A review of algorithms to computing irreducible testors applied to feature selection

Abstract

Feature selection is an important task in the areas of pattern recognition and data mining. Various approaches to feature selection have been developed. In particular, this paper focuses on the algorithms for computing irreducible testors, which have been used to solve feature selection problems. The calculation of irreducible testors is an expensive computational process; the complexity of the algorithms to calculate the complete set of irreducible testors exponentially depends on the number of characteristics that describe the objects in the problem. To improve the execution time of these algorithms, different alternatives have been developed, such as parallel implementations, hardware-software implementation, rearrangement of the data, as well as heuristics to generate just an irreducible testor or a subset of the entire set of irreducible testors, among other strategies. This paper presents a review of the literature on irreducible testors, with the aim of providing a guide for researchers working in the areas of pattern recognition and data mining, interested in feature selection, using heterogeneous data and possibly missing data