Related Experiment Video
Updated: Jul 14, 2026
09:47
DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
Published on: December 15, 2023
Early Autism Spectrum Disorder Detection Using Adaptive Fused Spatial-Temporal Graph Convolutional Network Optimized
Alphonsa Mandla1, Chilukala Mahender Reddy2, Goli Himabindu3
1Department of Computer Science and Engineering, Vasavi College of Engineering, Ibrahimbagh, Telangana, India.
Summary
This study introduces an advanced AI model for early autism spectrum disorder (ASD) detection, significantly improving diagnostic accuracy and reducing computational time. The novel approach promises more reliable identification for timely intervention.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Biomedical Engineering
Background:
- Autism spectrum disorder (ASD) diagnosis relies on behavioral assessments, which can be prone to errors.
- Early and accurate ASD detection is crucial for effective intervention and improved outcomes.
Purpose of the Study:
- To develop and evaluate an AI-driven method for early autism spectrum disorder detection.
- To enhance diagnostic accuracy and efficiency compared to conventional methods.
Main Methods:
- Utilized an Adaptive Fused Spatial-Temporal Graph Convolutional Network Optimized with Artificial Lemming Algorithm (AFSTGCN-ALA).
- Employed Adaptive Fast Desensitized Kalman Filter (AFDKF) for noise reduction and Multi-Synchro Squeezing Transform (MSST) for feature extraction.
- Optimized AFSTGCN-ALA model parameters using the Artificial Lemming Algorithm (ALA) for improved ASD categorization.
Main Results:
- The AFSTGCN-ALA model demonstrated superior accuracy, outperforming existing methods by 18.97% to 32.68%.
- Achieved significant reductions in computation time, ranging from 19.84% to 31.62%.
- Exhibited high precision and F1-score, indicating reliable ASD identification.
Conclusions:
- The proposed AFSTGCN-ALA model offers a highly effective and dependable solution for early autism spectrum disorder identification.
- This advancement facilitates more accurate diagnoses, paving the way for prompt and personalized therapeutic interventions.