Abstract
The use of interactive activation and competition (IAC) and backpropagation (BP) artificial neural networks (ANNs) for transit time estimation has been investigated in this piece of research. Owing to its competitive nature, the IAC ANN has been found able to correctly estimate the current transit time from short records of signals as well as to quickly follow changes in transit time and to detect when the transit time falls outside a predefined expected range. On the other hand, the interactive nature of the IAC ANN allows it to be robust to significant levels of noise and of the global component. A BP ANN has been appended to the IAC ANN, further allowing for the accurate estimation of decimated transit times.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M. Antonopoulos, M. Marseguerra, and E. Padovani. On the fast estimation of transit times — application to bwr simulated data. In Proceedings of the SMORN VII (Volume 2), 1995.
S. Grossberg. Adaptive pattern classification and universal recoding: Parallel development and coding of neural feature detectors. Biological Cybernetics, 23:121–134, 1976.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning representations by back-propogating errors. Nature, 323:533–536, 1986.
D. E. Rumelhart and D. Zipser. Feature discovery by competitive learning. Cognitive Science, 9:75–112, 1985.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Wien
About this paper
Cite this paper
Tambouratzis, T., Antonopoulos-Domis, M., Marseguerra, M., Padovani, E. (1998). Transit Time Estimation by Artificial Neural Networks. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6492-1_14
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6492-1_14
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83087-1
Online ISBN: 978-3-7091-6492-1
eBook Packages: Springer Book Archive