The particle filter (PF) is a novel technique that has sufficiently good estimation results for the nonlinear/non-Gaussian systems. However, PF is inconsistent that caused mainly by loss of particle diversity in resampling step and unknown a priori knowledge of the noise statistics. This paper introduces a new modified particle filter called adaptive unscented particle filter (AUPF) to overcome th...

Two sides of a finite marriage market engage in costly investment and are then matched assortatively. The purpose of the investment is solely to improve the quality of the match that the trader can attain in the second stage. The paper studies the limits of equilibrium of these finite matching games as the number of traders gets large. It is shown that mixed Nash equilibria in the finite games ...

A multiple representation database contains several geographic datasets defined at different resolutions covering the same area. Objects within the different datasets that represent the same real world feature are connected. This paper presents a method to build a multiple representation database by automatically creating these connections. First an analysis is made of how cartographic generali...

This paper presents new results about the robustness of invariantintegration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as “powerbias subtraction” for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to mismatching vocaltract length training-t...

The performance of least squares method ca'n be improved by changing the error metric so that points which lie far from the bulk of data do not influence the final value—that is to reject the outliers. In this paper, the combination of two robust estimators are used to obtain motion parameters of a camera from matched image features. Results obtained show that the robust estimator has the abili...

Modern financial practice depends heavily on mathematics and a correspondingly large theory has grown up to meet this demand. This paper focuses on the use of matched asymptotic expansions in option pricing; it presents illustrations of the approach in ‘plain vanilla’ option valuation, in valuation using a fast mean-reverting-stochastic volatility model, and in a model for illiquid markets. A t...

This paper presents a parameterized version of the stochastic information gradient (SIG) algorithm, in which the error distribution is modeled by generalized Gaussian density (GGD), with location, shape, and dispersion parameters. Compared with the kernel-based SIG (SIGKernel) algorithm, the GGD-based SIG (SIG-GGD) algorithm does not involve kernel width selection. If the error is zero-mean, th...

Detection of neural action potentials in background noise is the fist step to many neural researches. Matched filter is a simple and effective action potential detector, but it is found to be too sensitive to the amplitudes differences among the action potentials to be useful in general applications. By introducing adjust function, an improved matched filter detector is proposed. The detector e...

This report discusses the implementation of the Radon transform in the Analysts’ Detection Support System (ADSS) environment using non-equispaced Discrete Fourier Transforms (DFTs). It provides an analysis and experimental results for discretisation error and the use of matched filtering to enhance peaks in the transform. APPROVED FOR PUBLIC RELEASE

The purpose of this study is to investigate the effect of one year of regular “LEGO” training on pupils’ performances in schools. The underlying pedagogical perspective is the constructivist theory, where the main idea is that knowledge is constructed in the mind of the pupil by active learning. The investigation has been made in two steps. The first step was before the training and the second ...