Abstract
We present a shared-weights neural architecture for classifying spectrograms from regional seismic events. This approach does not use any high-level information available (like epicenter, magnitude, time origin etc.) on the event other than the estimated arrival times for the P-wave and eventually the S-wave. This severe restriction is to make sure that the system continues to function in the absence of high-level information. In spite of the very noisy character of the spectrograms, the classification rates obtained are comparable to those obtained by methods which do depend on the availability of high-level information (≈ 90 – 98%), though the rejection rate on non-trained events is rather high (≈ 20%).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
S. Muller, P. Garda, J.-D. Muller, R. Crusem, and Y. Cansi, “A neuro-fuzzy coding for processing incomplete data: Application to the classification of seismic events,” Neural Processing Letters, vol. 8, August 1998.
S. Muller, J.-F. Legrand, J.-D. Muller, Y. Cansi, R. Crusem, and P. Garda, “Seismic events discrimination by neuro-fuzzy data merging.” Submitted to Geophysical Research Letters.
S. Muller, J.-F. Legrand, P. Garda, J.-D. Muller, R. Crusem, and Y. Cansi, “Seismic events discrimination by a neuro-fuzzy merging of incomplete data,” in Annales Geophysicae, 23rd General Assembly of the European Geophysical Society, vol. 16, (Nice, France), April 1998.
C. Dugast and L. Devillers, “Incorporating acoustic-phonetic knowledge in hybrid tdnn/hmm frameworks,” in ICASSP92, vol. I, (San Francisco, USA), p. 421, 1992.
X. Driancourt and L. Bottou, “Tdnn-extracted features,” in Neuro-Nimes 90, (Nimes, France), EC2, 1990.
M. Joswig, “Automated classification of local earthquake data in the bug small array,” Geophys. J. Int., 1995.
G. Romeo, F. Mele, and A. Morelli, “Neural networks and discrimination of seismic signals,” Computers & Geosciences, vol. 21, pp. 279–288, March 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London
About this paper
Cite this paper
Klaassen, A.J., Driancourt, X., Muller, S., Muller, JD. (1998). Classifying Regional Seismic Signals Using TDDN-alike Neural Networks. In: Niklasson, L., Bodén, M., Ziemke, T. (eds) ICANN 98. ICANN 1998. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1599-1_125
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1599-1_125
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-76263-8
Online ISBN: 978-1-4471-1599-1
eBook Packages: Springer Book Archive