Advanced Gaze Analytics Dashboard

TL;DR

This work introduces an interactive, real-time gaze analytics dashboard that visualizes advanced eye-tracking measures, including ambient/focal attention $\mathcal{K}$, the cognitive-load indicator RIPA, and gaze transition matrices, by streaming data from RAEMAP. The methodology defines these measures and integrates them into a live visualization platform using hvPlot, enabling five concurrent real-time views: main sequence, fixations, $\mathcal{K}$, gaze transitions, and RIPA. Evaluation on Driving Simulation and Visual Scanning datasets demonstrates the dashboard's ability to reflect task demands—such as elevated cognitive load and focal attention in driving and ambient attention during complex visual searches—while highlighting limitations like the lack of a user study. The work suggests future directions including user evaluations, customization of visualized measures, and the incorporation of machine learning for predictive insights into cognitive states and task performance.

Abstract

Eye movements can provide informative cues to understand human visual scan/search behavior and cognitive load during varying tasks. Visualizations of real-time gaze measures during tasks, provide an understanding of human behavior as the experiment is being conducted. Even though existing eye tracking analysis tools provide calculation and visualization of eye-tracking data, none of them support real-time visualizations of advanced gaze measures, such as ambient or focal processing, or eye-tracked measures of cognitive load. In this paper, we present an eye movements analytics dashboard that enables visualizations of various gaze measures, fixations, saccades, cognitive load, ambient-focal attention, and gaze transitions analysis by extracting eye movements from participants utilizing common off-the-shelf eye trackers. We validate the proposed eye movement visualizations by using two publicly available eye-tracking datasets. We showcase that, the proposed dashboard could be utilized to visualize advanced eye movement measures generated using multiple data sources.

Figures (7)

• Figure 1: Example Visualizations of Advanced Gaze Measures Included in the Proposed Dashboard and Key Components.
• Figure 2: Visual Scanning - (1) Fixations Overlayed on "Where’s Waldo" Scene, (2) RIPA, a Measure of Cognitive Load, (3) Gaze Transitions Matrix.
• Figure 3: Driving Simulation - Left: Fixations along the Scan Path, Right: RIPA, Eye Tracked Measure of Cognitive Load.
• Figure 4: Driving Simulation - Ambient/Focal Attention Coefficient $\mathcal{K}$ Over Time, and Comparisons with Pupil Diameter, Fixation Duration, and Saccade Amplitude.
• Figure 5: Driving Simulation - Main Sequence Relationships. Left: Saccade Peak Velocity vs. Saccade Amplitude, Right: Saccade Duration vs. Saccade Amplitude.