Investigating memetic algorithm in solving rough set attribute reduction

Attribute reduction is the problem of selecting a minimal subset from the original set of attributes. Rough set theory has been used for attribute reduction with much success. Since it is well known that finding a minimal subset is a NP-hard problem; therefore, it is necessary to develop efficient algorithms to solve this problem. In this work, we propose a memetic algorithm-based approach inside the rough set theory which is a hybridisation of genetic algorithm and simulated annealing. The proposed method has been tested on UCI data sets. Experimental results demonstrate the effectiveness of this memetic approach when compared with previous available methods. Possible extensions upon this simple approach are also discussed.