Разработка оболочки системы поддержки принятия решений с использованием эволюционных алгоритмов
In this article we ground some advantages of the evolutionary approach to the solution of problems of decision support system development. The most popular methods of forecasting and detection of dependences are considered. Advantages of use of neural networks to forecast and to determine of dependences between parameters of systems are given. Advantages of interval neural networks are considered. Methods of finding of optimal input parameters for neural networks are appreciated. Realization of decision-making support systems with use of genetic algorithm and neural networks is described. The main advantages of parallelization of the general purpose calculations with use of the graphics processing units are listed. The realized system shell based on communication of neural networks and genetic algorithm, and optimized at the expense of use of general-purpose graphics processing units is described.