Abstract
It is considered the problem of structural-parametric synthesis of a hybrid neural networks based on the use of Group Method of Data Handling neural network. Hybridization is achieved through the use of various neurons: classical, nonlinearAdaline, R-neuron, W-neuron, Wavelet-neuron. The problem of structural-parametric synthesis of hybrid neural network consists in the optimal choice of the number of layers, the number of neurons in the layers, the order of alternation of layers with different neurons. As an example it is considered the forecast problem solution with help of hybrid neural networks based on the data of the COVID-19 pandemic, collected by Johns Hopkins University. A MAPE criterion was used for quality assessment.
Highlights
The need to forecast the time series arises in cases where it is necessary to make decisions based on accumulated data on the system behavior: it can be the control which has inertia, analysis of financial markets for effective investment of money, of a complex apparatus with inertia, making decision under managing an enterprise or business that depends, for example, from the expected profit, etc
The problem of structural-parametric synthesis of hybrid neural networks (HNN) is posed, which consists in optimal choice of basic neural network topology, number of layers, number of neurons in the layers, order of layers alternation with neurons of different types [3]
In order to simplify the process of structural synthesis of the system and obtain new properties of the model due to hybridity, it is proposed to supplement the above algorithm for constructing an evolutionary Group Method of Data Handling (GMDH)-network by the best type of neurons choice for each layer
Summary
The need to forecast the time series arises in cases where it is necessary to make decisions based on accumulated data on the system behavior: it can be the control which has inertia, analysis of financial markets for effective investment of money, of a complex apparatus with inertia, making decision under managing an enterprise or business that depends, for example, from the expected profit, etc. Due to the COVID-19 pandemic, the power of Ukraine and other countries are forced to decide about reduction or introduction the quarantine measures of epidemic containment The decision in these cases is made taking into account the dynamics of the spread of the virus. Structural-parametric synthesis of HNN in this case includes the selection of the number of network layers and the number of neurons, and the sequence of network architectures or combinations of neurons of different types within one architecture [3]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.