Automatic Discrimination of Earthquakes and False Events in Seismological Recording for Volcanic Monitoring
This paper reports on the classification of earthquakes and false events (thunders, quarry blasts and man-made undersea explosions) recorded by four seismic stations in the Vesuvius area in Naples, Italy. For each station we set up a specialized neural classifier, able to discriminate the two classes of events recordered by that station. Feature extraction is done using both the linear predictor coding technique and the waveform features of the signals. The use of properly normalized waveform features as input for the MLP network allows the network to better generalize compared to our previous strategy applied to a similar problem . To train the MLP network we compare the performance of the quasi-Newton algorithm and the scaled conjugate gradient method. On one hand, we improve the strategy used in  and on the other hand we show that it is not specific to the discrimination task  but has a larger range of applicability.
KeywordsMLP Seismic data
Unable to display preview. Download preview PDF.
- Bishop C., Neural Networks for Pattern Recognition, Oxford Press, 1995.Google Scholar
- Esposito A., Falanga M., Funaro M., Marinaro M., Scarpetta S., Signal Classification using Neural Networks, in Proceedings of WIRN’01, Vietri, pp. 187–1192, May 17–19, 2001.Google Scholar
- Makhoul J., Linear Prediction: A Tutorial Review, in Proceedings of the IEEE, vol. 63, No 4, 1975.Google Scholar
- Moller M., A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning, in Neural Networks 6(4), pp. 525–533.Google Scholar
- Shewchuk J. R., An Introduction to the Conjugate Gradient Method without the Agonizing Pain ftp://warp.cs.cmu.edu under the name quake-papers/painless-conjugate-gradient.ps.
- For more information look at the web site: http://www.ov.ingv.it.
- Numerical Recipes in C ISBN 0-521-43108-5, Cambridge University Press, 1988–1992.Google Scholar