A combinatorial cooperative-tabu search feature reduction approach

Presenting an efficient general feature selection method for the problem of the curse of dimensionality is still an open problem in pattern recognition, and, considering the cooperation among features through search processes, it is the most important challenge. In this paper, a combinatorial approach has been proposed, which consists of three feature reduction algorithms that have been applied in a parallel manner to cooperate. We consider each of these algorithms as a component in a reduction framework. For each component, among all various attribute selection algorithms, the Tabu Search (TS) a useful and state of the art algorithm, is used. To take account of the interaction between features, more subsets should be examined. Hence, each component should explore individually through feature space in a local area which is different from other components. The proposed algorithm, called the Cooperative-Tabu-Search (CTS), and also a revised version of this new method, is introduced to accelerate the convergence. After sufficient iterations, which satisfy the objective function; the final subset has been selected by voting between three reduction phases, and the data is then transformed into the new space, where the data are classified with some commonly used classifiers, such as Nearest Neighbor (NN) and Support Vector Machine (SVM). The employed benchmark of this paper is chosen among the UCI datasets to evaluate the proposed method compared to others. The experimental results show the supremacy of the accuracy of the implemented combinatorial approach in comparison with traditional methods.