Mathematical Model of the Conclusion of the Neural Network Defuzzificator in Fuzzy-Logic Output Procedures and Its Software Implementation
| Autor: | N. D. Kirillov, S. P. Dudarov |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
business.industry Computer science Computation Computer Science::Neural and Evolutionary Computation 010102 general mathematics Perceptron 01 natural sciences Fuzzy logic Software implementation 010305 fluids & plasmas Computational Mathematics Modeling and Simulation 0103 physical sciences Artificial intelligence 0101 mathematics business |
| Zdroj: | Mathematical Models and Computer Simulations. 13:328-337 |
| ISSN: | 2070-0490 2070-0482 |
| DOI: | 10.1134/s207004822102006x |
| Popis: | In this paper, a mathematical model of a neural network defuzzificator is presented. It is a two-layer perceptron and serves to convert a fuzzy solution to a numerical form in fuzzy-logic output procedures. The model allows optimizing the computational load that occurs when using the standard center-of-gravity method, through the use of a neural network. Training and testing are conducted with various settings of the neural-network model. The effectiveness of this approach by measuring the time required for the computation is also proved. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink