Loading...

Modeling of Children’s Behaviors In Interaction with A Virtual Social Robot During A Music Education Program Using Deep Neural Networks

Tandiseh, Armin | 2025

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57868 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Taheri, Alireza
  7. Abstract:
  8. Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by difficulties in communication and social interaction, along with repetitive and restricted behaviors. Effective interventions are crucial to improving skills and the quality of life for individuals with ASD. Music is a promising therapeutic approach that can help enhance social communication, emotional regulation, and sensory integration in children with ASD. Music therapy or education uses music to achieve therapeutic goals like improving social skills, reducing anxiety, and addressing communication challenges. Combining music-based games with virtual reality (VR) technology offers an immersive, multisensory experience that allows children with ASD to explore and interact with their environment in a safe and controlled way. This research aimed to develop an intelligent system to evaluate performance and extract behavioral models for children with ASD and neurotypical children by interacting with a virtual social robot in a music education program using deep neural networks. The system has three main features: it distinguishes between neurotypical children and those with ASD based on their behavior, evaluates participant performance and predicts future responses, and generates behaviors resembling those of neurotypical or ASD children in similar situations using deep learning. Early detection of autism significantly improves children’s skills and quality of life. Intelligent systems that identify complex patterns and simulate behavior can aid in diagnosis, therapist training, and understanding the disorder. Using data from a previous study at the Social and Cognitive Robotics Laboratory of Sharif University of Technology, the system achieved an accuracy of 81% and sensitivity of 96% in distinguishing neurotypical children from those with ASD using both impact data and motion signals. A transformer-based network was designed to reproduce children’s behaviors. Experts in the field struggled to differentiate real behaviors from reproduced ones, with an accuracy of 53.5% and agreement of 68%, indicating the model’s success in simulating realistic behaviors
  9. Keywords:
  10. Autism Spectrum Disorders (ASD) ; Imitation ; Deep Neural Networks ; Social Virtual Reality Robot ; Behavior Simulation ; Music Education

 Digital Object List

 Bookmark

No TOC