 2003 end-page: 391 ident: bib40 article-title: Experimental validation of CO publication-title: Indoor Built Environ. – ident: bib12 article-title: Roadmap to improve and ensure good indoor ventilation in the context of COVID-19 2021 – volume: 3 start-page: 1651 year: 2016 end-page: 1660 ident: bib48 article-title: Dropout as a Bayesian approximation: representing model uncertainty in deep learning publication-title: 33rd Int. Conf. Mach. Learn. ICML 2016 – volume: 32 start-page: 17569 year: 2020 end-page: 17585 ident: bib46 article-title: LSTM-based indoor air temperature prediction framework for HVAC systems in smart buildings publication-title: Neural Comput. Appl. – volume: 238 year: 2021 ident: bib38 article-title: Reinforcement learning of occupant behavior model for cross-building transfer learning to various HVAC control systems publication-title: Energy Build. – volume: 33 start-page: 303 year: 1998 end-page: 314 ident: bib63 article-title: Energy use for ventilation systems in underground car parks publication-title: Build. Environ. – volume: 47 start-page: 550 year: 2012 end-page: 560 ident: bib69 article-title: Calibration of building energy models for retrofit analysis under uncertainty publication-title: Energy Build. – ident: bib9 article-title: COVID-19 guidance document, How to operate and use building services in order to prevent the spread of the coronavirus disease (COVID-19) virus (SARS-CoV-2) in workplaces 2020:1–6 – ident: bib10 article-title: Guidance for building operations during the COVID-19 pandemic n.d – volume: 35 start-page: 795 year: 2021 end-page: 803 ident: bib47 article-title: Predictive model for PV power generation using RNN (LSTM) publication-title: J. Mech. Sci. Technol. – year: 2020 ident: bib11 article-title: Addressing COVID-19 in buildings module 15 meg sears PhD in collaboration with and approved by the Canadian committee for indoor air quality – volume: 20 start-page: 31 year: 2010 end-page: 39 ident: bib60 article-title: Characterizing exhaled airflow from breathing and talking publication-title: Indoor Air – year: 2012 ident: bib2 article-title: Indoor environmental input parameters for design and assessment of energy performance of buildings addressing indoor air quality, thermal environment, lighting and acoustics publication-title: Eur Stand – volume: 33 year: 2021 ident: bib18 article-title: Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system publication-title: J. Build. Eng. – volume: 237 year: 2021 ident: bib39 article-title: A study on the transferability of computational models of building electricity load patterns across climatic zones publication-title: Energy Build. – volume: 251 year: 2021 ident: bib14 article-title: Building occupancy forecasting: a systematical and critical review publication-title: Energy Build. – volume: 46 year: 2022 ident: bib49 article-title: Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks publication-title: J. Build. Eng. – volume: 56 start-page: 70 year: 2016 end-page: 72 ident: bib56 article-title: Infiltration in energy modeling : a simple equation made better publication-title: ASHRAE J. – year: 2021 ident: bib61 article-title: Coronavirus (COVID-19) Latest Insights: Work – volume: 261 year: 2020 ident: bib30 article-title: Risk-based online robust optimal control of air-conditioning systems for buildings requiring strict humidity control considering measurement uncertainties publication-title: Appl. Energy – volume: 2014 year: 2014 ident: bib43 article-title: An intelligent traffic flow control system based on radio frequency identification and wireless sensor networks publication-title: Int. J. Distributed Sens. Netw. – volume: 69 start-page: 566 year: 2021 end-page: 583 ident: bib59 article-title: Social representations of ‘social distancing’ in response to COVID-19 in the UK media publication-title: Curr. Sociol. – volume: 4 start-page: 359 year: 2011 end-page: 369 ident: bib32 article-title: Building energy and comfort management through occupant behaviour pattern detection based on a large-scale environmental sensor network publication-title: J. Build Perform Simul. – volume: 143 start-page: 163 year: 2018 end-page: 177 ident: bib68 article-title: Evaluation of air infiltration in a hub airport terminal: on-site measurement and numerical simulation publication-title: Build. Environ. – volume: 93 start-page: 71 year: 2015 end-page: 85 ident: bib17 article-title: Development of an occupancy learning algorithm for terminal heating and cooling units publication-title: Build. Environ. – volume: 18 start-page: 1933 year: 2015 end-page: 1952 ident: bib57 article-title: Calibration of a spinner anemometer for yaw misalignment measurements publication-title: Wind Energy – volume: 100 start-page: 186 year: 2016 end-page: 196 ident: bib58 article-title: Impact of ventilation and filtration strategies on energy consumption and exposures in retail stores publication-title: Build. Environ. – volume: 2 start-page: 314 year: 1993 end-page: 323 ident: bib64 article-title: Automatic fan control to reduce fan run time during warm weather ventilation publication-title: J. Appl. Poultry Res. – year: 2016 ident: bib1 publication-title: ASHRAE 62.1-2016. Ventilation for Acceptable Indoor Air Quality – volume: 123 start-page: 168 year: 2014 end-page: 178 ident: bib24 article-title: Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy publication-title: Appl. Energy – volume: 138 start-page: 591 year: 2017 end-page: 600 ident: bib33 article-title: Impact of occupancy rates on the building electricity consumption in commercial buildings publication-title: Energy Build. – reference: Fugate D, Fuhr P, Kuruganti T. Instrumentation systems for commercial building energy efficiency. 2011 Futur Instrum Int Work FIIW 2011 - Proc 2011:21–4. – start-page: 1 year: 2020 end-page: 13 ident: bib62 article-title: airborne.cam: a Risk Calculator of SARS-CoV-2 Aerosol Transmission under Well-Mixed Ventilation Conditions – reference: Qolomany B, Al-Fuqaha A, Benhaddou D, Gupta A. Role of Deep LSTM Neural Networks and Wi-Fi Networks in Support of Occupancy Prediction in Smart Buildings. Proc - 2017 IEEE 19th Intl Conf High Perform Comput Commun HPCC 2017, 2017 IEEE 15th Intl Conf Smart City, SmartCity 2017 2017 IEEE 3rd Intl Conf Data Sci Syst DSS 2017 2018;2018-Janua:50–7. – volume: 307 year: 2022 ident: bib7 article-title: Tube-based robust model predictive control of multi-zone demand-controlled ventilation systems for energy saving and indoor air quality publication-title: Appl. Energy – volume: 206 year: 2020 ident: bib20 article-title: Data-driven occupant-behavior analytics for residential buildings publication-title: Energy – start-page: 31 year: 2018 end-page: 43 ident: bib52 article-title: Understanding and working with Keras publication-title: Deep Learn with Appl Using Python – start-page: 4165 year: 2021 end-page: 4168 ident: bib51 article-title: Analysis of preprocessing techniques, Keras tuner, and transfer learning on cloud street image data publication-title: Proc. - 2021 IEEE Int. Conf. Big Data, Big Data 2021 – reference: . – year: 2011 ident: bib19 article-title: PreHeat: controlling home heating using occupancy prediction publication-title: UbiComp’11 - Proc 2011 ACM Conf Ubiquitous Comput – volume: 44 start-page: 85 year: 2019 end-page: 98 ident: bib66 article-title: Development and implementation of novel sensor fusion algorithm for occupancy detection and automation in energy efficient buildings publication-title: Sustain. Cities Soc. – volume: 74 start-page: 103256 year: 2021 ident: bib5 article-title: Optimal control of high-rise building mechanical ventilation system for achieving low risk of COVID-19 transmission and ventilative cooling publication-title: Sustain. Cities Soc. – volume: 211 start-page: 1343 year: 2018 end-page: 1358 ident: bib21 article-title: Using machine learning techniques for occupancy-prediction-based cooling control in office buildings publication-title: Appl. Energy – volume: 180 start-page: 135 year: 2018 end-page: 145 ident: bib22 article-title: Extracting typical occupancy data of different buildings from mobile positioning data publication-title: Energy Build. – year: 2013 ident: bib35 article-title: Real-time building occupancy sensing using neural-network based sensor network publication-title: IEEE Int. Conf. Digit. Ecosyst. Technol. – volume: 145 start-page: 155 year: 2017 end-page: 162 ident: bib41 article-title: Predictive control of indoor environment using occupant number detected by video data and CO2 concentration publication-title: Energy Build. – volume: 13 start-page: 154 year: 2012 end-page: 165 ident: bib42 article-title: Stereo-camera-based urban environment perception using occupancy grid and object tracking publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 62 start-page: 102390 year: 2020 ident: bib4 article-title: The efficacy of social distance and ventilation effectiveness in preventing COVID-19 transmission publication-title: Sustain. Cities Soc. – volume: 124 start-page: 130 year: 2017 end-page: 142 ident: bib53 article-title: Modeling and predicting occupancy profile in office space with a Wi-Fi probe-based Dynamic Markov Time-Window Inference approach publication-title: Build. Environ. – volume: 39 year: 2021 ident: bib70 article-title: Online model for indoor temperature control based on building thermal process of air conditioning system publication-title: J. Build. Eng. – year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib13 – start-page: 1 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib62 – volume: 33 start-page: 303 year: 1998 ident: 10.1016/j.buildenv.2022.109207_bib63 article-title: Energy use for ventilation systems in underground car parks publication-title: Build. Environ. doi: 10.1016/S0360-1323(97)00075-9 – volume: 39 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib70 article-title: Online model for indoor temperature control based on building thermal process of air conditioning system publication-title: J. Build. Eng. – volume: 238 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib38 article-title: Reinforcement learning of occupant behavior model for cross-building transfer learning to various HVAC control systems publication-title: Energy Build. doi: 10.1016/j.enbuild.2021.110860 – volume: 148 start-page: 327 year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib15 article-title: A methodology based on Hidden Markov Models for occupancy detection and a case study in a low energy residential building publication-title: Energy Build. doi: 10.1016/j.enbuild.2017.05.031 – volume: 44 start-page: 85 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib66 article-title: Development and implementation of novel sensor fusion algorithm for occupancy detection and automation in energy efficient buildings publication-title: Sustain. Cities Soc. doi: 10.1016/j.scs.2018.09.031 – volume: 143 start-page: 163 year: 2018 ident: 10.1016/j.buildenv.2022.109207_bib68 article-title: Evaluation of air infiltration in a hub airport terminal: on-site measurement and numerical simulation publication-title: Build. Environ. doi: 10.1016/j.buildenv.2018.07.006 – volume: 145 start-page: 155 year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib41 article-title: Predictive control of indoor environment using occupant number detected by video data and CO2 concentration publication-title: Energy Build. doi: 10.1016/j.enbuild.2017.04.014 – volume: 74 start-page: 103256 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib5 article-title: Optimal control of high-rise building mechanical ventilation system for achieving low risk of COVID-19 transmission and ventilative cooling publication-title: Sustain. Cities Soc. doi: 10.1016/j.scs.2021.103256 – year: 2012 ident: 10.1016/j.buildenv.2022.109207_bib2 article-title: Indoor environmental input parameters for design and assessment of energy performance of buildings addressing indoor air quality, thermal environment, lighting and acoustics publication-title: Eur Stand – volume: 206 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib20 article-title: Data-driven occupant-behavior analytics for residential buildings publication-title: Energy doi: 10.1016/j.energy.2020.118100 – volume: 152 start-page: 1 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib16 article-title: Occupancy prediction model for open-plan offices using real-time location system and inhomogeneous Markov chain publication-title: Build. Environ. doi: 10.1016/j.buildenv.2019.01.052 – volume: 199 start-page: 216 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib28 article-title: Real-time occupancy prediction in a large exhibition hall using deep learning approach publication-title: Energy Build. doi: 10.1016/j.enbuild.2019.06.043 – volume: 240 start-page: 110883 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib31 article-title: Occupant-density-detection based energy efficient ventilation system: prevention of infection transmission publication-title: Energy Build. doi: 10.1016/j.enbuild.2021.110883 – volume: 62 start-page: 102390 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib4 article-title: The efficacy of social distance and ventilation effectiveness in preventing COVID-19 transmission publication-title: Sustain. Cities Soc. doi: 10.1016/j.scs.2020.102390 – ident: 10.1016/j.buildenv.2022.109207_bib29 doi: 10.1109/HPCC-SmartCity-DSS.2017.7 – volume: 180 start-page: 135 year: 2018 ident: 10.1016/j.buildenv.2022.109207_bib22 article-title: Extracting typical occupancy data of different buildings from mobile positioning data publication-title: Energy Build. doi: 10.1016/j.enbuild.2018.09.002 – volume: 41 start-page: 745 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib67 article-title: Experimental study on tracer gas method for building infiltration rate measurement publication-title: Build. Serv. Eng. Technol. doi: 10.1177/0143624420911810 – volume: 183 start-page: 195 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib23 article-title: Occupancy detection of residential buildings using smart meter data: a large-scale study publication-title: Energy Build. doi: 10.1016/j.enbuild.2018.11.025 – volume: 2018 year: 2018 ident: 10.1016/j.buildenv.2022.109207_bib36 article-title: Enabling winter behavior analysis on electrically heated residential buildings by smart sub-metering publication-title: Proc. IEEE Int. Conf. Ind. Technol. – volume: 47 start-page: 550 year: 2012 ident: 10.1016/j.buildenv.2022.109207_bib69 article-title: Calibration of building energy models for retrofit analysis under uncertainty publication-title: Energy Build. doi: 10.1016/j.enbuild.2011.12.029 – volume: 11 start-page: 956 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib26 article-title: Energy consumption load forecasting using a level-based random forest classifier publication-title: Symmetry (Basel) doi: 10.3390/sym11080956 – volume: 46 year: 2022 ident: 10.1016/j.buildenv.2022.109207_bib49 article-title: Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks publication-title: J. Build. Eng. – volume: 191 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib3 article-title: Coordinated demand-controlled ventilation strategy for energy-efficient operation in multi-zone cleanroom air-conditioning systems publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.107588 – ident: 10.1016/j.buildenv.2022.109207_bib37 doi: 10.1109/FIIW.2011.6476826 – volume: 33 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib18 article-title: Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system publication-title: J. Build. Eng. – volume: 20 start-page: 31 year: 2010 ident: 10.1016/j.buildenv.2022.109207_bib60 article-title: Characterizing exhaled airflow from breathing and talking publication-title: Indoor Air doi: 10.1111/j.1600-0668.2009.00623.x – volume: 251 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib14 article-title: Building occupancy forecasting: a systematical and critical review publication-title: Energy Build. doi: 10.1016/j.enbuild.2021.111345 – volume: 123 start-page: 168 year: 2014 ident: 10.1016/j.buildenv.2022.109207_bib24 article-title: Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy publication-title: Appl. Energy doi: 10.1016/j.apenergy.2014.02.057 – volume: 4 start-page: 359 year: 2011 ident: 10.1016/j.buildenv.2022.109207_bib32 article-title: Building energy and comfort management through occupant behaviour pattern detection based on a large-scale environmental sensor network publication-title: J. Build Perform Simul. doi: 10.1080/19401493.2011.577810 – volume: 11 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib27 article-title: Forecasting hotel room occupancy using long short-term memory networks with sentiment analysis and scores of customer online reviews publication-title: Appl. Sci. doi: 10.3390/app112110291 – volume: 3 start-page: 1651 year: 2016 ident: 10.1016/j.buildenv.2022.109207_bib48 article-title: Dropout as a Bayesian approximation: representing model uncertainty in deep learning – start-page: 31 year: 2018 ident: 10.1016/j.buildenv.2022.109207_bib52 article-title: Understanding and working with Keras publication-title: Deep Learn with Appl Using Python doi: 10.1007/978-1-4842-3516-4_2 – volume: 13 start-page: 154 year: 2012 ident: 10.1016/j.buildenv.2022.109207_bib42 article-title: Stereo-camera-based urban environment perception using occupancy grid and object tracking publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2011.2165705 – volume: 307 year: 2022 ident: 10.1016/j.buildenv.2022.109207_bib7 article-title: Tube-based robust model predictive control of multi-zone demand-controlled ventilation systems for energy saving and indoor air quality publication-title: Appl. Energy doi: 10.1016/j.apenergy.2021.118297 – volume: 32 start-page: 17569 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib46 article-title: LSTM-based indoor air temperature prediction framework for HVAC systems in smart buildings publication-title: Neural Comput. Appl. doi: 10.1007/s00521-020-04926-3 – volume: 18 start-page: 1933 year: 2015 ident: 10.1016/j.buildenv.2022.109207_bib57 article-title: Calibration of a spinner anemometer for yaw misalignment measurements publication-title: Wind Energy doi: 10.1002/we.1798 – start-page: 4165 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib51 article-title: Analysis of preprocessing techniques, Keras tuner, and transfer learning on cloud street image data – volume: 138 start-page: 591 year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib33 article-title: Impact of occupancy rates on the building electricity consumption in commercial buildings publication-title: Energy Build. doi: 10.1016/j.enbuild.2016.12.056 – volume: 181 start-page: 29 year: 2019 ident: 10.1016/j.buildenv.2022.109207_bib34 article-title: Predicting plug loads with occupant count data through a deep learning approach publication-title: Energy doi: 10.1016/j.energy.2019.05.138 – year: 2014 ident: 10.1016/j.buildenv.2022.109207_bib54 – volume: 93 start-page: 71 year: 2015 ident: 10.1016/j.buildenv.2022.109207_bib17 article-title: Development of an occupancy learning algorithm for terminal heating and cooling units publication-title: Build. Environ. doi: 10.1016/j.buildenv.2015.06.009 – volume: 56 start-page: 70 year: 2016 ident: 10.1016/j.buildenv.2022.109207_bib56 article-title: Infiltration in energy modeling : a simple equation made better publication-title: ASHRAE J. – year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib50 article-title: What uncertainties do we need in Bayesian deep learning for computer vision? publication-title: Adv. Neural Inf. Process. Syst. – volume: 255 start-page: 16 year: 2014 ident: 10.1016/j.buildenv.2022.109207_bib44 article-title: Reliable classification: learning classifiers that distinguish aleatoric and epistemic uncertainty publication-title: Inf. Sci. doi: 10.1016/j.ins.2013.07.030 – year: 2016 ident: 10.1016/j.buildenv.2022.109207_bib1 – volume: 2014 year: 2014 ident: 10.1016/j.buildenv.2022.109207_bib43 article-title: An intelligent traffic flow control system based on radio frequency identification and wireless sensor networks publication-title: Int. J. Distributed Sens. Netw. – volume: 88 start-page: 395 year: 2015 ident: 10.1016/j.buildenv.2022.109207_bib25 article-title: Occupancy schedules learning process through a data mining framework publication-title: Energy Build. doi: 10.1016/j.enbuild.2014.11.065 – year: 2013 ident: 10.1016/j.buildenv.2022.109207_bib35 article-title: Real-time building occupancy sensing using neural-network based sensor network publication-title: IEEE Int. Conf. Digit. Ecosyst. Technol. – volume: 8 start-page: 377 year: 2003 ident: 10.1016/j.buildenv.2022.109207_bib40 article-title: Experimental validation of CO2-based occupancy detection for demand-controlled ventilation publication-title: Indoor Built Environ. doi: 10.1177/1420326X9900800605 – volume: 124 start-page: 130 year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib53 article-title: Modeling and predicting occupancy profile in office space with a Wi-Fi probe-based Dynamic Markov Time-Window Inference approach publication-title: Build. Environ. doi: 10.1016/j.buildenv.2017.08.003 – volume: 2 start-page: 314 year: 1993 ident: 10.1016/j.buildenv.2022.109207_bib64 article-title: Automatic fan control to reduce fan run time during warm weather ventilation publication-title: J. Appl. Poultry Res. doi: 10.1093/japr/2.4.314 – volume: 237 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib39 article-title: A study on the transferability of computational models of building electricity load patterns across climatic zones publication-title: Energy Build. doi: 10.1016/j.enbuild.2021.110826 – volume: 261 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib30 article-title: Risk-based online robust optimal control of air-conditioning systems for buildings requiring strict humidity control considering measurement uncertainties publication-title: Appl. Energy doi: 10.1016/j.apenergy.2019.114451 – volume: 211 start-page: 1343 year: 2018 ident: 10.1016/j.buildenv.2022.109207_bib21 article-title: Using machine learning techniques for occupancy-prediction-based cooling control in office buildings publication-title: Appl. Energy doi: 10.1016/j.apenergy.2017.12.002 – year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib61 – volume: 2017- Novem year: 2017 ident: 10.1016/j.buildenv.2022.109207_bib45 article-title: Deep and confident prediction for time series at uber – volume: 69 start-page: 566 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib59 article-title: Social representations of ‘social distancing’ in response to COVID-19 in the UK media publication-title: Curr. Sociol. doi: 10.1177/0011392121990030 – year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib8 – volume: 35 start-page: 795 year: 2021 ident: 10.1016/j.buildenv.2022.109207_bib47 article-title: Predictive model for PV power generation using RNN (LSTM) publication-title: J. Mech. Sci. Technol. doi: 10.1007/s12206-021-0140-0 – volume: 100 start-page: 186 year: 2016 ident: 10.1016/j.buildenv.2022.109207_bib58 article-title: Impact of ventilation and filtration strategies on energy consumption and exposures in retail stores publication-title: Build. Environ. doi: 10.1016/j.buildenv.2016.01.026 – volume: 80 start-page: 103719 year: 2022 ident: 10.1016/j.buildenv.2022.109207_bib6 article-title: Metabolism-based ventilation monitoring and control method for COVID-19 risk mitigation in gymnasiums and alike places publication-title: Sustain. Cities Soc. doi: 10.1016/j.scs.2022.103719 – volume: 216 year: 2020 ident: 10.1016/j.buildenv.2022.109207_bib65 article-title: A review of building occupancy measurement systems publication-title: Energy Build. doi: 10.1016/j.enbuild.2020.109965 – year: 2011 ident: 10.1016/j.buildenv.2022.109207_bib19 article-title: PreHeat: controlling home heating using occupancy prediction – volume: 88 start-page: 316 year: 2015 ident: 10.1016/j.buildenv.2022.109207_bib55 article-title: Improving infiltration modeling in commercial building energy models publication-title: Energy Build. doi: 10.1016/j.enbuild.2014.11.078
SSID	ssj0016934
Score	2.4901571
Snippet	Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol...
SourceID	pubmedcentral proquest crossref elsevier
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	109207
SubjectTerms	Autoencoder Bayesian deep neural network COVID-19 Occupancy prediction Ventilation
Title	Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks
URI	https://dx.doi.org/10.1016/j.buildenv.2022.109207 https://www.proquest.com/docview/2725443579 https://pubmed.ncbi.nlm.nih.gov/PMC9553470
Volume	219
WOSCitedRecordID	wos000808297800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-684X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016934 issn: 0360-1323 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1db9MwFLW6jgd4QHyKDpiMxNuUkiZxbD-OagiQmCo0pL5FcWKrm0ZStUnpfhl_j-vYzocADZB4iVJXTqLck-tr-9xzEXqt4pBSIWBawiPiRTLyPSaY8uKAqxTGu8yXrCk2Qc_P2XLJF6PRd5cLs7umRcH2e77-r6aGNjC2Tp39C3O3F4UGOAejwxHMDsc_MvxiA5-oprxqBeaTslER1umVEJ3KLN1WjjqpSeVe-k0zv0rwG1_BVg330ZDj2gI-aV2VWuxSa068TW9kk3SZS7k-0VKY0KkwRPLtYHvYFttutiZ6uXTdMnVt16nnqxSGphah81VZ56vU7O1_1oVauiXz3QbctC6xZIiYpuy3W7EIOnarwVhTbbquVuVmO23J_0203SbZdIwmk9jlezBpNn5QGj_NaOjFzJA7nSN3zte44pnPA1NQ1w7sXcNPw4ZZwbiaCv124K1M9WNP-1cYSHIvPs05IWFE_QN0GFDCyRgdnn44W35sN7BiHlrlMvPsveT0X9_md3FRb94zZO32wqCLB-i-nb_gU4O7h2gki0foXk_V8jHaDxCIWwTiHgL1Oe4QiC0CcQ-B2CIQ9xCIHQKxRiA2CMQOgU_Ql3dnF_P3ni3w4WVRxCoYiSXJsyCKVQqhKofxjisilCIyFIrnsyin8CsWnGQzEVAIXnOiMhnomDTzQxk-ReOiLOQzhBmEmszPAzETKpKUcaJ4GOciBGckIDqbIOJeb5JZ9XtdhOU6cTTHq8SZJdFmSYxZJuhN229t9F9u7cGd9RIbxZroNAG03dr3lTN3Am5e792lhSzrbRJQrSUYEsoniA5w0D6WFoof_lNcrhrBeAvWo3_u-Rzd7T7kF2hcbWr5Et3JdtXldnOMDuiSHdsv4Ad0-fKo
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Probabilistic+occupancy+forecasting+for+risk-aware+optimal+ventilation+through+autoencoder+Bayesian+deep+neural+networks&rft.jtitle=Building+and+environment&rft.au=Zhuang%2C+Chaoqun&rft.au=Choudhary%2C+Ruchi&rft.au=Mavrogianni%2C+Anna&rft.date=2022-07-01&rft.pub=The+Authors.+Published+by+Elsevier+Ltd&rft.issn=0360-1323&rft.eissn=1873-684X&rft.volume=219&rft.spage=109207&rft.epage=109207&rft_id=info:doi/10.1016%2Fj.buildenv.2022.109207&rft.externalDocID=PMC9553470
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-1323&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-1323&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-1323&client=summon