A serial and parallel genetic based learning algorithm for Bayesian classifier to predict metabolic syndrome

Abstract

This paper presents a serial and parallel genetic based learnable bayesian classifier for designing a prognostic model for metabolic syndrome. The objective of the classifier is to address the fundamental problem of finding the optimal weight in the learnable bayesian classifier, by serial GA, and minimize the response time by parallel GA. The algorithms exhibit an improved capability to eliminate spurious features from the large dataset and aid the researchers in identifying those features that are solely responsible for high prediction accuracy. The e ectiveness of the classifier are demonstrated using metabolic syndrome dataset obtained from Yonchon County of Korea.