Related Experiment Video
Updated: May 30, 2025
05:32
Comparing Eye-tracking Data of Children with High-functioning ASD, Comorbid ADHD, and of a Control Watching Social Videos
Published on: December 7, 2018
8.9K
Virtual Reality-Based Attention Prediction Model in Gaming for Autistic Children
1Department of Computer Science and Engineering, Vels Institute of Science & Technology & Advanced Studies, Chennai, Tamilnadu, India.
Summary
This study introduces VRAPMG, a virtual reality model using 3D gaming to assess attention in children with Autism Spectrum Disorder (ASD) by analyzing facial expressions and predicting engagement levels.
Area of Science:
- Computer Science
- Biomedical Engineering
- Psychology
Background:
- Virtual Reality (VR) offers therapeutic potential in healthcare, including rehabilitation and mental health.
- Assessing attention in children with Autism Spectrum Disorder (ASD) is crucial for tailored interventions.
- Existing methods for attention assessment in ASD may lack objective, real-time feedback mechanisms.
Purpose of the Study:
- To develop and evaluate a novel Virtual Reality-based Attention Prediction Model for Gaming (VRAPMG) for children with ASD.
- To utilize 3D gaming environments within VR to capture and analyze facial expressions for attention evaluation.
- To establish an automated system for predicting attention levels in children with ASD during VR-based activities.
Main Methods:
- Facial images were acquired, converted to grayscale, and preprocessed using a median filter.
- Face detection was performed using the Viola-Jones (VJ) algorithm.
- Feature extraction involved improved Active Shape Model (ASM), Shape Local Binary Texture (SLBT), and eye position localization.
- A hybrid classification model combining DMO and Bi-GRU was employed for emotion detection.
- Entropy-based attention prediction was utilized to determine attentiveness.
Main Results:
- The VRAPMG model successfully processed facial images to extract relevant features for attention analysis.
- The hybrid DMO-Bi-GRU model demonstrated effectiveness in classifying emotions indicative of attention.
- The entropy-based prediction accurately determined the attentiveness of children with ASD during the VR experience.
Conclusions:
- The developed VRAPMG model provides a promising, objective method for assessing attention in children with ASD.
- VR integrated with 3D gaming and advanced computational models can enhance diagnostic and therapeutic tools for ASD.
- This approach offers a foundation for developing more engaging and effective interventions for children with ASD.
