Maximally Informative Feature and Sensor Selection in Pattern Recognition Using Local and Global Independent Component Analysis
Authors: Lan, Tian1; Erdogmus, Deniz2
Source: The Journal of VLSI Signal Processing, Volume 48, Numbers 1-2, August 2007 , pp. 39-52(14)
Publisher: Springer
Abstract:
In pattern recognition, a suitable criterion for feature selection is the mutual information (MI) between feature vectors and class labels. Estimating MI in high dimensional feature spaces is problematic in terms of computation load and accuracy. We propose an independent component analysis based MI estimation (ICA-MI) methodology for feature selection. This simplifies the high dimensional MI estimation problem into multiple one-dimensional MI estimation problems. Nonlinear ICA transformation is achieved using piecewise local linear approximation on partitions in the feature space, which allows the exploitation of the additivity property of entropy and the simplicity of linear ICA algorithms. Number of partitions controls the tradeoff between more accurate approximation of the nonlinear data topology and small-sample statistical variations in estimation. We test the ICA-MI feature selection framework on synthetic, UCI repository, and EEG activity classification problems. Experiments demonstrate, as expected, that the selection of the number of partitions for local linear ICA is highly problem dependent and must be carried out properly through cross validation. When this is done properly, the proposed ICA-MI feature selection framework yields feature ranking results that are comparable to the optimal probability of error based feature ranking and selection strategy at a much lower computational load.Keywords: feature selection; sensor selection; mutual information; independent component analysis
Document Type: Research article
DOI: 10.1007/s11265-006-0026-5
Affiliations: 1: Email: lantian@bme.ogi.edu 2: Email: derdogmus@ieee.org

Click here for Page Help