Understanding pilots’ visual attention during Instrument Landing System (ILS) approaches is critical for enhancing aviation safety and operational success. This study investigates gaze patterns of successful and unsuccessful approaches using eye tracking data collected in simulated ILS environments to identify distinct visual behaviors associated with successful performances. The findings show that successful approaches are characterized by a compact and purposeful visual scan with smaller convex hull, longer fixation, and greater variability in gaze directions, indicating expert attention allocation, deliberate visual anchoring, and purposeful scanning of key flight instruments. Additionally, successful pilots focused more on critical control instruments reflecting a cause-and-primary-error strategy compared to unsuccessful pilots exhibiting gaze patterns more consistent with symptom monitoring. These insights contribute to the development of gaze-based assessment metrics, training protocols, interface designs that promote adaptive visual strategies to optimize precision and control, thereby improving safety outcomes and operational reliability in aviation.

Future intelligent aircraft are envisioned to predict human failures and mitigate threats at runtime to optimize safety. Contributing towards realizing this vision, and more specifically, recognizing when timely interventions should be invoked, this paper investigates gaze-based predictions on pilots' success and failure. In a simulated study with 50 licensed pilots performing an Instrument Landing System approach in low-visibility conditions, we examined the use of saccade magnitude and direction, pupil dilation, fixation duration, and blink rate to detect notable events experienced by pilots. We performed classification experiments using established machine learning models demonstrating that pilots' performance can be successfully predicted as early as 3.42 minutes after task initiation with accuracies up to 80.92% depending on the gaze measure used. Our findings also showed improved accuracies compared to predictions generated using established gaze measures such as gaze entropy. Furthermore, accuracies tend to peak during critical flight phases and support vector machines performed well across the tested gaze measures.

Designing and developing innovative visualizations to assist humans in the process of generating and understanding complex semantic data has become an important element in supporting effective human-ontology interaction, as visual cues are likely to provide clarity, promote insight, and amplify cognition. While recent research has indicated potential benefits of applying novel adaptive technologies, typical ontology visualization techniques have traditionally followed a one-size-fits-all approach that often ignores an individual user's preferences, abilities, and visual needs. In an effort to realize adaptive ontology visualization, this paper presents a potential solution to predict a user's likely success and failure in real time, and prior to task completion, by applying established machine learning models on eye gaze generated during an interactive session. These predictions are envisioned to inform future adaptive ontology visualizations that could potentially adjust its visual cues or recommend alternative visualizations in real time to improve individual user success. This paper presents findings from a series of experiments to demonstrate the feasibility of gaze-based success and failure predictions in real time that can be achieved with a number of off-the-shelf classifiers without the need of expert configurations in the presence of mixed user backgrounds and task domains across two commonly used fundamental ontology visualization techniques.

Information Visualization is a key technique to assist users in data analysis tasks, by creating visual representations of data to amplify human cognition. However, while human cognitive abilities and styles have been shown to differ significantly, Information Visualizations have traditionally been designed in a manner that does not consider such individual user differences. Recent research has started to address this issue, by identifying individual user characteristics that influence individual users' interactions with Information Visualizations, as well as developing novel Information Visualization systems that provide more personalized support. This paper presents a set of experiments aimed towards building such User-Adaptive Information Visualization systems, by studying the extent to which a user's cognitive style can be inferred from a user's interaction with an Information Visualization system. Results show that a user's eye gaze data can be used to infer a user's cognitive style during information visualization usage with up to 86% accuracy, and that the most informative features relate to a user's saccade angles and fixation durations.