Graph Matching using Hierarchical Fuzzy Graph Neural Networks (CROSBI ID 235672)
Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Krleža, Dalibor ; Fertalj, Krešimir
engleski
Graph Matching using Hierarchical Fuzzy Graph Neural Networks
Data and models can naturally be represented by graphs. Graph representation of data is used in many areas of science and engineering, making graph matching still current and important. Besides conventional graph matching algorithms, some successful attempts of utilizing recursive neural networks in this area have been made. In this article we extend previous research by proposing a novel approach using a combination of fuzzy logic and recursive neural network, which we named the fuzzy graph neural network. Adding fuzzy logic to the existing recursive neural network approach enables us to interpret graph matching result as the similarity to the learned graph. In this way we have created a neural network, which is more resilient to the introduced input noise than a classical non- fuzzy, supervised-learning based neural network. An implementation of the proposed fuzzy graph neural network is presented in the article. Testing of the implementation is done by using standard graph matching data sets and problems, and includes assessment of the relation between noise and recognition accuracy for the proposed fuzzy graph neural network.
Graph matching, Fuzzy neural networks, Recursive neural networks, Hierarchical neural networks, Noise resilience.
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o izdanju
25 (4)
2017.
892-904
objavljeno
1063-6706
10.1109/TFUZZ.2016.2586962