A contactless predictive model of thermal sensation for enhancing cognitive performance via facial skin temperature
Year: 2025
Type: article
Abstract: 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.
Source: Indoor and Built Environment
Author: Dongwoo (Jason) Yeom
Institution: Arizona State University
Language: English
Subfield: Building and Construction
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4410132383