Random set framework for context-based classification.

摘要

Pattern classification is a fundamental problem in intelligent systems design. Many different probabilistic, evidential, graphical, spatial-partitioning and heuristic models have been developed to automate classification. In some applications, there are unknown, overlooked, and disregarded factors that contribute to the data distribution, such as environmental conditions, which hinder classification.Most approaches do not account for these conditions, or factors, that may be correlated with sets of data samples. However, unknown or ignored factors may severely change the data distribution making it difficult to use standard classification techniques. Even if these variable factors are known, there may be a large number of them. Enumerating these variable factors as parameters in clustering or classification models can lead to the curse of high dimensionality or sparse random variable densities. Some Bayesian approaches that integrate out unknown parameters can be extremely time consuming, may require a priori information, and are not suited for the problem at hand. Better methods for incorporating the uncertainty due to these factors are needed.We propose a novel context-based approach for classification within a random set framework. The proposed model estimates the posterior probability of a class and context given both a sample a set of samples, as opposed to the standard method of estimating the posterior given a sample. This conditioned posterior is then expressed in terms of priors, likelihood functions and probabilities involving both a sample and a set of samples. Particular attention is focused on the problem of estimating the likelihood of a set of samples given a context. This estimation problem is framed in a novel way using random sets. Three methods are proposed for performing the estimation: possibilistic, evidential, and probabilistic. These methods are compared and contrasted with each other and with existing approaches on both synthetic data and extensive hyperspectral data sets used for minefield detection algorithm development.Results on synthetic data sets identify the pros and cons of the possibilistic, evidential and probabilistic approaches and existing approaches. Results on hyperspectral data sets in indicate that the proposed context-based classifiers perform better than some state-of-the-art, context-based and statistical approaches.