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

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

   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