A New Multivalued Neural Network for Isomorphism Identification of Kinematic Chains

Neural networks
Combinatorial optimization
Authors

Gloria Galán Marín

Domingo López-Rodríguez

Enrique Mérida Casermeiro

Published

1 March 2010

Publication details

Journal of Computing and Information Science in Engineering 10(1)

Links

DOI

 



Abstract

A lot of methods have been proposed for the kinematic chain isomorphism problem. However, the tool is still needed in building intelligent systems for product design and manufacturing. In this paper, we design a novel multivalued neural network that enables a simplified formulation of the graph isomorphism problem. In order to improve the performance of the model, an additional constraint on the degree of paired vertices is imposed. The resulting discrete neural algorithm converges rapidly under any set of initial conditions and does not need parameter tuning. Simulation results show that the proposed multivalued neural network performs better than other recently presented approaches.

Cites

The following graph plots the number of cites received by this work from its publication, on a yearly basis.

Citation

Please, cite this work as:

[MLC10] G. G. Marín, D. López-Rodríguez, and E. M. Casermeiro. “A New Multivalued Neural Network for Isomorphism Identification of Kinematic Chains”. In: J. Comput. Inf. Sci. Eng. 10.1 (2010). DOI: 10.1115/1.3330427. URL: https://doi.org/10.1115/1.3330427.

@article{MarinLC10,
     author = {Gloria Galán Marín and
     Domingo López{-}Rodríguez and
     Enrique Mérida Casermeiro},
     title = {A New Multivalued Neural Network for Isomorphism Identification of
     Kinematic Chains},
     journal = {J. Comput. Inf. Sci. Eng.},
     volume = {10},
     number = {1},
     year = {2010},
     url = {https://doi.org/10.1115/1.3330427},
     doi = {10.1115/1.3330427},
     timestamp = {Thu, 21 Jan 2021 17:35:20 +0100},
     biburl = {https://dblp.org/rec/journals/jcise/MarinLC10.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
}