UNLABELLED: PCP (Pattern Classification Program) is an open-source machine learning program for supervised classification of patterns (vectors of measurements). The principal use of PCP in bioinformatics is design and evaluation of classifiers for use in clinical diagnostic tests based on measurements of gene expression. PCP implements leading pattern classification and gene selection algorithms and incorporates cross-validation estimation of classifier performance. Importantly, the implementation integrates gene selection and class prediction stages, which is vital for computing reliable performance estimates in small-sample scenarios. Additionally, the program includes automated and efficient model selection (optimization of parameters) for support vector machine (SVM) classifier. The distribution includes Linux and Windows/Cygwin binaries. The program can easily be ported to other platforms. AVAILABILITY: Free download at http://pcp.sourceforge.net

Dimension reduction is the process of transforming multidimensional vectors into a low-dimensional space. In pattern recognition, it is often desired that this task be performed without significant loss of classification information. The Bayes error is an ideal criterion for this purpose; however, it is known to be notoriously difficult for mathematical treatment. Consequently, suboptimal criteria have been used in practice. We propose an alternative criterion, based on the estimate of the Bayes error, that is hopefully closer to the optimal criterion than the criteria currently in use. An algorithm for linear dimension reduction, based on this criterion, is conceived and implemented. Experiments demonstrate its superior performance in comparison with conventional algorithms.>

Dimension reduction is a process of transforming the multidimensional observations into low-dimensional space. In pattern recognition this process should not cause loss of classification accuracy. This goal is best accomplished using Bayes error as a criterion for dimension reduction. Since the criterion is not usable for practical purposes, the authors suggest the use of the k-nearest neighbor estimate of the Bayes error instead. They experimentally demonstrate the superior performance of the linear dimension reduction algorithm based on this criterion, as compared to the traditional techniques.>

Studies the k-nearest neighbor density estimation with fixed k, and its use in Bayes error estimation as proposed by Fukunaga and Hummels (1987). The authors arrive at a modified formula for a density estimator by analyzing the bias and variance expressions. The authors use four modifications of this formula for Bayes error estimation, and perform controlled experiments on Gaussian data in order to compare its performance with the original method. Given experimental results justify the proposed modifications.>

Deals with the interpretation and classification of optical images of three-dimensional scenes. An experimental system is described in which certain features, called Zernike moment invariants, are extracted from binary images and then used for automatic classification. Up to 20 features are used to describe binary images of five object types. The authors managed to achieve complete separation of the classes using 20 features. The Zernike invariants approach to the binary image analysis has proved to be a successful tool in object recognition.>

The minimal dimension of sufficient continuous statistics for a finite family of continuous probability density functions is determined. The relation between sufficient statistics and optimal statistics in the context of pattern recognition systems is studied, and the application of the main result to the case of exponential families is discussed.>