Effective multiple criterion approach for building a rule based decision tree classifier

Abstract

The reliability of disease classification for medical dataset has newlinebecome challenging task due to the measurement of noise and biological newlineheterogeneity among patients Most of the medical datasets have complicated newlineboundaries between attributes and classes The current classification methods newlinefind only the rules with high accuracy These methods either cover only a newlinenarrow part of the objects or require numerous attributes to explain a newlineclassification rule Although these methods are computationally effective for newlinerealizing the classifications rules there are heuristic approaches that can newlineinduce feasible rules Feature selection refers to the problem of selecting those newlineinput attributes that are most predictive for a given outcome a problem newlineencountered in many areas such as machine learning pattern recognition and newlinesignal processin newline newline