In this article proposed a new clustering technique, which is based on two methods: density algorithm DBSCAN and inductive objective clustering algorithm. Experimentally proved that the combination of two these methods can solve the problem of recognition of clusters of different nonlinear form, and greatly increase the accuracy in the detection of complex objects.
This paper proposes a method of finding functional relationships in dynamical systems on the set of input data by clonal hybrid algorithm and clonal synthesized using polynomial algorithm neural network. The technology of building models heteroscedastic processes.
The article suggests and describes a GMDH algorithm for the synthesis of co-operative immune network in the solution of tasks of forecasting of time series. Conducted comparative experiments have shown that the use of external criteria improves adaptability, robustness and accuracy of the obtained solutions.