Correlating Indoor Environmental Quality Parameters with Human Physiological Responses for Adaptive Comfort Control in Commercial Buildings

This study investigates the critical role of indoor environmental quality (IEQ) adaptations in influencing human physiological responses within commercial building settings. By integrating environmental engineering and human physiology, this research offers empirical insights into the relationship between IEQ modifications and occupant well-being, particularly in the context of energy performance and efficiency. This study examines correlations between human physiological responses and key IEQ components, including indoor air quality (IAQ), thermal comfort, lighting, and acoustics, using data collected from two office areas with 14 participants. Sensors tracked environmental parameters, while wearable devices monitored physiological responses. Cross-correlation analysis revealed significant relationships between physiological indicators and environmental factors, with indoor temperature, PM 2.5 , and relative humidity showing the strongest impacts on electrodermal activity, skin temperature, and stress levels, respectively ( p < 0.05). Furthermore, supervised machine learning techniques were employed to develop predictive models that evaluate IAQ and thermal comfort at both personal and general levels. Individual models achieved 84.76% accuracy for IAQ evaluation and 70.5% for thermal comfort prediction, outperforming the general model (69.7% and 64.3%, respectively). Males showed greater overall sensitivity to IEQ indicators, while females demonstrated higher sensitivity specifically to air quality and thermal comfort conditions. The findings underscore the potential of physiological signals to predict environmental satisfaction, providing a foundation for designing energy-efficient buildings that prioritize occupant health and comfort. This research bridges a critical gap in the literature by offering data-driven approaches to align sustainable building practices with human-centric needs. Future studies should expand participant diversity and explore broader demographics to enhance the robustness and applicability of predictive models.