Heat Flux Sensing for Machine-Learning-Based Personal Thermal Comfort Modeling

Abstract

In recent years, physiological features have gained more attention in developing models of personal thermal comfort for improved and accurate adaptive operation of Human-In-The-Loop (HITL) Heating, Ventilation, and Air-Conditioning (HVAC) systems. Pursuing the identification of effective physiological sensing systems for enhancing flexibility of human-centered and distributed control, using machine learning algorithms, we have investigated how heat flux sensing could improve personal thermal comfort inference under transient ambient conditions. We have explored the variations of heat exchange rates of facial and wrist skin. These areas are often exposed in indoor environments and contribute to the thermoregulation mechanism through skin heat exchange, which we have coupled with variations of skin and ambient temperatures for inference of personal thermal preferences. Adopting an experimental and data analysis methodology, we have evaluated the modeling of personal thermal preference of 18 human subjects for well-known classifiers using different scenarios of learning. The experimental measurements have revealed the differences in personal thermal preferences and how they are reflected in physiological variables. Further, we have shown that heat exchange rates have high potential in improving the performance of personal inference models even compared to the use of skin temperature.

The field of human building interaction for convergent research and innovation for intelligent built environments

“…Internet of Things (IoT) provides a way to connect building operations such as security and access control, predictive maintenance, structural health, fire detection and so on 74 . Similarly, wearable sensors that measure physiological variables, such as skin temperature, perspiration rate, and heart rate, can assist in understanding human health and well-being related to engagement within built environments 31 , 75 . These methods rely on sensing technologies that provide robust data throughout daily activities that require the direct engagement of the human or building.…”

Personal thermal comfort models: a deep learning approach for predicting older people’s thermal preference

“…, 2020), for instance, has been highlighted as a promising option for individual data collection, leveraging integrated data acquisition techniques that can potentially replace occupant survey feedback as proxy for thermal comfort. In addition, there is an increasing body of research focusing on personal comfort models driven by physiological variables, such as skin temperature or heart rate (Jung et al. , 2019; Lee and Ham, 2020; Shan et al.…”

“…The latter includes more interpretable approaches such as Classification Trees (Aryal and Becerik-Gerber, 2020), or less transparent but relatively more accurate techniques such as Gaussian Process Classification (Guenther and Sawodny, 2019; Fay et al. , 2017), Gradient Boosting Method (Lee and Ham, 2020), Support Vector Machine (Aryal and Becerik-Gerber, 2019; Jung et al. , 2019; Jiang and Yao, 2016; Lu et al.…”

An IoT Framework for Modeling and Controlling Thermal Comfort in Buildings

“…A recent work (Jung et al, 2019) used machine learning to create a heat flux sensing model to infer personal thermal comfort under transient ambient conditions. Finally, an online learning approach was introduced in Ghahramani et al (2015) for modeling personalized thermal comfort via stochastic modeling.…”