PersonalisedComfort: a personalised thermal comfort model to predict thermal sensation votes for smart building residents
Saif Ur Rehman, Abdul Rehman Javed, Mohib Ullah Khan, Mubashar Nazar Awan, Adees Farukh, Aseel Hussien
Abstract
Internet of Things (IoT) empowered Heating, Ventilation, and Air Conditioning (HVAC) buildings are considered to monitor and control the regulation of thermostats, sensors, actuators, and control devices smartly. In this article, we propose a novel model named PersonalisedComfort to predict the thermal sensation votes of individuals living in a building. We use publicly available standard dataset ASHRAE RP-884 for experimentation and analysis. We apply conventional machine learning algorithms and deep learning algorithms to predict the thermal sensation vote. PersonalisedComfort achieves an accuracy of 85% to predict thermal sensation votes which 8% higher than state-of-the-art studies.