Year: 2025
Type: article
Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by a range of symptoms and challenges related to social communication, repetitive behaviour’s, and restricted interests. People with ASD might find it difficult to talk or understand words, and they might use fewer words to express themselves. Understanding facial expressions and emotions can also be tricky for some individuals with ASD. The prevalence of Autism Spectrum Disorder (ASD) has been estimated to be around 1 in 54 children. Early detection of ASD traits in toddlers is critical for timely intervention and support. This Empirical study utilizes machine learning techniques for the automated detection of ASD traits in toddlers through the integration of diverse data modalities. The study leverages a rich dataset that combines behavioural observations, parent-reported assessments, and demographic information from a cohort of toddlers. The algorithms such as Decision tree, Random forest, SVM, CNN, Mobile Net-V2, VGG16 are tested using the autism spectrum dataset and comparison is made using the performance metrics. The results of the research work indicate that Mobile Net is better than other techniques.
Institution: Savitribai Phule Pune University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: diamond
OpenAlex ID: W4411889737