Proceedings of the 2006 IEEE International Workshop on Advanced Methods for Uncertainty Estimation in Measurement (AMUEM 2006)

RFVs are variables defined within the theory of evidence, which are suitable for the representation of measurement results together with the associated uncertainty, whichever is its nature. This paper proposes a suitable mathematics for processing RFVs, which considers the different nature of the uncertainty effects. This allows to process measurement algorithms in terms of RFVs, so that the final... View full abstract»

A correct representation of uncertainty in measurement is crucial in many applications. Statistical approach sometimes is not the best choice, especially when the knowledge of the measurement process refers only to the support of the values and does not allow a correct assumption on the probability density function (pdf) of the measured variable. In this paper we present an approach that uses the ... View full abstract»

The maximum entropy approach is a flexible and powerful tool for assigning a probability distribution to a measurable quantity treated as a random variable, subjected to known moment constraints. The aim of this paper is to describe how the principle of maximum entropy may be used to transform information about the value of a quantity into a probability density function reflecting exactly that inf... View full abstract»

At the application level, it is important to be able to define around the measurement result an interval which will contain an important part of the distribution of the measured values, that is, a confidence interval. This practice acknowledged by the ISO guide is a major shift from the probabilistic representation as a confidence interval represents a set of possible values for a parameter associ... View full abstract»

The Monte Carlo method is used to analyze the propagation of uncertainty through dynamic systems by means of simulation. To this purpose a specifically designed and implemented simulation engine is presented and some results are discussed View full abstract»

This paper proposes an innovative approach to the design of algorithms for indirect measurements based on a polynomial chaos observer (PCO). A PCO allows the introduction and management of uncertainty in the process. The structure of this algorithm is based on the standard closed-loop structure of an observer originally introduced by Luenberger. This structure is here extended to include uncertain... View full abstract»

A model of comparison loss in microwave power meter calibration is considered in the case when the standard power meter used for calibration and the signal generator to which this meter and the meter to be calibrated are connected are reflectionless. The uncertainty associated with an estimate of the model output quantity, viz., the ratio of the power absorbed by the meter being calibrated and tha... View full abstract»

Vision-based tracking is concerned with the recovery of position and orientation data of moving objects based on visual input provided by one or more cameras. This paper describes a framework to handle geometric parameter uncertainties within a monocular outside-in vision-based tracking application. We present a sensor model - the stochastic camera - that is capable to take parameter calibration u... View full abstract»

The problem of estimating model uncertainty of learning machines (LMs) is becoming a subject of great interest because of the wide application of such kind of methodologies for solving real-world problems. In this work we will provide a general overview on estimating and controlling uncertainity of LMs, by describing the algorithms, the theory and the empirical methods used to obtain a robust esti... View full abstract»

Significant attention is paid to common questions relative to the methods of the expression of the uncertainty of measurements and the estimates of the results of the definition of the environmental characteristics of global objects. The bases analysis of uncertainty and its main sources are considered. Peculiarities of the expression of uncertainty and the variants of its estimation in internatio... View full abstract»

In this paper, the parametric estimation of additive white Gaussian noise is considered, when available data are obtained from a quantized noisy stimulus. The Cramer-Rao lower bound is derived, and the statistically efficiency of a maximum likelihood parametric estimator is discussed, along with the estimation algorithm proposed in IEEE standard IEEE 1241 View full abstract»

Many measurements models are formalized in terms of a stochastic process relating its solution to some given observables. The expression of the measurement uncertainty for the solution requires the determination of its (joint) pdf evaluated in an assigned time window. Recently, polynomial chaos (PC) theory has been widely recognized as a promising technique in order to address the problem. However... View full abstract»

The paper deals with the analytical expression of the uncertainty on edge localization in image analysis applications. The analysis carried out relates analytically the uncertainty affecting the intensity of input image to the output uncertainty of edge detectors based on first and second derivative proprieties. The theoretical results are validated through experimental tests performed on real ima... View full abstract»