“…Attribute reduction [1,2,3,4,5], as a rough set based feature selection technology, has been widely investigated from various perspectives, and it has also been applied to many fields such as pattern recognition [6], decision analysis [7,8,9], data mining [10] and machine learning [11,12,13]. This is mainly because the data collected in real-world applications may contain redundant and irrelative attributes, these attributes may deteriorate the performance of learning algorithms [14,15], attribute reduction can effectively remove these attributes from data through searching a qualified reduct satisfying the intended constraint, and further reduce the dimensionality of data.…”