Smart Autism Spectrum Disorder Learning System Based on Remote Edge Healthcare Clinics and Internet of Medical Things

Area of Science:

• Artificial Intelligence
• Healthcare Technology
• Special Education

Background:

• Autism spectrum disorder (ASD) impacts children's learning, necessitating optimized educational technologies.
• Existing approaches often lack personalized, accessible learning environments for autistic children.
• Remote healthcare and IoT integration offer potential for improved ASD education.

Purpose of the Study:

• To develop a smart learning system for autistic children using remote edge healthcare and the Internet of Medical Things (IoMT).
• To provide an integrated online education and healthcare environment tailored for children with ASD.
• To optimize learning applications for ASD focusing on quality of service (QoS) and processing constraints.

Main Methods:

• The study proposes the Smartwatch Autism Spectrum Data Learning Scheme (SM-ASDS).
• SM-ASDS employs partitioning offloading and deep learning models (DCNN, ALSTM) for data training on various devices.
• Applications run on smartwatches, mobile devices, and edge nodes, considering optimization constraints like accuracy and processing time.

Main Results:

• The SM-ASDS scheme demonstrated a 30% improvement in learning scores.
• Accuracy was enhanced by 98% compared to baseline methods.
• Total processing time was reduced by 33%.

Conclusions:

• The developed smartwatch-based system effectively facilitates educational training for autistic patients.
• Artificial intelligence techniques integrated into the system significantly improve learning outcomes for ASD.
• The system offers a promising approach to online education and healthcare for children with autism.