In this paper, we proposed a new feature selection scheme, the incremental forward feature selection, which is inspired by incremental reduced support vector machines. In our method, a new feature will be added into the current selected feature subset if it will bring in the most extra information. We measure this information by using the distance between the new feature vector and the column space spanned by current feature subset. The incremental forward feature selection scheme can exclude

more »

... ghly linear correlated features which provide redundant information and might vectors unless otherwise specified or transposed to a row vector by a prime superscript . The inner product of two vectors x, z ∈ R n will be denoted by x z and the p-norm of x will be denoted by x p . A column vector of ones of arbitrary dimension will be denoted by 1. The base of the natural logarithm will be denoted by e. This paper is organized as follows. Section 2 gives an overview of filter model for feature selection. In section 3, we describe the wrapper model for feature selection. The experiments and numerical results for different feature selection approaches are stated in section 4. Section 5 concludes the paper. 4