Construction of Children's Education Evaluation System Based on Fuzzy Logic

Abstract

Preschool education is a complicated matter that requires a detailed analysis of many ecological and developmental factors. The existing approaches to educational evaluation lack consideration for the unpredictability bias associated with assessing children's learning and growth. The purpose of this project is to create an improved fuzzy logic (IFL)-based system for evaluating children’s education. For the children’s education assessment system, we collected the various preschool data samples. Physical, socio-emotional development, spiritual, and intellectual growth, parental participation, care, behavior control, and attendance are the seven main feature areas that are the focus of the examination. After the data collection, min-max normalization is employed, to preprocess the data. Principal component analysis (PCA) is performed to remove the irrelevant features, to identify major features.  These inputs are translated into fuzzy sets and evaluated using a fuzzy inference system. A prototype of the system is implemented and tested with a dataset of children's educational records.  An education evaluation system based on fuzzy logic improves traditional methods by addressing vagueness and subjectivity in assessments. This comprehensive and accurate evaluation enhances in preschool educational strategies and preschool children performance analysis interventions, leading to better outcomes for preschool children.