Investigating the generalizability of EEG-based Cognitive Load Estimation Across Visualizations
This addresses the problem of evaluating visualization usability for cognitive load in human-computer interaction, but it is incremental as it applies existing methods to new data.
The study investigated whether EEG-based cognitive load estimation generalizes across different visualizations (character, spatial pattern, bar graph, pie chart) for an n-back task, finding that estimation suffers across visualizations, highlighting the need for better machine learning techniques to benchmark visual interface usability.
We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the nback~task. CL is estimated via two recent approaches: (a) Deep convolutional neural network, and (b) Proximal support vector machines. Experiments reveal that CL estimation suffers across visualizations motivating the need for effective machine learning techniques to benchmark visual interface usability for a given analytic task.