Stress Assessment for Augmented Reality Applications Based on Head Movement Features.

Area of Science:

• Human-Computer Interaction
• Biomedical Engineering
• Psychophysiology

Background:

• Augmented reality (AR) offers potential benefits for work and training.
• Automatic stress detection in AR is crucial for user health and technology adoption.
• Non-invasive methods are needed for seamless integration into AR experiences.

Purpose of the Study:

• To design and validate a non-invasive stress assessment system for augmented reality users.
• To identify key head movement features indicative of stress during AR tasks.
• To develop a machine learning model for accurate stress classification in AR.

Main Methods:

• A subjective experiment was conducted with participants performing stress-inducing tasks using a Head Mounted Display (HMD).
• Analysis of head movement data was performed to identify stress-related features.
• A Support Vector Machine (SVM) classifier was designed and trained using the identified features.

Main Results:

• Specific head movement patterns were found to be representative of stress.
• The developed SVM classifier demonstrated promising accuracy in detecting stress.
• The non-invasive approach proved effective for stress assessment in AR.

Conclusions:

• Head movement analysis is a viable method for non-invasive stress detection in augmented reality.
• This approach can support user well-being and encourage wider AR adoption.
• Further research in this direction holds significant potential for human-centered AR systems.