Understanding early childhood obesity risks: An empirical study using fuzzy signatures

Abstract

Childhood obesity is a serious health problem that has adverse and long-lasting consequences for individuals, families, and communities. The magnitude of the problem has increased dramatically during the last three decades and, despite some indications of a plateau in this growth, the numbers remain stubbornly high. The nature of child obesity data is very complicated with different factors dependent on each other directly or indirectly affecting obesity as a whole. Traditional statistical analysis and machine learning approaches alone are not sufficient to model early childhood obesity risk and its impact on children's motor development. In this paper, we propose a computational model using Fuzzy Signature to understand and handle the intricacies of child obesity data and propose a solution that could be used to handle the risk associated with early childhood obesity and young children's motor development.