Accurate forecasting of individual thermal demand is essential for achieving personalized and energy-efficient control in heating, ventilation, and air conditioning (HVAC) systems. Traditional control strategies and thermal comfort models often rely on generalized assumptions or subjective surveys, which fail to capture individual variability. In this paper, we propose a demand forecasting model that uses physiological and microenvironmental parameters to infer personalized thermal needs in real-time. This study used skin temperature as the core physiological indicator, continuously collects physiological and microenvironment parameters of the wrist, and systematically analysed the relationship between skin temperature and environmental parameters. The results indicated that environmental temperature is the main factor affecting skin temperature, and there was a strong linear correlation between the two. Furthermore, the regression relationship between wrist skin temperature and environmental temperature differed during the temperature-falling and temperature-rising phases, reflecting different physiological responses. The research findings suggest that the coupled relationship between skin temperature and environmental parameters can provide important data support for individual thermal demand prediction in HVAC control.
KlepeisNENelsonWCOttWRRobinsonJPTsangAMSwitzerPBeharJVHernSCEngelmannWH. The National Human Activity Pattern Survey (NHAPS): a resource for assessing exposure to environmental pollutants. J Expo Anal Environ Epidemiol2000; 11(3): 231–252.
2.
FaghihimaniMMHosseiniSA. Study on thermal comfort of low-sweat and high-sweat young men based on heart rate variability analysis under different clothing. Indoor Built Environ2022; 31(10): 2430–2446.
3.
LanKLiSWuYChangGPengF. Experimental study on the impact of indoor lighting and thermal environment on university students’ learning performance in summer. Energy Build2025; 339: 115774.
4.
YuJHassanMDTBaiYAnNTamVWY. A pilot study monitoring the thermal comfort of the elderly living in nursing homes in Hefei, China, using wireless sensor networks, site measurements and a survey. Indoor Built Environ2020; 29(3): 449–464.
5.
ManeshMASarkardeheeEJafarianS. Effective environmental factors on efficiency of office buildings staff in a cold semi-arid climate (case study: kermanshah). Renew Energy Res Appl2023; 4(1): 103–111.
6.
YeomD. A contactless predictive model of thermal sensation for enhancing cognitive performance via facial skin temperature. Indoor Built Environ2025; 34(6): 1126–1143.
7.
FangZLiuHLiBChengY. Thermal comfort and skin temperature responses to the supplied air from personal air nozzles in aircraft cabins. Indoor Built Environ2018; 27(6): 831–845.
8.
ItoK. Toward the development of an in silico human model for indoor environmental design. Proc Japan Acad Ser B2016; 92(7): 185–203.
9.
WangZYuHLuoMWangZZhangHJiaoY. Predicting older people's thermal sensation in building environment through a machine learning approach: modelling, interpretation, and application. Build Environ2019; 161: 106231.
10.
WuYCaoB. Recognition and prediction of individual thermal comfort requirement based on local skin temperature. J Build Eng2022; 49: 104025.
11.
LanLXiaLTangJWyonDPLiuH. Mean skin temperature estimated from 3 measuring points can predict sleeping thermal sensation. Build Environ2019; 162: 106292.
12.
ChoiJHLoftnessV. Investigation of human body skin temperatures as a bio-signal to indicate overall thermal sensations. Build Environ2012; 58: 258–269.
13.
LiXChenQ. Development of a novel method to detect clothing level and facial skin temperature for controlling HVAC systems. Energy Build2021; 239(3): 110859.
14.
ZhaoQLianZLaiD. Thermal comfort models and their developments: a review. Energy Built Environ2021; 2(1): 21–33.
15.
LiBLiWLiuHYaoRTanHJingSMaX. Physiological expression of human thermal comfort to indoor operative temperature in the non-HVAC environment. Indoor Built Environ2010; 19(2): 221–229.
16.
QiaoYGaoXLiaoWChenD. Assessment of dynamic cognitive performance under different thermal conditions by multiple physiological signals. J Build Eng2024; 89: 109325.
17.
SongWZhongFCalautitJKLiJ. Exploring the role of skin temperature in thermal sensation and thermal comfort: a comprehensive review. Energy Built Environ2025; 6(4): 762–781.
18.
BaeCLeeHChunC. Predicting indoor thermal sensation for the elderly in welfare centres in Korea using local skin temperatures. Indoor Built Environ2017; 26(8): 1155–1167.
19.
MetzmacherHWolkiDSchmidtCFrischJvan TreeckC. Real-time human skin temperature analysis using thermal image recognition for thermal comfort assessment. Energy Build2018; 158: 1063–1078.
20.
ChaudhuriTZhaiDSohYCLiHXieL. Thermal comfort prediction using normalized skin temperature in a uniform built environment. Energy Build2018; 159: 426–440.
21.
ZeilerWVeselyMVissersDLiR. Thermal response of different body parts: the fingertip as control sensor for personalized heating. Energy Procedia2015; 78: 2766–2771.
22.
YanYLanLGongPGuoCHouZ. Association between bedroom environment and sleep quality of older adults: a winter field study. J Build Eng2025; 99: 111497.
23.
AryalABecerik-GerberB. A comparative study of predicting individual thermal sensation and satisfaction using wrist-worn temperature sensor, thermal camera and ambient temperature sensor. Build Environ2019; 160: 106223.
24.
GhahramaniACastroGBecerik-GerberBYuX. Infrared thermography of human face for monitoring thermoregulation performance and estimating personal thermal comfort. Build Environ2016; 109: 1–11.
25.
ChaudhuriTSohYCLiHXieL. Machine learning driven personal comfort prediction by wearable sensing of pulse rate and skin temperature. Build Environ2019; 170: 106615.
26.
ShanCHuJWuJZhangADingGXuLX. Towards non-intrusive and high accuracy prediction of personal thermal comfort using a few sensitive physiological parameters. Energy Build2020; 207: 109594.
27.
Arakawa MartinsLSoebartoVWilliamsonT. Performance evaluation of personal thermal comfort models for older people based on skin temperature, health perception, behavioural and environmental variables. J Build Eng2022; 51: 104357.
28.
FengYWangJGhaeiliNJaoYObonyoEAPavlakG. Exploring an occupant-involved closed-loop wearable sensing system and online tuning for individualized thermal preference. Energy Built Environ2025; In press. DOI: 10.1016/j.enbenv.2025.02.001.
29.
LiWZhangJZhaoTLiangR. Experimental research of online monitoring and evaluation method of human thermal sensation in different active states based on wristband device. Energy Build2018; 173: 613–622.
30.
LiWZhangJZhaoT. Indoor thermal environment optimal control for thermal comfort and energy saving based on online monitoring of thermal sensation. Energy Build2019; 197: 57–67.
31.
WangDZhangHArensEHuizengaC. Observations of upper-extremity skin temperature corresponding overall-body thermal sensations and comfort. Build Environ2007; 42(12): 3933–3943.
32.
LiKNieTLiuWLiuYLaiD. A machine learning approach to predict outdoor thermal comfort using local skin temperatures. Sustain Cities Soc2020; 59: 102216.
33.
OmidvarAKimJ. A novel theoretical model for predicting the individuals’ thermal sensations based on air temperature and biomarkers measured by wearable devices. Build Environ2023; 232: 110050.
34.
PiteràPCancelloRFontanaJMVermeFBouzigonRDuguéBBrunaniACapodaglioP. Sex and body mass index differences in changes in skin temperature after repeated sessions of whole-body cryostimulation. J Clin Med2024; 13(23): 7365.
35.
ZhaoXShiZChenQ. Inverse design of an indoor environment using a filter-based topology method with experimental verification. Indoor air2020; 30(6): 1–13.
36.
ZhaoXChenQ. Inverse design of indoor environment using an adjoint RNG k-s turbulence model. Indoor Air2019; 29(2): 320–330.
37.
Arakawa MartinsLSoebartoVWilliamsonT. A systematic review of personal thermal comfort models. Build Environ2022; 207: 108502.
38.
HommaHYakiyamaM. Examination of free convection around occupant’s body caused by its metabolic heat. ASHRAE Trans1988; 94(1): 104e24.
39.
ANSI/ASHRAE Standard 55-2020. Thermal Environmental Conditions for Human Occupancy. ASHRAE 2020; Atlanta, GA: Section 5.3.3.3.
40.
ZuoCLuoLLiuW. Effects of increased humidity on physiological responses, thermal comfort, perceived air quality, and Sick Building Syndrome symptoms at elevated indoor temperatures for subjects in a hot-humid climate. Indoor Air2021; 31(2): 524–540.
41.
CosmaACSimhaR. Thermal comfort modeling in transient conditions using real-time local body temperature extraction with a thermographic camera. Build Environ2018; 143: 36–47.
42.
SalehiBGhanbaranAHMaerefatM. Intelligent models to predict the indoor thermal sensation and thermal demand in steady state based on occupants’ skin temperature. Build Environ2020; 169: 106579.
43.
ZhangYZhouXZhengZOladokunMOFangZ. Experimental investigation into the effects of different metabolic rates of body movement on thermal comfort. Build Environ2020; 168: 106489.
44.
DowdySWeardenSChilkoD. Statistics for research. 3rd ed. Hoboken, NJ: Wiley-Interscience, 2004.
45.
LipczynskaASchiavonSGrahamLT. Thermal comfort and self-reported productivity in an office with ceiling fans in the tropics. Build Environ2018; 135: 202–212.
46.
KimJSchiavonSBragerG. Personal comfort models - a new paradigm in thermal comfort for occupant-centric environmental control. Build Environ2018; 132: 114–124.
47.
ChenQLangXLuSRehmanNUXieLSuH. Detection and root cause analysis of multiple plant-wide oscillations using multivariate nonlinear chirp mode decomposition and multivariate Granger causality. Comput Chem Eng2021; 147: 107231.
48.
ZhangSZhuN. Human thermal responses to temperature ramps in moderate built environments. Build Environ2022; 208: 108571.
49.
WillmottCMatsuuraK. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res2005; 30(1): 79–82.
50.
ZendehboudiAHosseiniSH. Modeling of the frost deposition by natural convection on horizontal ultra-low-temperature surfaces. J Therm Anal Calorim2019; 137: 2029–2043.
51.
RomanovskyA. Skin temperature: its role in thermoregulation. Acta Physiol2014; 210(3): 498–507.
52.
GamboaPVarandasRMrotzeckKPlacidoHQuaresmaC. Electrodermal activity analysis at different body locations. Sensors2025; 25(6): 1762.
53.
ZhangHXieXHongSLvH. Impact of metabolism and the clothing thermal resistance on inpatient thermal comfort. Energy Built Environ2021; 2(2): 223–232.
54.
PantanowitzACohenEGradidgePCrowtherNJAharonsonVRosmanBRubinDM. Estimation of body mass index from photographs using deep convolutional neural networks. Informatics Med Unlocked2021; 26: 100727.
55.
World Health Organization. Obesity: preventing and managing the global epidemic: report of a WHO consultation. Geneva: World Health Organization, 2000.
56.
SpeakmanJ. Obesity and thermoregulation. HCN2018; 156: 431–443.
57.
Herrera-GarcíaAPérez-MendozaMArellanes-LiceaEDCGasca-MartínezDCarmona-CastroADíaz-MuñozMMiranda-AnayaM. Obesity in male volcano mice Neotomodon Alstoni affects the daily rhythm of metabolism and thermoregulation. Front Nutr2022; 9: 963804.
58.
XuXZhangHWuGLianZXuH. Sex differences in body temperature and thermal perception under stable and transient thermal environments. Sci Total Environ2024; 951: 175323.
59.
DebrayASardarSDeshayesTAMornasAOubouchouKOuazaaYGagnonD. Sex-related differences in temperature regulation during heat stress from childhood to older age. Auton Neurosci2025; 260: 103294.
60.
ParchamiMNazarianNHartMALiuSMartilliA. Can your smartwatch measure ambient air temperature? Environ. Res Lett2025; 20: 064016.
61.
LaiDZhouXChenQ. Modelling dynamic thermal sensation of human subjects in outdoor environments. Energy Build2017; 149: 16–25.
62.
MarcoulidesKMRaykovT. Evaluation of variance inflation factors in regression models using latent variable modeling methods. Educ Psychol Meas2019; 79: 874–882.
63.
LiJPantelicJMerchantCBChenKWIzuharaIYukiRMeggersFMSchiavonS. Comparison of the environmental, energy, and thermal comfort performance of air and radiant cooling systems in a zero-energy office building in Singapore. Energy Build2024; 318: 114487.
64.
EvrenFBiswasSGravesR. Measuring mean radiant temperature for indoor comfort assessment using low-resolution optical sensors. Nat Commun2025; 16: 1215.
