Attribute reduction using backward elimination algorithm

Attribute reduction of an information system is a key problem in rough set theory and its applications. This paper proposes a new feature selection mechanism based on backward elimination algorithm to solve the attribute reduction problem in roughest theory. It is the most promising technique in the Rough set theory, a new mathematical approach to reduct car and cancer dataset using backward elimination algorithm. This technique was originally proposed to avoid the calculation of discernibility functions or positive regions, which can be computationally expensive. And more number of reduct is possible to compare forward selection algorithm. This paper analyses the efficiency of the proposed backward elimination algorithm against forward selection algorithm. The experiments are carried out on car data sets of UCI machine learning repository and the real breast cancer data set.