A framework of rough reducts optimization based on PSO/ACO hybridized algorithms

Rough reducts has contributed significantly in numerous researches of feature selection analysis. It has been proven as a reliable reduction technique in identifying the importance of attributes set in an information system. The key factor for the success of reducts calculation in finding minimal reduct with minimal cardinality of attributes is an NP-Hard problem. This paper has proposed an improved PSO/ACO optimization framework to enhance rough reduct performance by reducing the computational complexities. The proposed framework consists of a three-stage optimization process, i.e. global optimization with PSO, local optimization with ACO and vaccination process on discernibility matrix.