Cross-Task and Cross-Participant Classification of Cognitive Load in an Emergency Simulation Game

Assessment of cognitive load is a major step towards adaptive interfaces. However, non-invasive assessment rather subjective as well task specific and generalizes poorly, mainly due to methodological limitations. Additionally, it heavily relies on performance data like game scores or test results. In this study, we present an eye-tracking approach that circumvents these shortcomings allows for effective generalizing across participants tasks. First, established classifiers predicting individually typical working memory (n-back), which then applied emergency simulation by considering the similar ones weighting their predictions. Standardization steps helped achieve high levels cross-task cross-participant classification accuracy between 63.78 67.25 percent distinction easy hard game. These very promising results could pave way novel computer-human interaction domains particularly gaming learning environments.