Using Eye Tracking to Distinguish Between Different Levels of Cognitive Workload
Augmented cognition is a relatively new field in Human-Computer Interaction that aims for the development of systems that can detect the user’s cognitive state in real-time and consequently adapt the system appropriately. Such an adaptation could improve the effectiveness of human-computer interfaces. In this thesis a method is developed to distinguish between multiple levels of cognitive workload using eye-behavior features. These features are based on features that are known to be distinctive when used to distinguish between other cognitive states . The data are obtained using an eye tracker. The results indicate that this method is task dependent to a degree, but these results are not conclusive. On the other hand, it is shown that this method can distinguish between different levels of cognitive workload within a task and that this measure is subject-independent.
Faculteit der Sociale Wetenschappen