Detecting Autism Spectrum Disorder Using Machine Learning Techniques

DOI

No DOI

Published In

Volume 4, Issue 2 (2023)

Published Online

March-April 2023

Pages

08-11

Article Type

Research Article

Check for updates

No DOI available for cross-reference

Abstract: Those with autism spectrum disorders (ASDs) engage in a variety of disruptive behaviors. In most cases, they cannot speak clearly. Instead, they establish a relationship by gesturing and pointing. As a result, one of the most difficult tasks for caregivers is to comprehend their requirements, but early diagnosis of the disease can make it much simpler. The Internet of Things (IoT) and assistive technologies can eliminate the lack of verbal and nonverbal communication. By employing Deep Learning (DL) and Machine Learning (ML) algorithms, the IoT-based systems aid in diagnosis and enhance patient lives. Neuro developmental disorder known as Autism Spectrum Disorder (ASD) has an impact on behavior, social interaction, and communication. Because the symptoms and characteristics can vary widely from person to person, it is referred to as a "spectrum" disorder. Some people with ASD may have trouble communicating verbally and nonverbally, have trouble making and keeping friends, do things over and over again, or have narrow interests. Math, music, and art are just a few of the areas in which some people with ASD excel. The onset of symptoms typically occurs in early childhood, and their severity can range from mild to severe. While the specific reason for ASD isn't known, being a blend of hereditary and ecological factors is accepted. Although there is currently no known treatment for ASD, early intervention and therapy can assist individuals with ASD in acquiring new abilities and enhancing their quality of life. An agglomeration information stream has introduced a very important formulation for information and information engineering because the applications currently offer streaming information. It is challenging to instantiate in order to generate a vast variety of functions known as micro-clusters in tandem with an online method. The collective density of micro-clusters increases as a result of providing the information of enormous data points through a defined lay. A hypothetical to express agglomeration algorithmic rule that is utilized in a specific offline rate to transform the micro-clusters into the enormous final cluster is the requirement that is currently available.