The manual control of windows is one of the common adaptive behaviours for occupants to adjust their indoor environment in homes. The cross-ventilation by the window opening provides a useful tool to control the thermal comfort and indoor air quality in homes. The objective of this study was to develop a modelling methodology for predicting individual occupant's behaviour relating to the manual control of windows by using machine learning algorithms. The proposed six machine learning algorithms were trained by the field monitoring data of 23 sample homes. The predictive performance of the machine learning algorithms was analysed. The algorithms predicted the occupant's behaviour more precisely compared with the logistic model. Among the algorithms, K-Nearest Neighbours (KNN) shows the best fitness with the monitored data set. The driving parameters of the manual control of windows in each sample home can be clearly drawn by the algorithms. The proposed machine learning algorithms can help to understand the influence of the occupant's behaviour on the indoor environment in buildings.
DickJBThomasDA.Ventilating research in occupied houses. JIHVE1951;
19: 306–326.
2.
RijalHBHumphreysMANicolJF.Development of a window opening algorithm based on adaptive thermal comfort to predict occupant behaviour in Japanese dwellings. Jpn Archit Rev2018;
1: 310–321.
3.
RajaIANicolJFMcCartneyKJHumphreysMA.Thermal comfort: use of controls in naturally ventilated buildings. Energy Build2001;
33: 235–244.
4.
ParkJS.Long-term field measurement on effects of wind speed and directional fluctuation on wind-driven cross ventilation in a mock-up building. Build Environ2013;
66: 1–8.
5.
ParkJSChoiCS.Modeling occupant behavior of the manual control of windows in residential buildings. Indoor Air2018;
29: 242–251.
6.
CalìDOsterhageTStreblowRMüllerD.Energy performance gap in refurbished German dwellings: lesson learned from a field test. Energy Build2016;
127: 1146–1158.
7.
MartinaitisVZavadskasEKMotuzieneVVilutieneT.Importance of occupancy information when simulating energy demand of energy efficient house: a case study. Energy Build2015;
101: 64–75.
8.
ParkJSKimHJ.A field study of occupant behavior and energy consumption in apartments with mechanical ventilation. Energy Build2012;
50: 19–25.
9.
RaaijWFVerhallenT.Patterns of residential energy behavior. J Econ Psychol1983;
4: 85–106.
10.
KarlssonFRohdinPPerssonML.Measured and predicted energy demand of a low energy building. Build Serv Eng Res Technol2007;
28: 223–235.
11.
RijalHBTuohyPHumphreysMANicolJFSamuelAClarkeJ.Using results from field surveys to predict the effect of open windows on thermal comfort and energy use in buildings. Energy Build2007;
39: 823–836.
12.
HerkelSKnappUPfafferottJ.Towards a model of user behaviour regarding the manual control of windows in office buildings. Build Environ2008;
43: 588–600.
13.
YunGYSteemersK.Time-dependent occupant behaviour models of window control in summer. Build Environ2008;
43: 1471–1482.
14.
HaldiFRobinsonD.On the behaviour and adaptation of office occupants. Build Environ2008;
43: 2163–2177.
15.
RijalHBTuohyPNicolJFHumphreysMASamuelAClarkeJ.Development of an adaptive window-opening algorithm to predict the thermal comfort, energy use and overheating in buildings. J Build Perform Simul2008;
1: 17–30.
16.
PanSXiongYHanYZhangXXiaLWeiSWuJHanM.A study on influential factors of occupant window-opening behavior in an office building in China. Build Environ2018;
133: 41–50.
17.
NaspiFArnesanoMZampettiLStaziFRevelGMD’OrazioGM.Experimental study on occupants’ interaction with windows and lights in Mediterranean offices during the non-heating season. Build Environ2018;
127: 221–238.
18.
FritschRKohlerANyg Ard-FergusonMScartezziniJL.A stochastic model of user behaviour regarding ventilation. Build Environ1990;
25: 173–181.
19.
YaoMZhaoB.Window opening behavior of occupants in residential buildings in Beijing. Build Environ2017;
124: 441–449.
20.
FabiVAndersenRVCorgnatiSPOlesenBW.A methodology for modelling energy-related human behaviour: application to window opening behaviour in residential buildings. Build Simul2013;
6: 415–427.
21.
ShiSZhaoB.Occupants’ interactions with windows in 8 residential apartments in Beijing and Nanjing. Build Simul2016;
9: 221–231.
22.
JonesRVFuertesAGregoriEGirettiA.Stochastic behavioural models of occupants’ main bedroom window operation for UK residential buildings. Build Environ2017;
118: 144–158.
23.
FabiVAndersenRKCorgnatiS.Verification of stochastic behavioural models of occupants’ interactions with windows in residential buildings. Build Environ2015;
94: 371–383.
24.
JianYGuoYLiuJBaiZLiQ.Case study of window opening behavior using field measurement results. Build Simul2011;
4: 107–116.
25.
JeongBCJeongJWParkJS.Occupant behavior regarding the manual control of windows in residential buildings. Energy Build2016;
127: 206–216.
26.
KimJde DearRParkinsonTCandidoC.Understanding patterns of adaptive comfort behaviour in the Sydney mixed-mode residential context. Energy Build2017;
141: 274–283.
27.
NicolJF. Characterising occupant behavior in buildings: towards a stochastic model of occupant use of windows, lights, blinds heaters and fans. In: The proceedings of the seventh Int. IBPSA Conference, Rio de Janeiro, Brazil, August 13–15 2001; pp.1073–1078.
28.
HaldiFRobinsonD.Interactions with window openings by office occupants. Build Environ2009;
44: 2378–2395.
29.
AndersenRFabiVToftumJCorgnatiSPOlesenBW.Window opening behaviour modelled from measurements in Danish dwellings. Build Environ2013;
69: 101–113.
30.
GrabeJ.Potential of artificial neural networks to predict thermal sensation votes. Appl Energy2016;
161: 412–424.
31.
CheungTCTSchiavonSGallETJinMNazaroffWW.Longitudinal assessment of thermal and perceived air quality acceptability in relation to temperature, humidity, and CO2 exposure in Singapore. Build Environ2017;
115: 80–90.
32.
KimJZhouYSchiavonSRafteryPBragerG.Personal comfort models: predicting individuals’ thermal preference using occupant heating and cooling behavior and machine learning. Build Environ2018;
129: 96–106.
33.
MoonJWJungSK.Development of a thermal control algorithm using artificial neural network models for improved thermal comfort and energy efficiency in accommodation buildings. Appl Therm Eng2016;
103: 1135–1144.
34.
BarthelmesVMHeoYFabiVCorgnatiSP.Exploration of the Bayesian Network framework for modelling window control behavior. Build Environ2017;
126: 318–330.
35.
PanSHanYWeiSWeiYXiaLXieLKongXYuW.A model based on Gauss distribution for predicting window behavior in building. Build Environ2019;
149: 210–219.
36.
MarkovicRGrintalEWölkiDFrischJTreeckC.Window opening model using deep learning methods. Build Environ2018;
145: 319–329.
37.
WeiYYuHPanSXiaLXieJWangXWuJZhangWLiQ.Comparison of different window behavior modeling approaches during transition season in Beijing, China. Build Environ2019;
157: 1–15.
38.
ASHRAE Standard 55-2017. Thermal comfort standard.
Atlanta, Georgia:
American Society of Heating Refrigerating and Air-Conditioning Engineers, 2017.
39.
YaoMZhaoB.Factors affecting occupants’ interactions with windows in residential buildings in Beijing, China. Procedia Eng2017;
205: 3428–3434.
40.
CramerSKampouridisMFreitasAAAlexandridisAK.An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives. Expert Syst Appl2017;
85: 169–181.
41.
WahidFKimDH.A prediction approach for demand analysis of energy consumption using K-nearest neighbor in residential buildings. IJSH2016;
10: 97–108.
LeeY.Handwritten digit recognition using K Nearest-neighbor, radial-basis function, and backpropagation neural networks. Neural Comput1991;
3: 440–449.
44.
TakasuMOokaRRijalHBIndragantiMSinghMK.Study on adaptive thermal comfort in Japanese offices under various operation modes. Build Environ2017;
118: 273–288.
