Optimizing Early Autism Detection In Toddlers: A Hybrid Approach Utilizing Ant Colony And Particle Swarm Intelligence
Main Article Content
Abstract
This study presents a novel methodology for the identification of Autism Spectrum Disorder (ASD) in toddlers by integrating Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) algorithms. The objective is to enhance the accuracy and reliability of ASD diagnosis through a hybrid computational model. Each toddler’s symptoms were quantified and processed using ACO to identify potential ASD cases, followed by PSO to optimize the classification based on symptom severity.
The model’s performance was assessed using a random forest classifier which demonstrated an accuracy range between 94% and 98%, indicating a significant improvement over traditional diagnostic methods.
In conclusion, this hybrid model offers a promising tool for early ASD detection, with the potential to facilitate timely intervention and support for affected children. The findings underscore the efficacy of combining nature-inspired algorithms in medical diagnosis, paving the way for further research and application in clinical settings.