Thesis on Detecting Immersion with EEG

In my master’s dissertation, I explored how Machine Learning can connect immersion in multimedia content to physiological signals, primarily electroencephalogram (EEG) data.

Main Contributions

Objective condition classification: EEG data can effectively distinguish between users watching content in objectively different settings.

Subjective rating classification: EEG data can accurately predict when a user will rate an experience as immersive.

Implications

The thesis shows that cognitive processes such as immersion can be modeled with EEG. These findings could enable personalized immersive experiences in emerging multimedia formats, with implications for entertainment, healthcare, and education.

Acknowledgements

I want to thank the researchers at Ghent University who helped me: Prof. dr. ir. Maria Torres Vega, Ir. Sam Van Damme, Ir. Mohammad Javad Sameri and Prof. dr. ir. Filip De Turck. I am also grateful to Dr. Anne-Flore Perrin for the data and prior research on quality assessment of immersive media.