Detection of Autism Spectrum Disorder using Deep Neural Network

Rajkumar, Timothy Antony (2023) Detection of Autism Spectrum Disorder using Deep Neural Network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by neurological variations. Individuals diagnosed with Autism Spectrum Disorder (ASD) may exhibit distinctive patterns of behavior, communication, social interaction, and cognitive processes that differ from the typical functioning observed in the majority of the population. Autism Spectrum Disorder (ASD) frequently appears at age three and can last a lifetime, however symptoms may improve over time. Some children show indicators of Autism Spectrum Disorder (ASD) in their first year. A child may not show symptoms until 24 months or older. Some children with Autism Spectrum Disorder (ASD) learn new skills and reach developmental milestones by 18–24 months. The condition's wide range of behavioral and verbal symptoms makes it hard to identify, especially in toddlers. Due to timeconsuming clinical tests and high financial expenses, Autism Spectrum Disorder (ASD) diagnosing processes stress healthcare personnel. The advent of machine learning and deep learning in the medical domain presents a potentially advantageous resolution. This study introduces a novel approach by employing a Deep Learning architecture to significantly enhance the early identification of Autism Spectrum Disorder (ASD) in toddlers. The methodology relies on the utilization of an Artificial Neural Network (ANN), which is a method of Deep Learning. Through the use of this method, the study seeks to augment diagnostic accuracy and optimize the diagnostic procedure. This study represents a significant progress in the early diagnosis of Autism Spectrum Disorder (ASD), utilizing the ability of Artificial Intelligence (AI) to transform diagnostic methodologies in order to improve the healthcare outcomes for toddlers. The trained model is tuned using hyper-parameters which gave the best performance of the model. The accuracy of the suggested artificial neural network (ANN) model after tuning was found to be 98%. This suggests that our approach represents effectiveness for the diagnosis of Autism Spectrum Disorder (ASD) in toddlers. If implemented, this method might enable parents to immediately provide suitable therapy that reduce the symptoms of ASD.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Siddig, Abubakr UNSPECIFIED
Uncontrolled Keywords:	ASD; Deep Learning; diagnosis; Accuracy; Artificial Neural network; therapy
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science B Philosophy. Psychology. Religion > Psychology > Child psychology R Medicine > Diseases > Disabilities > Developmental disabilities Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	28 Dec 2024 15:15
Last Modified:	28 Dec 2024 15:15
URI:	https://norma.ncirl.ie/id/eprint/7254

Actions (login required)

View Item