Elliott waves classification via softcomputing

Abstract

This article presents a comparative study of the classification of Elliott waves in the chart. Regarding the methods of classification, the paper deals with backpropagation neural networks. Forms of activation functions of neurons in the hidden and output layers have been proposed by analytical programming with the differential evolution. The adaptation of the proposed neural network was performed by a standard backpropagation rule and Levenberg- Marquardt adaptation from Neural Network Toolbox in the Wolfram Mathematica environment. In conclusion, all results of this experimental study were evaluated and compared with each other.