FUZZY ROBUST ESTIMATES OF LOCATION AND SCALE PARAMETERS OF A FUZZY RANDOM VARIABLE

A random variable is a variable whose components are random values. To characterise a random variable, the arithmetic mean is widely used as an estimate of the location parameter, and variation as an estimate of the scale parameter. The disadvantage of the arithmetic mean is that it is sensitive to extreme values, outliers in the data. Due to that, to characterise random variables, robust estimates of the location and scale parameters are widely used: the median and median absolute deviation from the median. In real situations, the components of a random variable cannot always be estimated in a deterministic way. One way to model the initial data uncertainty is to use fuzzy estimates of the components of a random variable. Such variables are called fuzzy random variables. In this paper, we examine fuzzy robust estimates of location and scale parameters of a fuzzy random variable: fuzzy median and fuzzy median of the deviations of fuzzy component values from the fuzzy median.

Bi-Level Programming for Earning Management in Imprecise and Random Environments

Organizations striving in today's environment of active technological and business transformations are confronted with the difficulties of “twofoldness,” that is, performing efficiently in the present while innovating effectively for the future. Administrators inside these organizations not only have to concentrate on the business benefit and profitability of each of their authorized commodities and services but must also guarantee their ability to introduce into next-generation contributions that output properties that will maintain and even enhance their renewed global competitiveness. The surprisingly fast breakdown of so many probably great companies over the last decade gives an extensive declaration to the consequence of accomplishing this dualism. In this chapter, to deal with this dualism, the authors consider a fuzzy stochastic bi-level programming problem in the mathematical models. The fuzziness and randomness concept has been taken care of by the fuzzy random variable as the parameter of the bi-level programming problem. A two-stage approach has been defined to solve the problem.

FRand: MATLAB Toolbox for Fuzzy Random Number Simulation

Context: This paper presents a MATLAB code implementation and the GUI (General User Interface) for fuzzy random variable generation. Based on previous theoretical results and applications, a MATLAB toolbox has been developed and tested for selected membership functions. Method: A two–step methodology was used: i) a MATLAB toolbox was implemented to be used as interface and ii) all .m functions are available to be used as normal code. The main goal is to provide graphical and code–efficient tools to users. Results: The main obtained results are the MATLAB GUI and code. In addition, some experiments were ran to evaluate its capabilities and some randomness statistical tests were successfully performed. Conclusions: Satisfactory results were obtained from the implementation of the MATLAB code/toolbox. All randomness tests were accepted and all performed experiments shown stability of the toolbox even for large samples (>10.000). Also, the code/toolbox are available online. Acknowledgements: The authors would like to thank to the Prof. M Sc. Miguel Melgarejo and Prof. Jos´e Jairo Soriano–Mendez sincerely for their interest and invaluable support, and a special gratefulness is given to all members of LAMIC.

Algebra of Fuzzy Random Variable and its Application to Science and Engineering Problem- Radon Transport from Soil into Building

The theme of this paper is to bring out the mathematical details of fuzzy random variable and its application to model radon transport from soil into buildings. The physical processes that influence radon transport are advection and diffusion. Parameters associated with the governing partial differential equation describing radon transport from soil into buildings are radon diffusion coefficient and advective velocity of radon in air. Both the parameters are imprecise. Imprecision of these parameters is addressed as fuzzy random variable due to presence of inherent randomness within their fuzziness. Handling fuzziness within randomness is an innovative concept of computation to quantify the uncertainty of any physical system. Paper presents the mathematical structure (algebra) of fuzzy random variables. The concept of fuzzy randomness is implemented in developing radon transport model. Numerical solution of radon transport model with fuzzy random parameters is obtained by explicit forward time central space finite difference method. Support, uncertainty index, possibility, necessity and credibility of the spatial and temporal behaviour of the random behaviour of radon concentration are also computed to explore the concept and role of the fuzzy randomness in decision making issue

Functional and operational risk as a criterion for assessing the durability of an autonomous energy system

The article presents new models and methods for estimating the residual service life of an autonomous energy system, using the functional operational risk criterion (FOR). The purpose of the article is to demonstrate a new method of durability evaluation using the fuzzy logic and soft computing framework. Durability in the article is understood as a complex property directly adjacent to the complex property of system resilience, as understood in the Western practice of assessing and ensuring the reliability of technical systems. Due to the lack of reliable homogeneous statistics on system equipment failures and recoveries, triangular fuzzy estimates of failure and recovery intensities are used as fuzzy functions of time based on incomplete data and expert estimates. The FOR in the model is the possibility for the system availability ratio to be below the standard level. An example of the evaluation of the FOR and the residual service life of a redundant cold supply system of a special facility is considered. The transition from the paradigm of structural reliability to the paradigm of functional reliability based on the continuous degradation of the technological parameters of an autonomous energy system is considered. In this case, the FOR can no longer be evaluated by the criterion of a sudden failure, nor is it possible to build a Markov’s chain on discrete states of the technical system. Assuming this, it is appropriate to predict the defi ning functional parameters of a technical system as fuzzy functions of a general form and to estimate the residual service life of the technical system as a fuzzy random variable. Then the FOR is estimated as the possibility for the residual life of the technical system to be below its warranty period, as determined by the supplier of the equipment.