This study investigated the relationship between indoor temperature, facial skin temperature, thermal sensation and cognitive performance in an office environment, aiming to develop a contactless predictive model for thermal sensation to optimize cognitive performance. Using thermographic imaging, facial skin temperature from four locations (forehead, nose, cheek and chin) were collected, while cognitive performance was assessed through the Operation Span Task (OSPAN) and Psychomotor Vigilance Task (PVT). Three machine learning algorithms (J48 Decision Tree, Logistic Model Tree and Random Forest) were applied to construct thermal sensation predictive models based on these data. Results demonstrated that facial skin temperatures are significantly correlated with cognitive performance, validating that factors such as facial skin temperature, indoor temperature and gender can predict thermal sensation with high accuracy (93.96% to 98.84%), depending on the algorithm and cognitive function. Findings indicate that a slightly cool environment could benefit response-related tasks (PVT) for both genders, while slightly warmer settings could optimize working memory tasks (OSPAN) for females, with a cool environment favoured for males. These insights underscore the potential for developing a contactless, personalized thermal management system that enhances cognitive function and reduces energy consumption by fine-tuning indoor climates to occupants’ needs, marking a step forward in occupant-centred building design.
KlepeisNENelsonWCOttWRRobinsonJTsangASwitzerPBeharJHernSEngelmannW. The national human activity pattern survey (NHAPS): a resource for assessing exposure to environmental pollutants. J Expo Anal Environ Epidemiol2001; 11: 231–252.
2.
LiDMenassaCCKamatVRStudentPD. A Personalized HVAC Control Smartphone Application Framework for Improved Human Health and Well-Being. In: Proceedings of Computing in Civil Engineering 2017; Seattle, 25–27 June 2017, pp82–90. ASCE.
3.
KangSOuDMakCM. The impact of indoor environmental quality on work productivity in university open-plan research offices. Build Environ2017; 124: 78–89.
4.
WittersehTWyonDPClausenG. The effects of moderate heat stress and open-plan office noise distraction on SBS symptoms and on the performance of office work. Indoor Air2004; 14: 30–40.
5.
ChoiJHYeomD. Investigation of the relationships between thermal sensations of local body areas and the whole body in an indoor built environment. Energy Build2017; 149: 204–215.
6.
LanLLianZ. Use of neurobehavioral tests to evaluate the effects of indoor environment quality on productivity. Build Environ2009; 44: 2208–2217.
7.
YeomDJDeloguF. Local body skin temperature-driven thermal sensation predictive model for the occupant’s optimum productivity. Build Environ2021; 204: 108196.
8.
YeomDJDeloguF. Thermal preferences and cognitive performance estimation via user’s physiological responses. In: ARCC Conference Repository 2019; 7(1):375–384.
9.
ChoiJLoftnessVAzizA. Post-occupancy evaluation of 20 office buildings as basis for future IEQ standards and guidelines. Energy Build2012; 46: 167–175.
10.
ChoiJHYeomD. Development of the data-driven thermal satisfaction prediction model as a function of human physiological responses in a built environment. Build Environ2019; 150: 206–218.
11.
Ashrae Standard 55–2023. Thermal Environmental Conditions for Human Occupancy. Atlanta: ASHRAE 2023.
12.
ParkinsonTSchiavonSKimJBettiG. Common sources of occupant dissatisfaction with workspace environments in 600 office buildings. Buildings and Cities2023; 4: 17–35.
13.
ChoiJHYeomD. Study of data-driven thermal sensation prediction model as a function of local body skin temperatures in a built environment. Build Environ2017; 121: 130–147.
14.
MoonJW. Performance of ANN-based predictive and adaptive thermal-control methods for disturbances in and around residential buildings. Build Environ2012; 48: 15–26.
15.
HoytTLeeKZhangHArensEWebsterT. Energy Savings from Extended Air Temperature Setpoints and Reductions in Room Air Mixing. In: Proceedings of the international conference on environmental ergonomics 2009. Boston, 2–7 August 2009, https://escholarship.org/uc/item/289d7xj.
16.
DuCLiBLiuHJiYYaoRYuW. Quantification of personal thermal comfort with localized airflow system based on sensitivity analysis and classification tree model. Energy Build2019; 194: 1–11.
17.
KimJBaumanFRafteryPArensEZhangHFierroGAndersenMCullerD. Occupant comfort and behavior: high-resolution data from a 6-month field study of personal comfort systems with 37 real office workers. Build Environ2019; 148: 348–360.
18.
WangZYangYLiuCZhouFHaoH. Human thermal comfort model and evaluation on building thermal environment. Energy Build2024; 323: 114796.
19.
FreireRZOliveiraGHCMendesN. Predictive controllers for thermal comfort optimization and energy savings. Energy Build2008; 40: 1353–1365.
20.
LicinaDYildirimS. Occupant satisfaction with indoor environmental quality, sick building syndrome (SBS) symptoms and self-reported productivity before and after relocation into WELL-certified office buildings. Build Environ2021; 204: 108183.
21.
GoyalSBarooahPMiddelkoopT. Experimental study of occupancy-based control of HVAC zones. Appl Energy2015; 140: 75–84.
22.
ZhaoQZhaoYWangFWangJJiangYZhangF. A data-driven method to describe the personalized dynamic thermal comfort in ordinary office environment: from model to application. Build Environ2014; 72: 309–318.
23.
GuptaSKAtkinsonSO’BoyleIDrogoJKarKMishraSWenJ. BEES: real-time occupant feedback and environmental learning framework for collaborative thermal management in multi-zone, multi-occupant buildings. Energy Build2016; 125: 142–152.
24.
LiWZhangJZhaoT. Indoor thermal environment optimal control for thermal comfort and energy saving based on online monitoring of thermal sensation. Energy Build2019; 197: 57–67.
25.
KimJZhouYSchiavonSRafteryPBragerG. Personal comfort models: predicting individuals’ thermal preference using occupant heating and cooling behavior and machine learning. Build Environ2018; 129: 96–106.
26.
VeselýMZeilerW. Personalized conditioning and its impact on thermal comfort and energy performance - A review. Renewable and Sustainable Energy Reviews2014; 34: 401–408.
27.
ZhangHYangXZhengWYouSZhengXYeT. The CPMV* for assessing indoor thermal comfort and thermal acceptability under global solar radiation in transparent envelope buildings. Energy Build2020; 225: 110306.
28.
YangCYinTFuM. Study on the allowable fluctuation ranges of human metabolic rate and thermal environment parameters under the condition of thermal comfort. Build Environ2016; 103: 155–164.
29.
IndragantiMRaoKD. Effect of age, gender, economic group and tenure on thermal comfort: A field study in residential buildings in hot and dry climate with seasonal variations. Energy Build2010; 42(3): 273–281.
30.
KarjalainenS. Gender differences in thermal comfort and use of thermostats in everyday thermal environments. Build Environ2007; 42: 1594–1603.
31.
WuYLiuHLiBKosonenRWeiSJokisaloJChengY. Individual thermal comfort prediction using classification tree model based on physiological parameters and thermal history in winter. Build Simul2021; 14: 1651–1665.
32.
DaiCZhangHArensELianZ. Machine learning approaches to predict thermal demands using skin temperatures: steady-state conditions. Build Environ2017; 114: 1–10.
33.
LiuSSchiavonSDasHPJinMSpanosCJ. Personal thermal comfort models with wearable sensors. Build Environ2019; 162: 106281.
34.
ShanCHuJWuJZhangADingGXuLX. Towards non-intrusive and high accuracy prediction of personal thermal comfort using a few sensitive physiological parameters. Energy Build2020; 207: 109594.
35.
WuYLiuHLiBJokisaloJKosonenRChengYZhaoWYuanX. Evaluation and modification of the weighting formulas for mean skin temperature of human body in winter conditions. Energy Build2020; 229: 110390.
36.
ChaudhuriTSohYCLiHXieL. Machine learning driven personal comfort prediction by wearable sensing of pulse rate and skin temperature. Build Environ2020; 170: 106615.
37.
YangBLiXHouYMeierAChengXChoiJWangFWangHWagnerAYanDLiAOlofssonTLiH. Non-invasive (non-contact) measurements of human thermal physiology signals and thermal comfort/discomfort poses -A review. Energy Build2020; 224: 110261.
38.
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.
39.
TakadaSMatsumotoSMatsushitaT. Prediction of whole-body thermal sensation in the non-steady state based on skin temperature. Build Environ2013; 68: 123–133.
40.
SalehiBGhanbaranAHMaerefatM. Intelligent models to predict the indoor thermal sensation and thermal demand in steady state based on occupants’ skin temperature. Build Environ2020; 169: 106579.
41.
LanLXiaLTangJWyonDPLiuH. Mean skin temperature estimated from 3 measuring points can predict sleeping thermal sensation. Build Environ2019; 162: 106292.
42.
ChoiJKMikiKSagawaSShirakiK. Evaluation of mean skin temperature formulas by infrared thermography. Int J Biometeorol1997; 41: 68–75.
43.
ChengXYangBOlofssonTLiuGLiH. A pilot study of online non-invasive measuring technology based on video magnification to determine skin temperature. Build Environ2017; 121: 1–10.
44.
ChengXYangBTanKIsakssonELiLHedmanAOlofssonTLiH. A contactless measuring method of skin temperature based on the skin sensitivity index and deep learning. Applied Sciences (Switzerland)2019; 9: 1–13.
45.
ChengXYangBHedmanAOlofssonTLiHVan GoolL. NIDL: a pilot study of contactless measurement of skin temperature for intelligent building. Energy Build2019; 198: 340–352.
46.
ChaudhuriTSohYCLiHXieL. A feedforward neural network based indoor-climate control framework for thermal comfort and energy saving in buildings. Appl Energy2019; 248: 44–53.
47.
NižetićSPivacNZankiVPapadopoulosAM. Application of smart wearable sensors in office buildings for modelling of occupants’ metabolic responses. Energy Build2020; 226: 110399.
48.
PengYNagyZSchlüterA. Temperature-preference learning with neural networks for occupant-centric building indoor climate controls. Build Environ2019; 154: 296–308.
49.
KimTLimSYoonSGYeomDJ. Pupil size and gender-driven occupant’s productivity predictive model for diverse indoor lighting conditions in the office environment. Build Environ2022; 226: 109673.
50.
LiQYHanJLuL. A random forest classification algorithm based personal thermal sensation model for personalized conditioning system in office buildings. Computer Journal2021; 64: 500–508.
51.
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.
52.
YanHJiGCaoSZhangB. Developing an integrated prediction model for daylighting, thermal comfort, and energy consumption in residential buildings based on the stacking ensemble learning algorithm. Build Simul2024; 17: 2125–2143.
53.
UpasaniNGuerra-SantinOMohammadiM. Developing building-specific, occupant-centric thermal comfort models: a methodological approach. Journal of Building Engineering2024; 95: 110281.
54.
SunRXuSHanYZhuangDYanBSunC. Exploring impacts of thermal and lighting conditions on office workers’ subjective evaluations, cognitive performance and EEG features in multi-person offices. J Buil Eng2024; 95: 110170.
55.
CosmaACSimhaR. Machine learning method for real-time non-invasive prediction of individual thermal preference in transient conditions. Build Environ2019; 148: 372–383.
56.
LiLZhangC. Personalized thermal demand prediction algorithm based on wrist temperature and heart beat. ASHRAE Trans2019; 125: 181–188.
57.
CosmaACSimhaR. Thermal comfort modelling in transient conditions using real-time local body temperature extraction with a thermographic camera. Build Environ2018; 143: 36–47.
58.
LuSWangWWangSHameenEC. Thermal comfort-based personalized models with non-intrusive sensing technique in office buildings. Appl Sci (Switzerland)2019; 9: 1768.
59.
LiDMenassaCCKamatVR. Non-intrusive interpretation of human thermal comfort through analysis of facial infrared thermography. Energy Build2018; 176: 246–261.
60.
JiaMChoiJHLiuHSusmanG. Development of facial-skin temperature driven thermal comfort and sensation modelling for a futuristic application. Build Environ2022; 207: 108479.
61.
LiKLiWLiuFXueW. Non-invasive human thermal comfort assessment based on multiple angle/distance facial key-region temperatures recognition. Build Environ2023; 246: 110956.
62.
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.
63.
MetzmacherHWölkiDSchmidtCFrischJvan TreeckC. Real-time human skin temperature analysis using thermal image recognition for thermal comfort assessment. Energy Build2018; 158: 1063–1078.
64.
BaiYLiuLLiuKYuSShenYSunD. Non-intrusive personal thermal comfort modeling: a machine learning approach using infrared face recognition. Build Environ2024; 247: 111033.
65.
JeoungJJungSHongTLeeMKooC. Thermal comfort prediction based on automated extraction of skin temperature of face component on thermal image. Energy Build2023; 298: 113495.
66.
IntharachathornKJareemitDWatcharapinchaiS. Potential use of an extended-distance thermal imaging camera for the assessment of thermal comfort in multi-occupant spaces. Build Environ2023; 246: 110949.
67.
LyuJDuHZhaoZShiYWangBLianZ. Where should the thermal image sensor of a smart A/C look?-occupant thermal sensation model based on thermal imaging data. Build Environ2023; 239: 110405.
68.
HeYZhangHArensEMerrittAHuizengaCLevinsonRWangAGhahramaniAAlvarez-SuarezA. Smart detection of indoor occupant thermal state via infrared thermography, computer vision, and machine learning. Build Environ2023; 228: 109811.
69.
SoleimanijavidAKonstantzosI. Non-intrusive infrared facial thermography for personal thermal sensation prediction models: a field study. Build Environ2025; 271: 112606.
70.
YangBChengXDaiDOlofssonTLiHMeierA. Real-time and contactless measurements of thermal discomfort based on human poses for energy efficient control of buildings. Build Environ2019; 162: 106284.
71.
MiuraJDemuraMNishiKOishiS. Thermal comfort measurement using thermal-depth images for robotic monitoring. Pattern Recognit Lett2019; 137: 108–113.
72.
GhahramaniACastroGKarvighSABecerik-GerberB. Towards unsupervised learning of thermal comfort using infrared thermography. Appl Energy2018; 211: 41–49.
73.
CosmaACSimhaR. Using the contrast within a single face heat map to assess personal thermal comfort. Build Environ2019; 160: 106163.
74.
LanLLianZPanL. The effects of air temperature on office workers’ well-being, workload and productivity-evaluated with subjective ratings. Appl Ergon2010; 42: 29–36.
75.
LanLWargockiPLianZ. Thermal effects on human performance in office environment measured by integrating task speed and accuracy. Appl Ergon2014; 45: 490–495.
76.
WangHLiuL. Experimental investigation about effect of emotion state on people’s thermal comfort. Energy Build2020; 211: 109789.
77.
CuiWCaoGParkJHOuyangQZhuY. Influence of indoor air temperature on human thermal comfort, motivation and performance. Build Environ2013; 68: 114–122.
78.
WangXLiDMenassaCCKamatVR. Investigating the effect of indoor thermal environment on occupants’ mental workload and task performance using electroencephalogram. Build Environ2019; 158: 120–132.
79.
Tanabe S ichi, Haneda M, Nishihara N. Workplace productivity and individual thermal satisfaction. Build Environ2015; 91: 42–50.
80.
KimHHongTKimJYeomS. A psychophysiological effect of indoor thermal condition on college students’ learning performance through EEG measurement. Build Environ2020; 184: 107223.
81.
SunCHanYLuoLSunH. Effects of air temperature on cognitive work performance of acclimatized people in severely cold region in China. Indoor and Built Environment2020; 30: 816–837.
82.
HaoSWangFGuanJTangKWangX. Skin temperature indexes to evaluate thermal sensation and cognitive performance in hot environments. Build Environ2023; 242: 110540.
83.
TianXFangLLiuW. The influencing factors and an error correction method of the use of infrared thermography in human facial skin temperature. Build Environ2023; 244: 110736.
84.
GutiérrezÁBlancoPRuizVChatzigeorgiouCOreguiXAlvarezMNavarroSFeidakisMAzpirozIIzquierdoGLarraga-GarciaBKasnesisPOlaizolaIAlvarezF. Biosignals monitoring of first responders for cognitive load estimation in real-time operation. Applied Sciences (Switzerland)2023; 13: 7368.
85.
CardoneDPerpetuiniDFilippiniCManciniLNoccoSTrittoMRinellaSGiacobbeAFallicaGRicciFGallinaSMerlaA. Classification of Drivers’ mental workload levels: comparison of machine learning methods based on ECG and infrared thermal signals. Sensors2022; 22: 7300.
86.
HuSMaedaT. Productivity and physiological responses during exposure to varying air temperatures and clothing conditions. Indoor Air2020; 30: 251–263.
87.
LanLXiaLHejjoRWyonDPWargockiP. Perceived air quality and cognitive performance decrease at moderately raised indoor temperatures even when clothed for comfort. Indoor Air2020; 30: 841–859.
88.
LanLWargockiPWyonDPLianZ. Effects of thermal discomfort in an office on perceived air quality, SBS symptoms, physiological responses, and human performance. Indoor Air2011; 21: 376–390.
89.
TurnerMLEngleRW. Is working memory capacity task dependent?J Mem Lang1989; 28: 127–154.
90.
BaddeleyA. Working memory. Science1992; 255: 556–559.
91.
LittleDRLewandowskySCraigS. Working memory capacity and fluid abilities: the more difficult the item, the more is better. Sec. Cognitive Science2014; 5: 239.
92.
RomanovskyAA. Skin temperature: its role in thermoregulation. Acta Physiologica2014; 210: 498–507.
93.
IwaseSCuiJWallinBGKamiyaAManoT. Effects of increased ambient temperature on skin sympathetic nerve activity and core temperature in humans. Neurosci Lett2002; 327: 37–40.
