Open Access


Download data is not yet available.


In recent years, fuzzy neural systems have become increasingly popular due to their powerful learning and interpreting capabilities. In the field of control, the fuzzy neural system is superior to other intelligent systems. In addition, the theory of the combination of neural networks and fuzzy logic is also used in many other fields such as prediction, simulation, decision support, etc. However, most neural systems are Fuzzy systems used today are a combination of neural networks and univariate membership functions in fuzzy theory. These functions have the advantage of being simple and easy to set up, but with that is a lack of interpretability for complex objects. For objects that need to be described by two or more quantities, unidirectional membership functions are not able to represent it. Application of multivariable membership function is necessary in this case. The application of multivariable membership functions encounters many barriers due to their complexity, the algorithms for applying multivariable membership functions are sketchy and have not fully promoted its advantages. In this article, we will introduce a method for applying multivariable Gaussian membership function that allows to improve simulation performance compared to previously introduced methods.

Author's Affiliation
Article Details

 Copyright Info

Creative Commons License

Copyright: The Authors. This is an open access article distributed under the terms of the Creative Commons Attribution License CC-BY 4.0., which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

 How to Cite
Truong An, B., Anh, P., & Nguyen, P. (2024). The application of multivariable membership functions to the fuzzy neural model. VNUHCM Journal of Engineering and Technology, 6(SI8), In press.

 Cited by

Article level Metrics by Paperbuzz/Impactstory
Article level Metrics by Altmetrics

 Article Statistics
HTML = 143 times
Online First   = 50 times
Total   = 50 times