1,721,007 research outputs found
Beyond the opposition between the Bayesian and the frequentistic views in measurement
No full textThe probabilistic modelling of measurement systems is discussed, showing how it provides a practical and effective way for addressing uncertainty evaluation, that does not require any commitment to specific philosophical schools, such as the frequentistic and the Bayesian ones. Firstly, different ways of modelling the same measuring device are compared and discussed, considering both the designer's and the user's standpoints. Then philosophical issues concerning both the nature of probability and the probabilistic inferences related to the measurement process are considered, in the perspective of this model-based approach. Applications to education and to the revision of international guides for measurement are finally addressed
Probabilistic measurement modelling may overcome the opposition between the Bayesian and the frequentistic views
No full text
Tuning of ARMA models for mono-modal sea spectrum estimation
No full textThe paper focuses on the tuning of Auto Regressive Moving Average (ARMA) models aimed at describing the spectral behaviour of sea wave elevation time series. The analysis considers mono-modal sea states, mainly due to the wind effect. The main problem related to the estimation of such models, starting from the wave elevation time series, concerns the tuning of the parameters involved in the identification algorithms. Indeed, the value of some parameters must be chosen by the user and these choices strongly affect the goodness of the estimates. Here, some of these parameters are considered, highlighting their effect on the goodness of the fit, and indications about how to set their values for applications related to mono-modal sea states are presented. The results are fully discussed considering a reference case study and a procedure to tune the model is proposed
Probabilistic decision making for the implementation of the Measuring Instrument Directive
No full textThe approval of the European Measuring Instrument Directive on April 2004 renews completely the legal metrology sector, proposing a "new approach" aiming to technical normalization and harmonization and toward a "global approach" to evaluation and conformity. According to the principles of the "new approach" regulatory model, the Directive leaves to the manufacturer itself to adopt proper technical solutions, giving only very essential requirements, without going in any detail. Moreover new certification procedures based on Quality Systems are available and there is no indication regarding the procedure to verify product conformity. In the present paper, after a brief discussion regarding the MID philosophy, a probabilistic approach to conformity assessment is presented. The proposed approach covers a set of open issues such as the measurement uncertainty due to the influence of operating conditions, the management of the risk due to conformity decision based upon a set of measurement results, the costs of instrument uncertainty and eventually non conformity for the manufacturer and instrument user. The approach is supported by a set of software codes enabling an easy and user friendly application. All these aspects are presented with reference to the case of water meters, considering both the end of production acceptance tests and the operative situation of the meter
Power measurement in maximum height jump
No full textAthletes performance can be evaluated through different tests generally specifically designed to consider a specific quality. When dealing with explosive power, maximum height jump is widely used. Athlete's performance may be evaluated through different parameters such as elevation differential, excursion of the center of mass in vertical direction, or in more detailed way, through a power measurement. A few methods can be considered for this purpose and the aim of this paper is to compare them, providing guidelines for their application and for measurement-uncertainty evaluation, as far as possible for such a gesture, considering the complexity of the measurement
A formal theory of the measurement system
No full textMeasurement aims at obtaining a numerical description of objects/events/persons in the real world by means of a measuring system. Measurement is widely used as a key way for obtaining high quality information from the real world, across disciplines. In the present day, there is growing consensus in holding that measurement is characterized by the use of something that qualifies as a “measuring system”. Therefore, we discuss sufficient conditions for an empirical system to qualify as a measuring system and we present a formal model of the measuring system, in terms of empirical relations among objects to be measured and the measuring device. The theory applies to all the main structures of metrological interest – order, difference, intensive and extensive, and we hope that this may help to fill a gap in these studies. We also briefly address practical applications of the theory, including calibration, modelling of measuring devices and performance statement
Evaluation of the uncertainty due to dynamic effects in linear measuring devices
No full textThe evaluation of the uncertainty due to systematic dynamic effects is addressed. When high dynamic performance is required, they should be compensated, by solving the associated inverse dynamic problem. When
instead they are considered compatible with the target uncertainty, they may be simply included in the uncertainty budget. Furthermore, even in the case of dynamic compensation, a residual uncertainty remains, due to
the imperfect compensation, and should be evaluated. Therefore, simple formulas are presented here, applicable
to many classes of dynamic phenomena, including periodic, harmonic, transitory impulsive and stochastic stationary ones
Probability theory as a logic for modelling the measurement process
No full textThe problem of the nature of probability has been drawn to the attention of the measurement community in the comparison between the frequentist and the Bayesian views, in the expression and the evaluation of measurement uncertainty. In this regard, it is here suggested that probability can be interpreted as a logic for developing models of measurement capable of accounting for uncertainty. This contributes to regard measurement theory as an autonomous discipline, rather than a mere application field for statistics. Following a previous work in this line of research, where only measurement representations, through the various kinds of scales, were considered, here the modelling of the measurement process is discussed and the validity of the approach is confirmed, which suggests that the vision of probability as a logic could be adopted for the entire measurement theory. With this approach, a deterministic model can be turned into probabilistic by simply shifting from a deterministic to a probabilistic semantic
Effects of measurement conditions on the projection of faces in the eigenface space: An experimental investigation
No full textAutomatic face recognition is vital for many security applications. From a scientific standpoint, it may be considered a classification process, based on the measurement of a "face", where a face is a property of a person, representable as a surface in a three-dimensional physical space. In this perspective, face measurement may be considered as derived from length measurement. The space of the measurand is theoretically an infinite dimensional one: to manage it, a two dimension projection may be considered and a suited eigenvector representation of reduced dimension may be looked for. In this context, this is called an eigenface approach. From an experimental standpoint, when operating in the field, such measurement is affected mainly by the surrounding environment and by the lack of collaboration by the investigated subject. In the current vast technical literature, the performance of different recognition procedures is investigated mainly in respect of the overall performance. By converse the pro osed approach closely follows the pattern of the metrological characterisation, viz. calibration, of a measuring instrument and consists of a detailed analysis of the effects of some critical influence quantities. We have first designed and performed an extensive experimentation aimed at identifying the most critical influence quantities, such as the dimension of the face in the image (scale), the orientation of the face, the expression and illumination conditions. Than their influence has been linearly modelled and the parameters have been evaluated form a large set of recorded images controlling the influence quantities values. Lastly, some compensation of the systematic effects has been attempted, which has proved to be useful
- …
