Utilizing Wearable Devices To Design Personal Thermal Comfort Model

have confirmed that thermal comfort significantly depends on internal personal parameters such as metabolic rate, age, and health status. This is manifested as a difference in comfort levels between people residing under the same roof, and hence no general comprehensive comfort model satisfying everyone. Current and newly emerging advancements in state of the art wearable technology have made it possible to continuously acquired biometric information. This work proposes to access and exploit this data to build personal thermal comfort model. Relying on various supervised machine-learning methods, a personal thermal comfort model will be produced and compared to a general model to show its superior performance. In this work, it has been shown that the introduction of galvanic skin response (GSR) data in training the models results in more reliable and accurate private models