International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 02 | Feb 2024
p-ISSN: 2395-0072
www.irjet.net
Autism Spectrum Disorder Detection Using Machine Language Dr. Rajesh Prasad, Dipti Shendre, Heli Shah, Kaustubh Kohale, Prashant Tanwar Dr.Rajesh Prasad, Guide, Dept. of Computer Science Engineering, MIT Art , Design and Technology University, Maharashtra, India Dipti Shendre, Dept. of Computer Science Engineering, MIT Art , Design and Technology University, Maharashtra, India Heli Shah, Dept. of Computer Science Engineering, MIT Art , Design and Technology University, Maharashtra, India Kaustubh Kohale, Dept. of Computer Science Engineering, MIT Art , Design and Technology University, Maharashtra, India Prashant Tanwar, Dept. of Computer Science Engineering, MIT Art , Design and Technology University, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - According to the World Health Organization (WHO), about 1 in 160 people worldwide are affected by Autism Spectrum Disorder (ASD). The increasing cases of ASD have inspired researchers globally to study it, and new technologies like Machine Learning (ML) are being used to detect ASD early. Our project aims to address these challenges. The main goals include: Early Detection of ASD: ASD can't be cured, but if we find it early, we can reduce its negative effects. Our focus is on spotting it as soon as possible. Improving Diagnostic Methods: Most clinical methods are costly, take a long time, and sometimes give inaccurate results. We're using ML to make the process more affordable, accurate, and quicker for early treatment. Enhancing Existing Techniques: Previous work usually compares methods or introduces entirely new algorithms. Our project not only compares different techniques using three datasets but also aims to create a better and more accurate algorithm. Our project aims to make ASD detection more accessible, accurate, and timely, contributing to better outcomes for individuals affected by this condition. Key Words: WHO, Early Detection , Clinical Methods , Enhanced Algorithms , Accuracy
1. INTRODUCTION Autism spectrum disorder is a developmental disorder that describes certain challenges associated with communication (verbal and non-verbal), social skills, and repetitive behaviors. Typically, autism spectrum disorder is diagnosed in a clinical environment by licensed specialists using procedures which can be lengthy and cost-ineffective. In addition to the clinical methods, machine learning methods have been successfully applied to shorten the duration of the diagnosis and to increase the performance of the diagnosis of the ASD. We discovered algorithms like Random Forests which show high compatibility with few of the other important algorithms and once infused give maximum accuracy which can be further improved with introduction of more compatible algorithms and methods which will not only bring out the most accurate but also a faster technique. Machine learning has the potential to make this medical field a lot more easier and advanced which will help doctors and professionals across the globe in future.
1.1 Goals Researchers worldwide are studying ASD with the goal of early detection. Early detection is important because ASD is incurable, but early treatment can reduce the negative effects of symptoms.
Early detection gives licensed clinical experts an advantage in treating ASD.
However, early detection is meaningless if the results are inaccurate. Therefore, we will use machine learning (ML) techniques to improve the accuracy of ASD diagnosis.
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 512