article · Neural Computing and Applications
Autism diagnosis is often challenging because conventional medical assessments rely on brain function abnormalities that may not appear during early development. Facial expressions offer an alternative diagnostic route because autistic children display distinct expressive patterns. A real-time emotion recognition system has been designed to identify six primary facial expressions in autistic youth: anger, fear, joy, natural expression, sadness, and surprise. The framework operates through three consecutive stages comprising face identification, feature extraction, and feature classification. It combines an enhanced deep learning technique based on convolutional neural networks with a genetic algorithm that selects optimal hyperparameters. To achieve low latency, rapid response times, and location awareness, the architecture integrates Internet of Things devices and fog computing. Evaluation results demonstrate that this enhanced approach outperforms alternative methods, achieving an emotion classification accuracy of 99.99 per cent.
Early diagnosis of autism remains difficult when relying solely on neurological indicators that may not be apparent in early childhood. By using assistive technology to recognise facial emotion patterns in real time, this approach offers an alternative route to support early detection and improve the quality of life for autistic individuals through timely intervention.
The technology offers potential application in assistive healthcare tools and real-time monitoring devices used by medical practitioners and caregivers supporting children with autism. Integrating fog computing and Internet of Things hardware provides a framework for responsive, localised deployment. The work demonstrates an applied software model tested to achieve high classification accuracy, placing it at an experimental applied research stage that requires clinical validation before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Diagnosis of autism considers a challenging task for medical experts since the medical diagnosis mainly depends on the abnormalities in the brain functions that may not appear in the early stages of early onset of autism disorder. Facial expression can be an alternative and efficient solution for the early diagnosis of Autism. This is due to Autistic children usually having distinctive patterns which facilitate distinguishing them from normal children. Assistive technology has proven to be one of the most important innovations in helping people with autism improve their quality of life. A real-time emotion identification system for autistic youngsters was developed in this study. Face identification, facial feature extraction, and feature categorization are the three stages of emotion recognition. A total of six facial emotions are detected by the propound system: anger, fear, joy, natural, sadness, and surprise. This section proposes an enhanced deep learning (EDL) technique to classify the emotions using convolutional neural network. The proposed emotion detection framework takes the benefit from using fog and IoT to reduce the latency for real-time detection with fast response and to be a location awareness. From the results, EDL outperforms other techniques as it achieved 99.99% accuracy. EDL used GA to select the optimal hyperparameters for the CNN.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-08372-9
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
