Eye Movement Analysis for Context Inference and Cognitive-Awareness: Wearable Sensing and Activity Recognition Using Electrooculaography

The current work introduces eye movement analysis as a novel modality for context inference and cognitive-awareness. The movement patterns the eyes perform as people carry out different activities reveal much about the activities themselves. In the same manner, eye movements are influenced by the current location or a particular environment. In addition, unconscious eye movements are linked to several cognitive processes of visual perception. These characteristics make eye movements a distinct source of information on a user's context. Eventually, information derived from eye movements may allow us to extend the current notion of context with a cognitive dimension, leading to so-called cognitive-aware systems. This work develops and evaluates wearable sensing and pattern recognition solutions for eye-based activity recognition, eye-based human-computer interaction and cognitive-awareness using electrooculography.