Enhanced Autism Spectrum Disorder Facial Expression Recognition Using Hybrid Weighed Quantum Particle Swarm Optimization with Fast Mask Recurrent Convolutional Neural Network

Autism Spectrum Disorder (ASD) affects brain development, impacting socialization, communication, and creativity in children.Signs typically appear within the first three years, with many children struggling with language acquisition, affecting their learning abilities.Various treatments help manage behaviors, benefiting both children and their parents.The mechanisms by which visual information about facial expressions translates into emotional categories are not well understood.This study proposes a system-level explanation through predictive processing theory.An innovative method combining Fast Mask Recurrent Convolutional Neural Network (FMRCNN) and hybrid Weighed Quantum Particle Swarm Optimization (WQPSO) aims to improve recognition of abnormal facial movements in individuals with ASD.FMRCNN captures temporal relationships and extracts features from input data, while the fast mask mechanism enhances network speed and efficiency by focusing on relevant input regions.The proposed method leverages predictive processing to improve accuracy and efficiency in facial expression recognition.It can identify six emotions: anger, fear, joy, sadness, surprise, and disgust.Results show significant potential in supporting ASD-related challenges, achieving 99.8% accuracy, 99.8% precision, 100% recall, and 94% specificity, surpassing existing systems in ASD facial expression recognition.