Exploring data analysis methods to find correlations between physiological data and flow

In learning situations, achieving Flow, the state of ideal experience of an activity, can greatly support the learning efficacy. Utilizing this connection by detecting and measuring Flow during the learning activity could potentially help to improve the learning rate in Serious Games. In a prior study aimed towards developing a tool to link Flow to physiological measurements, no meaningful correlations were found. However, this does not rule out the existence of such a correlation and different analysis methods might deliver results that are more favorable. In this work in progress paper, the previously collected data is revisited and an approach is outlined to explore the use of a multitude of machine learning methods, based on multiple physiological measurements, to detect Flow and to investigate, whether it provides adequate tools to gain further insight into the link between physiological data and Flow states.