From Thermal Preference Prediction to Adaptive Thermal Intervention: A Reinforcement Learning Approach Using Physiological and Environmental Sensing
Researchers have developed a system that uses sensors to monitor an individual's physiological responses and environmental conditions to provide personalized thermal comfort. The approach is based on reinforcement learning, which allows the system to adapt its decisions in real-time. This could lead to more efficient use of energy in buildings by adjusting heating and cooling systems according to individual needs.
Researchers have developed a system that uses sensors to monitor an individual's physiological responses and environmental conditions to provide personalized thermal comfort. The approach is based on reinforcement learning, which allows the system to adapt its decisions in real-time. This could lead to more efficient use of energy in buildings by adjusting heating and cooling systems according to individual needs.
---
Why it matters: This matters because it has the potential to improve occupant wellbeing and reduce energy consumption in buildings. The ability to tailor thermal comfort to individual physiological variability could also inform the development of more responsive building-control strategies.
Source: https://arxiv.org/abs/2608.20423
This article was originally published at: https://arxiv.org/abs/2608.20423