Functional data classification using the rotation forest method combined with the patch selection

Functional data classification is one of the major challenges in the field of functional data analysis. In this article, we propose the Rotation Forest method combined with the patch selection for functional data classification. The Rotation Forest method first divides the feature matrix into disjoint subsets. Feature extraction is performed on each subset by principal component analysis. All the coefficients of the principal components are retained and reordered to form a new feature matrix to do feature extraction for the training dataset. The patch selection is to connect the pixels in each patch in an orderly manner to form a sub-vector, then each sub-vector for each patch is connected according to the order of the patches to form a feature vector for each subject. This way, the patterns contained in the two-dimensional patches are transformed into information embedded in the one-dimensional feature vectors to be analyzed more efficiently. The new method combines the advantages of both the Rotation Forest method and the patch selection. It generates competitive prediction errors for new observations. Extensive simulations and a real dataset consisting of 372 brain image datasets suggest the superiority of this approach over existing methods.