A novel approach for grouping of autism by using convolutional neural network

Chinnala Balakrishna 1, *, Akurathi Lakshmi pathi Rao 2 and Vinay Kumar Enugala 3

1 Associate Professor, Department of CSE (Cyber Security), Guru Nanak Institute of Technology, Telangana, India.
2 Assistant Professor, Department of CSE, Guru Nanak Institute of Technology, Telangana, India.
3 Assistant Professor, Department of CSE (AIML), Guru Nanak Institute of Technology, Telangana, India.
 
Research Article
International Journal of Science and Research Archive, 2024, 12(02), 2321–2326.
Article DOI: 10.30574/ijsra.2024.12.2.1534
Publication history: 
Received on 07 July 2024; revised on 16 August 2024; accepted on 19 August 2024
 
Abstract: 
Autism Spectrum Disorder (ASD) is a complicated neurological disease marked by difficulties in social communication, restricted interests, and repetitive activities. The disorder's spectrum nature reflects its vast range of symptoms, skills, and impairment levels. ASD usually develops in early childhood, often before the age of three, and lasts throughout a person's life. Although the specific etiology of ASD is unknown, it is thought to be a combination of genetic and environmental factors. Early identification and intervention are critical in improving outcomes for people with ASD, allowing them to acquire social, communicative, and adaptive skills. The condition affects each person differently, with some requiring extensive care and others living independently. Research is continuing to better understand the underlying mechanisms and enhance diagnostics. Deep neural networks function well in a variety of applications. In this method, a convolution neural network is proposed to detect young children with ASD at an early age. The photos of Autism spectrum disorder are separated from normal controls using the Convolution Neural Network (CNN) ResNet-50 architecture.
 
Keywords: 
Autism spectrum disorder (ASD); Convolutional Neural Network (CNN); Logistic Regression (LR); Residual Network (ResNet50)
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0