Abstract
Perception can influence individuals’ behaviour and attitude affecting responses and compliance to precautionary measures. This study aims to investigate the performance of methods for thermal sensation and comfort prediction. Four machine learning algorithms (MLA), artificial neural networks, random forest (RF), support vector machines, and linear discriminant analysis were examined and compared to the physiologically equivalent temperature (PET). Data were collected in field surveys conducted in outdoor sites in Cyprus. The seven- and nine-point assessment scales of thermal sensation and a two-point scale of thermal comfort were considered. The models of MLA included meteorological and physiological features. The results indicate RF as the best MLA applied to the data. All MLA outperformed PET. For thermal sensation, the lowest prediction error (1.32 points) and the highest accuracy (30%) were found in the seven-point scale for the feature vector consisting of air temperature, relative humidity, wind speed, grey globe temperature, clothing insulation, activity, age, sex, and body mass index. The accuracy increased to 63.8% when considering prediction with at most one-point difference from the correct thermal sensation category. The best performed feature vector for thermal sensation also produced one of the best models for thermal comfort yielding an accuracy of 71% and an F-score of 0.81.
Similar content being viewed by others
References
American Society of Heating Refrigerating and Air-Conditioning Engineers (2013) Thermal environmental conditions for human occupancy. Atlanta, Georgia
Chai Q, Wang H, Zhai Y, Yang L (2020) Using machine learning algorithms to predict occupants’ thermal comfort in naturally ventilated residential buildings. Energy Build 217:109937
Chan SY, Chau CK (2019) Development of artificial neural network models for predicting thermal comfort evaluation in urban parks in summer and winter. Build Environ 164:106364
Choi JH, Yeom D (2017) Study of data-driven thermal sensation prediction model as a function of local body skin temperatures in a built environment. Build Environ 121:130–147
Cortez P, Cerdeira A, Almeida F et al (2009) Modeling wine preferences by data mining from physicochemical properties. Decis Support Syst 47:547–553
de Freitas CR, Grigorieva EA (2015) A comprehensive catalogue and classification of human thermal climate indices. Int J Biometeorol 59:109–120
de Freitas CR, Grigorieva EA (2017) A comparison and appraisal of a comprehensive range of human thermal climate indices. Int J Biometeorol 61:487–512
Environmental Protection Agency (EPA) (2021) Climate Change. https://www.epa.gov/climate-change. Accessed 7 Jun 2022
European Commission (EC) (2022) Consequences of climate change. https://ec.europa.eu/clima/climate-change_en. Accessed 7 Jun 2022
Farhan AA, Pattipati K, Wang B, Luh P (2015) Predicting individual thermal comfort using machine learning algorithms. IEEE Int Conf Autom Sci Eng 2015-Octob:708–713
Fawagreh K, Gaber MM, Elyan E (2014) Random forests: from early developments to recent advancements. Syst Sci Control Eng 2:602–609
Gasparrini A, Guo Y, Hashizume M et al (2015) Mortality risk attributable to high and low ambient temperature: a multicountry observational study. Lancet 386:369–375
ISO 10551 (2001) Ergonomics of the thermal environment assessment of the influence of the thermal environment using subjective judgement scales. Geneva, Switzerland
ISO 7726 (2001) Ergonomics of the thermal environment – instruments for measuring physical quantities. Geneva, Switzerland
ISO 9920 (2007) Ergonomics—estimation of the thermal characteristics of a clothing ensemble. Geneva, Switzerland
Kariminia S, Shamshirband S, Motamedi S et al (2016) A systematic extreme learning machine approach to analyze visitors’ thermal comfort at a public urban space. Renew Sustain Energy Rev 58:751–760
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations. San Diego, United States
Koelblen B, Psikuta A, Bogdan A et al (2018) Thermal sensation models: validation and sensitivity towards thermo-physiological parameters. Build Environ 130:200–211
Lai D, Zhou X, Chen Q (2017) Modelling dynamic thermal sensation of human subjects in outdoor environments. Energy Build 149:16–25
Li QY, Han J, Lu L (2021) A random forest classification algorithm based personal thermal sensation model for personalized conditioning system in office buildings. Comput J 64:500–508
Lin T, Matzarakis A (2008) Tourism climate and thermal comfort in Sun Moon. Int J Biometeorol 52:281–290
Liu K, Nie T, Liu W et al (2020) A machine learning approach to predict outdoor thermal comfort using local skin temperatures. Sustain Cities Soc 59:102216
Loh WY, Shih YS (1997) Split selection methods for classification trees. Stat Sin 7:815–840
Luo M, Xie J, Yan Y et al (2020) Comparing machine learning algorithms in predicting thermal sensation using ASHRAE Comfort Database II. Energy Build 210:109776
MathWorks Treebager Class (2022) Bag of decision trees - MATLAB. https://www.mathworks.com/help/stats/treebagger-class.html. Accessed 3 Jun 2022
Matzarakis A, Rutz F, Mayer H (2007) Modelling radiation fluxes in simple and complex environments—application of the RayMan model. Int J Biometeorol 51:323–334
Matzarakis A, Rutz F, Mayer H (2010) Modelling radiation fluxes in simple and complex environments: basics of the RayMan model. Int J Biometeorol 54:131–139
Mayer H, Höppe P (1987) Thermal comfort of man in different urban environments. Theor Appl Climatol 38:43–49
NASA Global Climate Change (2021) Effects | facts – climate change: vital signs of the planet. https://climate.nasa.gov/effects/. Accessed 7 Jun 2022
Nikolopoulou M, Steemers K (2003) Thermal comfort and psychological adaptation as a guide for designing urban spaces. Energy Build 35:95–101
Oshiro TM, Perez PS, Baranauskas JA (2012) How many trees in a random forest?. In: Perner P (ed) Machine learning and data mining in pattern recognition. MLDM 2012. Lecture Notes in Computer Science. Springer Berlin Heidelberg, pp 154–168
Pantavou K, Giallouros G, Lykoudis S, Nikolopoulos G (2021) Assessment of thermal indices applicability in Cyprus. In: 17th International Conference on Environmental Science and Technology. Athens, Greece
Pantavou K, Koletsis I, Lykoudis S et al (2020) Native influences on the construction of thermal sensation scales. Int J Biometeorol 64:1497–1508
Pantavou K, Lykoudis S, Michael N et al (2020) Thermal sensation and indices in the urban outdoor hot Mediterranean environment of Cyprus. Theor Appl Climatol 140:1315–1329
Pantavou K, Lykoudis S, Nikolopoulou M, Tsiros IX (2018) Thermal sensation and climate: a comparison of UTCI and PET thresholds in different climates. Int J Biometeorol 62:1695–1708
Pantavou K, Psiloglou B, Lykoudis S et al (2018) Perceived air quality and particulate matter pollution based on field survey data during a winter period. Int J Biometeorol 62:2139–2150
Pantavou K, Santamouris M, Asimakopoulos D, Theoharatos G (2013) Evaluating the performance of bioclimatic indices on quantifying thermal sensation for pedestrians. Adv Build Energy Res 7:170–185
Pantavou K, Santamouris M, Asimakopoulos D, Theoharatos G (2014) Empirical calibration of thermal indices in an urban outdoor Mediterranean environment. Build Environ 80:283–292
Pantavou K, Theoharatos G, Santamouris M, Asimakopoulos D (2013) Outdoor thermal sensation of pedestrians in a Mediterranean climate and a comparison with UTCI. Build Environ 66:82–95
Parsons K (2010) Thermal comfort in buildings | Multi Comfort - Saint-Gobain. Mater energy Effic Therm Comf Build 127–147
Peel MC, Finlayson BL, McMahon T (2007) Updated world map of the K¨ oppen-Geiger climate classificatio. Hydrol Earth Syst Sci 11:1633–1644
Potchter O, Cohen P, Lin TP, Matzarakis A (2018) Outdoor human thermal perception in various climates: A comprehensive review of approaches, methods and quantification. Sci Total Environ 631–632:390–406
Shahzad S, Brennan J, Theodossopoulos D et al (2018) Does a neutral thermal sensation determine thermal comfort? Build Serv Eng Res Technol 39:183–195
Statistical Service (2020) Annual publications: demographic statistics - 2019. https://www.cystat.gov.cy/en/PublicationList?s=46. Accessed 14 Apr 2022
Wang Z, Yu H, Luo M et al (2019) Predicting older people’s thermal sensation in building environment through a machine learning approach: modelling, interpretation, and application. Build Environ 161:106231
World Health Organization (WHO) (2022) Heatwaves. https://www.who.int/health-topics/heatwaves#tab=tab_1. Accessed 7 Jun 2022
World Meteorological Organization (WMO) (2020) 2020 closes a decade of exceptional heat | World Meteorological Organization. https://public.wmo.int/en/media/news/2020-closes-decade-of-exceptional-heat. Accessed 7 Jun 2022
Wu Z, Li N, Peng J et al (2018) Using an ensemble machine learning methodology-Bagging to predict occupants’ thermal comfort in buildings. Energy Build 173:117–127
Yaglou CP, Minard D (1957) Control of heat casualties at military training centers. AMA Arch Intern Med 16:302–316
Funding
This research was co-funded by the European Regional Development Fund and the Republic of Cyprus through the Research and Innovation Foundation (project: EXCELLENCE/1216/0007).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
This study was performed in line with the principles of the Declaration of Helsinki. The protocol and the questionnaire used in the field surveys were approved by the Cyprus National Bioethics Committee (EEBE/EΠ2018/48).
Competing interests
The authors declare no competing interests.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Pantavou, K., Delibasis, K.K. & Nikolopoulos, G.K. Machine learning and features for the prediction of thermal sensation and comfort using data from field surveys in Cyprus. Int J Biometeorol 66, 1973–1984 (2022). https://doi.org/10.1007/s00484-022-02333-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00484-022-02333-y