TY - JFULL AU - A. Thomas and B. John Oommen PY - 2012/1/ TI - Order Statistics-based “Anti-Bayesian“ Parametric Classification for Asymmetric Distributions in the Exponential Family T2 - International Journal of Computer and Information Engineering SP - 1794 EP - 1803 VL - 6 SN - 1307-6892 UR - https://publications.waset.org/pdf/14578 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 72, 2012 N2 - Although the field of parametric Pattern Recognition (PR) has been thoroughly studied for over five decades, the use of the Order Statistics (OS) of the distributions to achieve this has not been reported. The pioneering work on using OS for classification was presented in [1] for the Uniform distribution, where it was shown that optimal PR can be achieved in a counter-intuitive manner, diametrically opposed to the Bayesian paradigm, i.e., by comparing the testing sample to a few samples distant from the mean. This must be contrasted with the Bayesian paradigm in which, if we are allowed to compare the testing sample with only a single point in the feature space from each class, the optimal strategy would be to achieve this based on the (Mahalanobis) distance from the corresponding central points, for example, the means. In [2], we showed that the results could be extended for a few symmetric distributions within the exponential family. In this paper, we attempt to extend these results significantly by considering asymmetric distributions within the exponential family, for some of which even the closed form expressions of the cumulative distribution functions are not available. These distributions include the Rayleigh, Gamma and certain Beta distributions. As in [1] and [2], the new scheme, referred to as Classification by Moments of Order Statistics (CMOS), attains an accuracy very close to the optimal Bayes’ bound, as has been shown both theoretically and by rigorous experimental testing. ER -