• A STUDY OF AUTISM SPECTRUM DISORDER USING PRINCIPAL COMPONENT ANALYSIS and FUZZY C-MEANS CLUSTERING

DR. R. UMA RANI, R. SUGUNA, MISS. P. AMSINI

Abstract


A dimension means measurement of a certain aspect of an object. Dimensionality reduction is the study of reducing the dimension of a dataset without affecting the original data. Autism is a most sensitive problem for the children and adolescent also. Principal Component Analysis (PCA) is mostly used to do dimensionality reduction in data analysis. After preprocessing, Fuzzy C-means (FCM) algorithm is applied for clustering the data. ASD occurs more often in people who have certain genetic conditions and how genes interact with each other and with environmental factors, such as family medical conditions, parental age and complications during birth or pregnancy. The term “spectrum” refers to the wide range of symptoms, strengths, and levels of abrasion that people with ASD can have. In this paper we have focused on reducing the weak components of the autism spectrum disorder dataset and gene expression in blood of children with autism spectrum disorder (ASD).  The study was based on PCA and Fuzzy Clustering.


Keywords


PCA (Principal Component Analysis), Autism, dimension reduction, ASD (autism spectrum disorder), fuzzy clustering, R Studio.

Full Text:

PDF


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
© 2010-2022 International Journal of Mathematical Archive (IJMA)
Copyright Agreement & Authorship Responsibility
Web Counter