Hybrid personalized thermal comfort model based on wrist skin temperature

Indoor thermal comfort plays a crucial role in enhancing the quality of life in residential and work environments. However, existing thermal comfort models often rely on complex measurements or require a large number of personal thermal votes, which limits their practical application. To address these challenges, this study develops a hybrid thermal comfort model aimed at reducing the measurement burden and personal response while improving the accuracy of personalized thermal comfort prediction. The proposed hybrid model combines a mathematical model with machine learning techniques, integrating the generalization ability of the mathematical model and the self-learning capabilities of machine learning. Data were collected from an experiment conducted in the climate controlled chamber in an office building with 12 subjects. By monitoring only wrist skin temperature, indoor air temperature, and their temporal variations, the proposed model significantly simplifies the measurement. In the absence of available training data, the mathematical model can be used independently, improving prediction accuracy by 21.11% on median and up to 44.45% over the PMV model. In a 5-fold cross-validation with 45 data points per subject, the hybrid model outperforms the standalone machine learning model by up to 24.45%. The model demonstrates robust performance with limited training data across various metrics and scenarios, highlighting its potential for practical application in building environments. • Proposes mathematical model with 9 adaptive parameters for personalization. • Mathematical model outperforms PMV model by 21.11% accuracy without training data. • Simplifies measurement by requiring only wrist skin temperature and indoor air temperature. • Proposes a hybrid model combining mathematical model and machine learning. • Improves prediction accuracy by up to 24.45% compared to standalone ML models.