Weak-lensing searches for galaxy clusters are plagued by low completeness and purity, severely limiting their usefulness for constraining cosmological parameters with the cluster mass function. A significant fraction of ‘false positives’ are due to projection of large-scale structure and as such carry information about the matter distribution. We demonstrate that by constructing a “peak functio...

Initially, multiple-output Gaussian processes models (MOGPs) were constructed as linear combinations of independent, latent, single-output Gaussian processes (GPs). This resulted in cross-covariance functions with limited parametric interpretation, thus conflicting with single-output GPs and their intuitive understanding of lengthscales, frequencies and magnitudes to name but a few. On the cont...

The time relationships which characterize the intermedia synchronization in a multimedia stream affect network performance. For this purpose in this paper a new parameter is introduced, here referred to as the Intermedia Synchronization Index (ISI), which measures the intermedia relationships in a multimedia stream. The parameter is defined as the cross-covariance between the monomedia streams ...

This paper addresses the problem of estimation when the cross-correlation in the errors between diierent random variables are unknown. A new data fusion algorithm, the Covariance Intersection Algorithm(CI), is presented. It is proved that this algorithm yields consistent estimates irrespective of the actual correlations. This property is illustrated in an application of decentralised estimation...

The intertemporal capital asset pricing model of Merton (1973) is examined using the dynamic conditional correlation (DCC) model of Engle (2002). The mean-reverting DCC model is used to estimate a stock’s (portfolio’s) conditional covariance with the market and test whether the conditional covariance predicts time-variation in the stock’s (portfolio’s) expected return. The risk-aversion coeffic...

An optimal mean-square fusion formulas with scalar and matrix weights are presented. The relationship between them is established. The fusion formulas are compared on the continuous-time filtering problem. The basic differential equation for cross-covariance of the local errors being the key quantity for distributed fusion is derived. It is shown that the fusion filters are effective for multi-...

Tangle machines are a topologically inspired diagrammatic formalism to describe information flow in networks. This paper begins with an expository account of tangle machines motivated by the problem of describing ‘covariance intersection’ fusion of Gaussian estimators in networks. It then discusses learning tangle machines from data. It concludes with two examples in which tangle machines tell ...

Earth science studies deal in general with multivariate and regionalized observations which may be compositional. Sometimes, it is interesting to know whether these data have to be divided into different subpopulations, a task usually performed by cluster analysis. This problem cannot be studied with traditional methods because samples are not independent. In that case, an extension of Ward’s c...

In this paper we present some recent results involving track level fusion in a distributed tracking environment. Successful fusion for the application requires that target state estimates and their error covariance matrices be available for processing. For this study, we are dealing with the limitations associated with several of the existing communication links (missing covariance) and how we ...

The 20th-century physics starts with Einstein and ends with Feynman. Einstein introduced the Lorentz-covariant world with E = mc. Feynman observed that fast-moving hadrons consist of partons which act incoherently with external signals. If quarks and partons are the same entities observed in different Lorentz frames, the question then is why partons are incoherent while quarks are coherent. Thi...