Response time and eye tracking datasets for activities demanding varying cognitive load

Area of Science:

• Human-Computer Interaction
• Cognitive Science
• Biomedical Engineering

Background:

• Cognitive load assessment is crucial for human-system automation.
• Non-invasive, low-cost sensor data is needed for real-time cognitive load monitoring.
• Existing methods for cognitive load measurement can be invasive or expensive.

Purpose of the Study:

• To present a novel dataset for cognitive load research.
• To facilitate the development of machine learning algorithms for human-system automation.
• To support applications like Advanced Driver Assistance Systems (ADAS).

Main Methods:

• Collected data from 28 participants performing tasks at three cognitive difficulty levels.
• Measured cognitive load using Detection Response Task (DRT) response time, pupil diameter, and eye gaze.
• Utilized low-cost, non-invasive sensors for data acquisition.

Main Results:

• The dataset provides comprehensive measures of cognitive load under varying task difficulties.
• Data is suitable for training and validating machine learning models.
• Demonstrated the feasibility of using eye-tracking and response time for cognitive load detection.

Conclusions:

• The dataset is a valuable resource for researchers in cognitive science and HCI.
• Enables advancements in predictive human modeling for automated systems.
• Promotes the development of more intuitive and responsive human-machine interfaces.