Informatica

The paper proposes a novel predictive-reactive planning and scheduling framework in which both approaches are combined to complement each other in a reasonably balanced way. Neither original scheduling algorithms nor original techniques can be find in this paper. It also does not intend to invent new mechanisms or to propose some cardinally new ideas. The aim is to choose, adapt and test ideas, mechanisms and algorithms already proposed by other researchers. The focus of this research is set on make-to-order production environments. The proposed approach aims not only to absorb disruptions in shop floor level schedules but also to mitigate the impacts of potential exceptions, which disrupt mid-term level production plans. It is based on application of risk mitigation techniques and combines various simulation techniques extended by optimization procedures. The proposed approach is indented to be implemented in Advanced Planning and Scheduling system, which is an add-on for Enterprise Resources Planning system. To make it easier to understand the focus of the paper, at the beginning the position from which we start is clarified.

The main scientific problems investigated in this paper deal with the problem of multiple criteria evaluation of the quality of the main components of e-learning systems, i.e., learning objects (LOs) and virtual learning environments (VLEs). The aim of the paper is to analyse the existing LO and VLE quality evaluation methods, and to create more comprehensive methods based on learning individualisation approach. LOs and VLEs quality evaluation criteria are further investigated as the optimisation parameters and several optimisation methods are explored to be applied. Application of the experts' additive utility function using evaluation criteria ratings and their weights is explored in more detail. These new elements make the given work distinct from all the other earlier works in the area.

In the present paper, the method of structure analysis for multivariate functions was applied to rational approximation in classification problems. Then the pattern recognition and generalisation ability was investigated experimentally in numerical recognition. A comparison with Hopfield Net was carried out. The overall results of using of new approach may be treated as a success.