Autism Spectrum Disorder (ASD) affects millions globally, disrupting communication, social interaction, and behaviour. Early, precise diagnosis is critical, yet current methods based on behavioural observations are often subjective and time-consuming. Researchers from the University of Warith Al-Anbiyaa and the University of Kufa are leading a shift in ASD detection using Electroencephalography (EEG), a non-invasive and painless method that measures brain electrical activity. Their studies explore the potential of EEG signals to identify neural differences linked to ASD.

These studies focus on improving EEG signal analysis through advanced feature extraction methods and machine learning (ML) techniques. For example, one study achieved 96.37% accuracy in detecting ASD by combining Riemannian geometry with ensemble learning methods like AdaBoostM1 and GentleBoost. Another review paper examined over 200 studies, highlighting the high performance of ML models like SVM, CNN, and ResNet50 in diagnosing ASD with accuracies up to 99.39%

These groundbreaking findings have been approved for publication in respected journals such as the Kufa Journal of Engineering, the Springer Series - ICCCnet2024, and Artificial Intelligence Review Magazine. While not yet published, these studies pave the way for more reliable, efficient, and accessible ASD diagnostic methods, offering hope for early intervention and better patient outcomes.

Research Publication to be Published (Approval granted):

• An Optimal EEG Features Extraction Methods for Autism Detection
• Enhanced EEG Signal Classification for Autism Spectrum Disorder using Riemannian Geometry and Ensemble Learning Techniques
• A Recent Advances on Autism Spectrum Disorders in Diagnosing Based on Machine Learning and Deep Learning
• Feature Fusion Correction