A Hybrid Feature Selection Algorithm: Combination of Symmetrical Uncertainty and Genetic Algorithms
Bai-Ning Jiang, Xiangqian Ding, Lintao Ma, Ying He, Tao Wang, Weiwei Xie · 2008
Abstract A hybrid feature selection method called SU-GA-W is proposed to make full use of advantages of filter and wrapper methods. This method falls into two phases. The filter phase removes features with lower SU and guides the initialization of GA population; the wrapper phase searches the final feature subset. The effectiveness of this algorithm is demonstrated on various data sets.