This paper proposes criteria for the optimal choice of a database management system (DBMS), based on the requirements to this system. Empirically assessed criteria and method of analytic hierarchy process for decision making were used to carry out the comparative analysis of several DBMSs, implementing relation data model and having similar functionalities. The obtained matrixes of pair-wise comparison are examined for concurrence by calculating indices described in the article. As a result, the database management system for the own project is rationally chosen.

Keywords: DBMS, method of analytic hierarchy process, criteria, matrixes of pair-wise

This paper offers an improvement for machine vision based tracking algorithm using NARX neural network. This is achieved by predicting the next position of a mobile agent based on previous movement described by time-series functions. The algorithm remains passive and does not interfere with the quadrotr flight path until detection of multiple agent-candidates, when the tracking algorithm is not able to identify or locate the assigned agent. Meanwhile the NARX training set are updated in parallel with each successful tracking cycle. This process is done to eliminate the overfitting problem of BPTT training.

Keywords: NARX, quadrotor, agent tracking, local minimum problem, machine vision

Specialized robots are occupying a vast share of researches worldwide. In terms of aerial specialized robots, autonomy is the one of the major subjects that are being studied. As  known, flight autonomy is consisting of three parts: Mission planning, trajectory generation and path tracking. While it exists variety of local and global generation algorithm, UAV path planning is always associated with machine vision. This intellectual approach is solid because it can give a dual supervision link to the situation being surveyed. The operator has always the authority to step in and stop any unwanted action. The machine vision based algorithm has a huge disadvantage due to homogeneity and identity factors. This is because from distance object tend to look the same geometrically as well as color wise. In this paper we offer a solution to tackle the homogeneity problem between tracked agents which can cause local minimum problems. The UAV will forecast the next position of the tracked agent using Artificial Neural Networks. Position estimation is based on registered previous coefficient.

Keywords: position prediction, path planning, quadrotor, neural networks

Case is an event that took place in the past and can be an example for similar steps in present. Case-based reasoning (CBR) is a methodology of finding a decision based on previous experience. The main difficulties in CBR are recognition of present situation of decision-making and finding similar case in the past. Making a decision in the field of purchasing drugs is a quite difficult and many-valued task with a plenty of various parameters, which however might be solved with the help of CBR. CBR is an important and perspective area of artificial intelligence (AI) decision support systems. Constantly growing research amount has already led to breakthroughs in theoretical part of AI and in AI-based applications. The general case model and formula for determining cases similarity is suggested in this work. Application of the formula will help determine similarity of cases and make the better decision.

Keywords: case, case-based reasoning, case description, decision support system, case-based decision making

We consider a one-step part (B, S) - a market with an infinite number of states. The first part of the article deals with modeling of random behavior of an infinite number of aggressive buyers of the shares in the financial market. There will be described one way to exit the buyers of shares on the market, the gap between the announcement of the share price. In the second part of the article presents the procedure hedge payment obligation (bp), which uses interpolation of incomplete full-arbitrage market economies (Haar interpolation method).

Keywords: Stochastic basis, financial market, martingale measure,the weakened property of the universal Haar uniqueness, self-financing portfolios, capital of portfolio, contingent claim.

There has been carried out the comparative analysis of the training algorithms of artificial neural networks of perceptron type: genetic, adaptive and hybrid.The comparison revealed that the adaptive algorithm is better coped with the task than the other algorithms. It is better to use the hybrid algorithm to solve the problem with complex target multiextremal function for which the adaptive algorithm is less convenient.

Keywords: artificial neural networks, multilayer perceptron, genetic, adaptive, hybrid algorithm

Information about authors of issue №4 (2013)

Keywords: authors

  The experimental studies of technological modes of formation of the elements for hybrid microfluidic sensor systems using focused ion beams by nanotechnology complex UHV NANOFAB are performed. The parameters of the focused ion beam to enable the development of microfluidics components are determined. Methods of forming of microfluidics structures on silicon substrate are studied. Parameters of generated elements were studied by scanning electron microscopy and atomic force microscopy. Formed and studied filtration membranes containing holes from 105 to 150 nm in diameter. The results can be used in the formation of nanoscale structures and the development of manufacturing processes microfluidics components for hybrid systems and lab-on-chip.

Keywords: Nanotechnology, focused ion beams, microfluidics, hybrid systems, sensor, lab-on-chip

In presented article rank criteria for the statistical analysis of two selections are considered. These criteria check statistical hypotheses. Three groups of rank criteria were considered: about equality of the central tendencies, scopes of a variation and distribution laws. Researches were conducted on data on exchange rates in two next days in nine banks. Correctness of criteria was estimated proceeding from an US dollar exchange rate established by the Central bank of Russia. To these data rank criteria of Wilcoxon, Van der Waerden, Kolmogorov-Smirnov and others were applied rubbed. Coinciding values of two selections were estimated by means of a method of an average rank. For all examples rank criteria gave the correct assumptions of equality of two selections.

Keywords: statistics, rank, sample, hypotheses statistical, critical value, normal distribution, the interfaced couples

The article is devoted to the modeling of plant material and to increase the strength properties of building structures using bionic principles. The different kinds of structures reinforcing fabric leafy plants. Recommendations on the use of reinforcement cages during restoration work in construction.

Keywords: shell strength, plant, reinforcing fabric, building construction

   The authors created information-analytical system based on OLAP and using data mining algorithms for the development of automated technology point-rating system of student assessment to monitor and to analyze the quality of the educational process in the course of the monthly student achievements' assessment  and monitoring of the results of examinations. As a result, managers on various levels have increased the level of control and efficiency of the university, received timely consistent and accurate information.

Keywords: data processing, OLAP, Data Mining, Microsoft SQL Server, education, university, reports, information and analysis system, multi-dimensional data warehouse

The article offers a general gradient methods for all-adaptive method. With the help of an experimental environment was developed by a comparative analysis of gradient methods of finding the minimum. As a result of experiments, it was found that the adaptive method for approaching to a minimum minimal number of iterations. Thus encouraged to use this method in the optimization of the error function, artificial neural network training. 
Keywords: neural networks, gradient methods, teaching methods, analysis of optimization techniques.

Keywords: