To read the full-text of this research, you can request a copy directly from the author.


Modern measurement problems are solved in conditions of uncertainty Significant information uncertainty is caused by the lack of complete and accurate knowledge about the models of measurement objects, influencing factors, measurement conditions, as well as a variety of experimental data. The article briefly discusses the history of the development of methods for the intellectualization of measurement processes, which are also focused on the situation of uncertainty and the classification of measurements and measurement systems. The basic requirements for intelligent measurement systems and technologies and their distinctive properties are formulated. The article discusses the conceptual aspects of intelligent measurements as measurements based on the integration of metrologically certified data and knowledge, and defines intelligent measurements. The properties of intelligent measurements are defined. The article discusses the main properties of soft measurements and their differences from deterministic classical measurements of physical quantities. Cognitive, systemic, and global dimensions are designated as new types of dimensions. In this paper, the methodology and technologies of Bayesian intelligent measurements based on the regularizing Bayesian approach are considered in detail. In conclusion, the main characteristics that should be inherent in intelligent measurement systems, the advantages and prospects of using intelligent measurements both for solving applied problems and for the development and integration of artificial intelligence technologies and measurement theory are formulated.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

Full-text available
In the article, the possibilities of using neural networks constructed on neurons with an activation function based on the Bayes' theorem for intelligent processing of measurement results are discussed. In the authoring Bayesian model of a neuron, the weight vector is used as a reference pattern, the input signals of the neuron are interpreted as evidence in favor of two alternative hypotheses: compliance and noncompliance with the condition of the neuron activation. The output signal of the neuron is formed on the basis of the posterior probability distribution of hypotheses calculated using the Bayes' rule. The ability of the Bayesian neuron to recognize fuzzy graphic images covered with a raster grid is shown. An illustrative example of processing the results of measuring the surface temperature of the mechanism in order to detect potential malfunctions in places of overheating is given.
ResearchGate has not been able to resolve any references for this publication.