Traditional thermal comfort models, such as the Predicted Mean Vote (PMV) model, estimate population-wide average comfort and overlook individual physiological differences. To address this, Personal Thermal Comfort (PTC) models incorporating physiological signals have been explored, with electroencephalography (EEG) gaining attention for its responsiveness to thermal perception and adaptation. This study analyzes EEG responses during thermal adaptation, distinguishing it from prior research focusing on stabilized conditions. EEG and skin temperature were measured under two thermal conditions, and Artificial Neural Networks (ANNs) were used to analyze EEG patterns. Results show significant individual variability, highlighting limitations of conventional models. Findings demonstrate that integrating EEG with environmental and physiological data enhances thermal comfort assessment accuracy, contributing to the development of a PTC model for real-time adaptive climate control in smart buildings and HVAC systems.