Feature selection using the Kalman filter for classification of multivariate data

A Kalman filter is developed as a feature selection method and classifier for multivariate data. Three near-infrared (NIR) data sets and a pollution data set are analyzed. For the two most difficult data sets (data sets 1 and 3), the Kalman filter successfully selects the wavelengths which lead to very good results with a correct classification rate (CCR) equal to one. These results are much better than the best results obtained from regularized discriminant analysis (RDA) using Fourier transform (FT), principal component regression (PCA) and univariate feature selection methods as the variable reduction methods. For the second data set which consists of more than two classes, the Kalman filter gives similar results (CCR = 1) to those of RDA. For the pollution data set (data set 4), the Kalman filter gives similar results to partial least-squares (PLS) using fewer variables. The disadvantage of the Kalman filter is that it needs more memory and more computing time than PLS. The potential hazards of overfitting have been considered.