AUTISM Spectrum Disorder Detection Using Machine Learning
Nagalla Balakrishna, M. B. Mukesh Krishnan, Samanu Manvitha Reddy, Shaik Kandeme Irfan, Shaik Sumaiya
Abstract
Smart objects from the IoT, especially in e-Healthcare, Individuals with a neurodevelopmental disorder called autism spectrum disorder (ASD) may develop sensory issues like heightened sensitivity or reduced sensitivity to various stimuli such as sounds, smells, and touch. For effective interventions and improved results, autism spectrum disorder (ASD) must be diagnosed as soon as possible. ASD can be identified in infants as early as 18 months. A diagnosis at the age of two is considered reliable for ASD. Currently, Autism Spectrum Disorder (ASD) is increasingly prevalent, and traditional methods of detecting its characteristics are often costly. However, in this modern era, the use of artificial intelligence and machine learning (ML) has made it possible to predict ASD at an early stage, leading to more effective interventions. This project aims to analyze and compare the accuracy and efficiency of various machine learning algorithms, including Support Vector Machine (SVM), Decision Trees, Linear Discriminant Analysis, and Logistic Regression, for detecting ASD. The results of this project can help in developing more accurate and efficient ASD detection tools, leading to earlier interventions and improved outcomes for individuals with ASD.