×
Methodology of Measurement Intellectualization based on Regularized Bayesian Approach in Uncertain Conditions

Authors

Svetlana Prokopchina1 and Veronika Zaslavskaia2, 1Financial University under the Government of the Russian Federation, Russia, 2Zello Russia, "Artificial Intelligence" Committee of "RUSSOFT" Association, Russia

Abstract

Modern measurement tasks are confronted with inherent uncertainty. This significant uncertainty arises due to incomplete and imprecise knowledge about the models of measurement objects, influencing factors, measurement conditions, and the diverse nature of experimental data. This article provides a concise overview of the historical development of methodologies aimed at intellectualizing measurement processes in the context of uncertainty. It also discusses the classification of measurements and measurement systems. Furthermore, the fundamental requirements for intelligent measurement systems and technologies are outlined. The article delves into the conceptual aspects of intelligent measurements, which are rooted in the integration of metrologically certified data and knowledge. It defines intelligent measurements and establishes their key properties. Additionally, the article explores the main characteristics of soft measurements and highlights their distinctions from traditional deterministic measurements of physical quantities. The emergence of cognitive, systemic, and global measurements as new measurement types is discussed. In this paper, we offer a comprehensive examination of the methodology and technologies underpinning Bayesian intelligent measurements, with a foundation in the regularizing Bayesian approach. This approach introduces a novel concept of measurement, where the measurement problem is framed as an inverse problem of pattern recognition, aligning with Bayesian principles. Within this framework, innovative models and coupled scales with dynamic constraints are proposed. These dynamic scales facilitate the development of measurement technologies for enhancing the cognition and interpretation of measurement results by measurement systems. This novel type of scale enables the integration of numerical data (for quantifiable information) and linguistic information (for knowledge-based information) to enhance the quality of measurement solutions. A new set of metrological characteristics for intelligent measurements is introduced, encompassing accuracy, reliability (including error levels of the 1st and 2nd kind), dependability, risk assessment, and entropy characteristics. The paper provides explicit formulas for implementing the measurement process, complete with a metrological justification of the solutions. The article concludes by outlining the advantages and prospects of employing intelligent measurements. These benefits extend to solving practical problems, as well as advancing and integrating artificial intelligence and measurement theory technologies.

Keywords

Measurement Theory, Bayesian approach, Uncertainty.