Janjua, Osama Maqsood  <br/><br/>
Hybrid AI-Driven Probabilistic Modeling of Window Operations and Thermal Comfort: A Multi-Variable Approach for Residential Environments / 
Osama Maqsood Janjua 
 - 109p.  Soft Copy  30cm 
<br/><br/> Occupant window interactions is a critical component in optimizing energy consumption and<br/>indoor environmental quality. Understanding the influence of environmental and behavioral<br/>factors on window state decisions remains a significant challenge in building management<br/>systems. We present an AI integrated probabilistic model to assess thermal comfort and predict<br/>the probability of the occupant opening or closing the window. The data was acquired from an<br/>open-source platform that provided yearly university dormitory window interactions. Bayesian<br/>networks and logistic regression models were applied to predict the window-opening behavior<br/>of the occupants. An average accuracy of 92% for Bayesian and 94% for Logistic regression<br/>were obtained. The results were further enhanced by combining these models through<br/>weighted methods, with weights extrapolated through generative recursive iterations<br/>generating an average accuracy of 95% and AUC of 98%. The proposed hybrid approach<br/>significantly improves over existing predictive models in thermal comfort and window state<br/>prediction.  
<br/><br/><label>Subjects--Topical Terms: </label><br/>MS Mechanical Engineering      
<br/><br/><label>Dewey Class. No.: </label>621