An approach to a priori assessment of fuzzy classification models in monitoring tasks

The article addresses the problems of using automation tools to perform monitoring and management tasks applicable to assessing the quality of fuzzy classification models, where the classification procedure is implemented on the basis of knowledge (rules) in the absence of the training set. An approach is proposed to obtain a priori assessments of the classification quality based on the study of the used model sensitivity to changes in the values of internal parameters during the corresponding modeling. The interpretation of the modeling results in the form of risk assessment caused by the self-imperfection of the classification models is obtained. The article provides an example of a fuzzy classification model based on a comparison of the current state of a monitoring object described using fuzzy features with a set of predefined typical states, which form corresponding fuzzy equal (close) states (monitoring situations). The comparison is carried out using the fuzzy implication operation provided that the required reliability is met. The example of this model demonstrates how the type of implication operation, as well as the internal features of the model, affect the results of classification, and appropriate indicators are proposed, which are both an interpretation of generally accepted indicators for assessing the classification quality, and unique, inherent in the considered model. Computational experiments were carried out, which made it possible to obtain graphs of changes in classification quality assessment indicators for the considered model and its modification and visualize the influence of internal parameters of the model on the results of its application. A number of indicators are proposed that allow for an a priori assessment of the risks arising from the application of the model before its actual application.