Gender classification from anthropometric measurement by boosting decision tree: A novel machine learning approach

Abstract

The decision tree used a generating set of rules based on various correlated variables for developing an algorithm from the target variable. Using the training dataset this paper used boosting tree algorithm for gender classification from twenty-five anthropometric measurements and extract twelve significant variables chest diameter, waist girth, biacromial, wrist diameter, ankle diameter, forearm girth, thigh girth, chest depth, bicep girth, shoulder girth, elbow girth and the hip girth with an accuracy rate of 98.42%, by seven decision rule sets serving the purpose of dimension reduction.