Personal thermal comfort models: a deep learning approach for predicting older people’s thermal preference

Abstract

PurposeThis paper presents the development of personal thermal comfort models for older adults and assesses the models’ performance compared to aggregate approaches. This is necessary as individual thermal preferences can vary widely between older adults, and the use of aggregate thermal comfort models can result in thermal dissatisfaction for a significant number of older occupants. Personalised thermal comfort models hold the promise of a more targeted and accurate approach.Design/methodology/approachTwenty-eight personal comfort models have been developed, using deep learning and environmental and personal parameters. The data were collected through a nine-month monitoring study of people aged 65 and over in South Australia, who lived independently. Modelling comprised dataset balancing and normalisation, followed by model tuning to test and select the best hyperparameters’ sets. Finally, models were evaluated with an unseen dataset. Accuracy, Cohen’s Kappa Coefficient and Area Under the Receiver Operating Characteristic Curve (AUC) were used to measure models’ performance.FindingsOn average, the individualised models present an accuracy of 74%, a Cohen’s Kappa Coefficient of 0.61 and an AUC of 0.83, representing a significant improvement in predictive performance when compared to similar studies and the “Converted” Predicted Mean Vote (PMVc) model.Originality/valueWhile current literature on personal comfort models have focussed solely on younger adults and offices, this study explored a methodology for older people and their dwellings. Additionally, it introduced health perception as a predictor of thermal preference – a variable often overseen by architectural sciences and building engineering. The study also provided insights on the use of deep learning for future studies.

Enhanced Thermal Comfort Prediction Model by Addressing Outliers and Data Imbalance

“…Their results highlighted that Deep Neural Network (DNN) achieved the highest accuracy of 78.01%, outperforming traditional models like Gradient Boosting and PMV. Finally, a study by Martins et al, [46] in 2022 emphasized the role of downsampling to address data imbalance. Their model, which considered parameters like health perception, showed that a DNN with health perception could achieve an accuracy of up to 91.67%.…”

Guest editorial – Future construction: design solutions and approaches

“…Arakawa Martins et al (2022) concentrate on indoor spaces, where we spend over 90% of our time exploring thermal comfort conditions as one of the core components of Indoor Environmental Quality (IEQ). With attention to personalised thermal comfort models, the study explores older adults' thermal comfort preferences using deep learning approaches.…”