Abordagens baseadas em teoria da informação para seleção automatizada de atributos

Abstract

With the fast growing of complex data in real world applications, the feature selection becomes a mandatory preprocessing step in any application to reduce both the complexity of the data and the computing time. Based on that, several works have been produced in order to develop efficient methods to perform this task. Most feature selection methods select the best attributes based on some specic criteria. Although some advancement has been made, a poor choice of a single algorithm or criteria to assess the importance of attributes, and the arbitrary choice of attribute numbers made by the user may lead to poor analysis. In order to overcome some of these issues, this paper presents the development of two strands of automated attribute selection approaches. The first are fusion methods of multiple attribute selection algorithms, which use ranking-based strategies and classifier ensembles to combine feature selection algorithms in terms of data (Data Fusion) and decision (Fusion Decision), allowing researchers to consider different perspectives in the attribute selection stage. The second strand approaches the dynamic feature selection context through the proposition of the PF-DFS method, an improvement of a dynamic feature selection algorithm, using the idea of Pareto frontier multiobjective optimization, which allows us to consider different perspectives of the relevance of the attributes and to automatically define the number of attributes to select. The proposed approaches were tested using several real and artificial databases and the results showed that when compared to individual selection methods, the performance of one of the proposed methods is remarkably higher. In fact, the results are promising since the proposed approaches have also achieved superior performance when compared to established dimensionality reduction methods, and by using the original data sets, showing that the reduction of noisy and/or redundant attributes may have a positive effect on the performance of classification tasks.