Fuzzy-rough feature selection accelerator

Abstract

Fuzzy rough set method provides an effective approach to data mining and knowledge discovery from hybrid data including categorical values and numerical values. However, its time-consumption is very intolerable to analyze data sets with large scale and high dimensionality. Many heuristic fuzzy-rough feature selection algorithms have been developed however, quite often, these methods are still computationally time-consuming. For further improvement, we propose an accelerator, called forward approximation, which combines sample reduction and dimensionality reduction together. The strategy can be used to accelerate a heuristic process of fuzzy-rough feature selection. Based on the proposed accelerator, an improved algorithm is designed. Through the use of the accelerator, three representative heuristic fuzzy-rough feature selection algorithms have been enhanced. Experiments show that these modified algorithms are much faster than their original counterparts. It is worth noting that the performance of the modified algorithms becomes more visible when dealing with larger data sets.