-Fuzzy inference systems are widely used in various areas of human activity. Their most widespread use lies in the field of fuzzy control of technical devices of different kind. Another direction of using fuzzy inference systems is modelling and assessment of different kind of risks under insufficient or missing objective initial data. Fuzzy inference is concluded by the procedure of defuzzification of the resulting fuzzy sets. A large number of techniques for implementing the defuzzification procedure are available nowadays. The paper presents a comparative analysis of some widespread methods of fuzzy set defuzzification, and proposes the most appropriate methods in the context of ecological risk assessment.

-Being able to evaluate risks is an important task in many areas of human activity: economics, ecology, etc. Usually, environmental risk assessment is carried out on the basis of multiple and sometimes conflicting factors. Using multiple criteria decision-making (MCDM) methodology is one of the possible ways to solve the problem. Analytic hierarchy process (AHP) is one of the most commonly used MCDM methods, which combines subjective and personal preferences in the risk assessment process. However, the AHP involves human subjectivity, which introduces vagueness type of uncertainty and requires the use of decision making under those uncertainties. In this paper, work with uncertainty is considered using fuzzy-based techniques. The paper also analyses the ecological risk assessment towards human health in case of gaseous substance escape at a chemical factory using the fuzzy analytical hierarchy process.

No abstract

Any data in an implicit form contain information of interest to the researcher. The purpose of data analysis is to extract this information. The original data may contain redundant elements and noise, distorting these data to one degree or another. Therefore, it seems necessary to subject the data to preliminary processing. Reducing the dimension of the initial data makes it possible to remove interfering factors and present the data in a form suitable for further analysis. The paper considers an approach to reducing the dimensionality of the original data based on principal component analysis.

The aim of the paper is to examine procedures of descriptive statistics in the case when the values of relevant attribute in a sample are set in the form of fuzzy categories. The paper provides alternative definitions of a fuzzy random variable, and describes corresponding procedures for calculating the analogues of location and spread parameters. The paper also presents some illustrative examples and analyses the results obtained. Based on the result analysis, practical recommendations are given on how to use procedures of fuzzy statistics.