دانلود رایگان ترجمه مقاله استنتاج درختان تصمیم گیری با الگوریتم بهینه سازی کلونی مورچه ها (نشریه الزویر 2012)

استنتاج درختان تصمیم گیری با یک الگوریتم بهینه سازی کولونی مورچه

Inducing decision trees with an ant colony optimization algorithm

Abstract

Decision trees have been widely used in data mining and machine learning as a comprehensible knowledge representation. While ant colony optimization (ACO) algorithms have been successfully applied to extract classification rules, decision tree induction with ACO algorithms remains an almost unexplored research area. In this paper we propose a novel ACO algorithm to induce decision trees, combining commonly used strategies from both traditional decision tree induction algorithms and ACO. The proposed algorithm is compared against three decision tree induction algorithms, namely C4.5, CART and cACDT, in 22 publicly available data sets. The results show that the predictive accuracy of the proposed algorithm is statistically significantly higher than the accuracy of both C4.5 and CART, which are well-known conventional algorithms for decision tree induction, and the accuracy of the ACO-based cACDT decision tree algorithm.

1 Introduction

One of the most studied data mining tasks in the literature is the classification task [15,29]. In essence, the classification task consists of learning a predictive relationship between input values and a desired output. Each example (data instance or record) is described by a set of features (attributes)—referred to as predictor attributes—and a class attribute. Given a set of examples, a classification algorithm aims at creating a model, which represents the relationship between predictor attributes values and class values (labels), and which is able to predict the class label of a new (unseen) example based on the values of its predictor attributes. Classification problems can be viewed as optimisation problems, where the goal is to find the best function (model) that represents the predictive relationships in the data.