Handling Continuous Attributes in an Evolutionary Inductive Learner

Abstract

This paper analyzes experimentally discretization algorithms for handling continuous attributes in evolutionary learning. We consider a learning system that induces a set of rules in a fragment of first-order logic (evolutionary inductive logic programming), and introduce a method where a given discretization algorithm is used to generate initial inequalities, which describe subranges of attributes' values. Mutation operators exploiting information on the class label of the examples (supervised discretization) are used during the learning process for refining inequalities. The evolutionary learning system is used as a platform for testing experimentally four algorithms: two variants of the proposed method, a popular supervised discretization algorithm applied prior to induction, and a discretization method which does not use information on the class labels of the examples (unsupervised discretization). Results of experiments conducted on artificial and real life datasets suggest that the proposed method provides an effective and robust technique for handling continuous attributes by means of inequalities.

Acoustic Diagnostics Applications in the Study of Technical Condition of Combustion Engine

“…This method identifies the damage on the basis of the sound emission spectral characteristics and is sufficient for recognition of injuries taking into account not large number of measurements. In the literature many studies regarding other methods of failure identification may be found ( It is possible to use heuristic search methods in order to create the method of decision trees (Divina, Marchiori, 2005). Actions undertaken while the problem is being solved can be classified as searching of objects of the specified characteristics.…”

Alternative approach for learning and improving the MCDA method PROAFTN

“…With the inductive approach, the classification rules are obtained from examples, where each object or example belongs to a known labeled class. The goal of this inductive approach is to ultimately generate classification models that assign new objects to the right class 22. Decision tree (DT), Support vector machine (SVM),23,24 naive Bayes (NB), Bayesian networks (BN), neural networks (NN), and k ‐nearest neighbor ( k ‐nn) are well‐known examples of the inductive approach 2,22,23.…”

“…However, the main problem associated with MCDA is that the classification models do not automatically result only from the vectors describing the objects but depend also on the judgment of a DM. The DM defines the “boundaries” of the attributes and the weights which define the importance of each attribute in the data set 17,22. However, it is usually difficult for a DM to assign accurate quantitative values to these parameters.…”

A Review of Evolutionary Algorithms for Data Mining

“…In this case the EA is effectively doing a discretization of continuous values "on-the-fly", since by creating rule conditions such as "30K ≤ Salary ≤ 50K the EA is effectively producing discrete intervals. The effectiveness of an EA that directly copes with continuous attributes can be improved by using operators that enlarge or shrink the intervals based on concepts and methods borrowed from the research area of discretization in data mining (Divina & Marchiori 2005).…”