Personal thermal comfort models: A deep learning approach for predicting older people's thermal preference

Purpose: This 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/approach: Twenty-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. Findings: On 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/value: While 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.