Predicting user action from skin conductance

There are many studies focusing on enhancing physiological data in user interfaces. On one hand biofeedback games are using skin conductance and heart rate data to reflect the emotional state of the user, on the other hand BCI research tries to conclude user intentions from EEG signals. In our research we are collecting usual biofeedback data but process it with complex algorithms similarly to the BCI methodologies. This way we are able to conclude more complex user states than relaxation or anxiety. In our experiments we asked users to play with a simple arcade game, while we were recording physiological data. We were training artificial neural networks to learn the time of user action from the physiological signals. The networks were capable of detecting and also predicting user action 2 seconds before it was carried out.