A DIAMOND Method for Classifying Biological Data

Abstract

This study proposes an effective method called DIAMOND to classify biological and medical data. Given a set of objects with some classes, DIAMOND separates the objects into different cubes, where each cube is assigned to a class. Via the union of these cubes, we utilize mixed integer programs to induce classification rules with better rates of accuracy, support and compactness. Two practical data sets, one of HSV patient results and the other of Iris flower, are tested to illustrate the advantages of DIAMOND over some current methods.