Serhiy Shtovba

Ant Algorithms: Theory and Applications

This paper reviews the theory and applications of ant algorithms, new methods of discrete optimization based on the simulation of self-organized colony of biologic ants. The colony can be regarded as a multi-agent system where each agent is functioning independently by simple rules. Unlike the nearly primitive behavior of the agents, the behavior of the whole system happens to be amazingly reasonable. The ant algorithms have been extensively studied by European researchers from the mid-1990s. These algorithms have successfully been applied to solving many complex combinatorial optimization problems, such as the traveling salesman problem, the vehicle routing problem, the problem of graph coloring, the quadratic assignment problem, the problem of network-traffic optimization, the job-shop scheduling problem, etc. The ant algorithms are especially efficient for online optimization of processes in distributed nonstationary systems (for example, telecommunication network routing).

Analyzing the criteria for fuzzy classifier learning

In a fuzzy classifier, the maping “inputs–output” is described by the linguistic 〈If–then〉 rules, the antecedents in which contain the fuzzy terms “low,” “average,” “high,” and so on. To increase the correctness, the fuzzy classifier is learned by using experimental data. The problems with equal and different costs of various classification errors are discussed. A new criterion is offered for problems with undistinguishable types of errors, in addition to the two known criteria. A new one implies that the distance between the desired and real fuzzy results of classification for the cases of a wrong decision is weighted by the penalty factor. The learning criteria are generalized for problems of classification with the cost matrix. The conducted computer experiments on the wine recognition and heart disease diagnostics problems show that the best quality parameters of tuning fuzzy classifiers are achieved by a new learning criterion.

Fuzzy Rule Based System for Doagnosis of Stone Construction Cracks of Buildings

This paper presents the fuzzy expert system for intelligent support of decision making about cause of stone construction crack of building. The system is based on some linguistic expert expressions formalised by 9 fuzzy knowledge bases. Tuning of fuzzy rules by genetic algorithms provided a good concordance between real causes of cracks and results of decision making by the system.

Modeling of the human operator reliability with the aid of the Sugeno fuzzy knowledge base

Whenever a problem to predict and ensure reliability of human-machine systems is posed, regression models are usually applied to evaluate the influence of different factors on faultlessness, exactitude, operating speed, and other characteristics of the operator performance. The Sugeno fuzzy knowledge bases are proposed to model multi-factor relations of reliability. It is shown that this approach allows to combine expert knowledge and analytical relations of the parametric reliability theory in operator activity models. The expert component of a model provides with a comprehensive interpretation, while analytical input-output relations make a model compact. Appropriate examples are presented to demonstrate advantages of the Sugeno knowledge base application to describe multi-factor reliability relations of human operator.

A citation index with allowance for the implicit diffusion of scientific knowledge

This paper suggests a new scientometric index that estimates knowledge diffusion and has two constituents: the first one is equivalent to a usual citation index, i.e., it describes the visible diffusion of scientific knowledge; the second one reflects the implicit diffusion of scientific knowledge and is expressed through the number of implicit citations. The practical value of the suggested index is that it permits implicit initiators of the scientific mainstream to be easily identified. The distinctive feature of such scientists is the large value of the suggested citation index and the low value of the usual citation index.

Genetic Optimization of Multidimensional Technological Process Reliability

A technological process (TP) is considered multidimensional if a number of defects of diverse types occur, and they are detected and corrected simultaneously within the process execution [4, 5]. Quality of the TP is estimated by the probability of output zero-defects as well as by the probabilities of zero-defects for each of the defect types. The tasks of TP-optimization involve the choice of such a process structure that will provide the necessary output level of product quality given some certain cost limits [5]. The typical example of such optimization tasks is optimal choice of multiplicity of control-retrofit procedures in a TP. This particular optimization problem is studied in this article. An initial perspective would view this problem as one that may be solved by using known mathematical programming methods. However, taking into account that defects of many diverse types increase the dimensionality of the state space. It means that using classical mathematical programming techniques becomes impractical. Therefore, in this article, the task of TP optimization is solved by using genetic algorithms (GA) [2, 3], which allow to find nearly global optimal solution, and additionally do not require much mathematical backgrounds about optimization. Principal

Processing of optical information for medical decision-making support systems by intelligent techniques

In paper the basic stages of intelligent techniques application for processing the optical information in medical systems of diagnostic decisions making support are considered. The features of intelligent techniques application are illustrated on an example of system of decision making support in instant nontrauma death occurrence time determination construction.