Models for identifying structures in the data: a performance comparison

ABSTRACT

This paper reports on the unsupervised analysis of seismic signals recorded in Italy, respectively on the Vesuvius volcano, located in Naples, and on the Stromboli volcano, located North of Eastern Sicily. The Vesuvius dataset is composed of earthquakes and false events like thunders, man-made quarry and undersea explosions. The Stromboli dataset consists of explosion-quakes, landslides and volcanic microtremor signals. The aim of this paper is to apply on these datasets three projection methods, the linear Principal Component Analysis (PCA), the Self-Organizing Map (SOM), and the Curvilinear Component Analysis (CCA), in order to compare their performance. Since these algorithms are well known to be able to exploit structures and organize data providing a clear framework for understanding and interpreting their relationships, this work examines the category of structural information that they can provide on our specific sets. Moreover, the paper suggests a breakthrough in the application area of the SOM, used here for clustering different seismic signals. The results show that, among the three above techniques, SOM better visualizes the complex set of high-dimensional data discovering their intrinsic structure and eventually appropriately clustering the different signal typologies under examination, discriminating the explosion-quakes from the landslides and microtremor recorded at the Stromboli volcano, and the earthquakes from natural (thunders) and artificial (quarry blasts and undersea explosions) events recorded at the Vesuvius volcano.

References

1. Demartines, P., Herault, J.: Curvilinear Component Analysis: A Self-Organizing Neural Network for Nonlinear Mapping of Data Sets. IEEE Transactions on Neural Networks, 8(1), 148-154 (1997).
2. Esposito, A.M., Giudicepietro, F., Scarpetta, S., D'Auria, L., Marinaro, M., Martini, M.: Automatic Discrimination among Landslide, Explosion-Quake and Microtremor Seismic Signals at Stromboli Volcano using Neural Networks. Bulletin of Seismological Society of America (BSSA), 96(4A).
3. Esposito, A.M., Scarpetta, S., Giudicepietro, F., Masiello, S., Pugliese, L., Esposito, A.: Nonlinear Exploratory Data Analysis Applied to Seismic Signals. In: Apolloni, B., Marinaro, M., Nicosia, G., Tagliaferri, R. (eds.) WIRN 2005 and NAIS 2005. LNCS, vol. 3931, pp. 70-77. Springer, Heidelberg (2006).
4. Jollife, I.T.: Principal Component Analysis. Springer, New York (1986).
5. Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J.: SOM_PAK: The Self-Organizing Map Program Package, Report A31. Helsinki University, Finland (1996) Also available at http://www.cis.hut.fi/research/som_lvq_pak.shtml
6. Kohonen, T.: Self-Organizing Maps, Series in Information Sciences, 2nd edn. vol. 30. Springer, Heidelberg (1997).
7. Lee, J.A., Lendasse, A., Verleysen, M.: Nonlinear Projection with Curvilinear Distances: Isomap versus Curvilinear Distance Analysis. Neurocomputing, 57, 49-76 (2004).
8. Makhoul, J.: Linear Prediction: a Tutorial Review. In: Makhoul, J. (ed.) Proceeding of IEEE, pp. 561-580. IEEE, Los Alamitos (1975).
9. Scarpetta, S., Giudicepietro, F., Ezin, E.C., Petrosino, S., Del Pezzo, E., Martini, M., Marinaro, M.: Automatic Classification of Seismic Signals at Mt. Vesuvius Volcano, Italy, Using Neural Networks, Bulletin of Seismological Society of America (BSSA), Vol. 95, pp. 185-196 (2005).
10. Wish, M., Carroll, J.D.: Multidimensional Scaling and its Applications. In: Krishnaiah, P.R., Kanal, L.N. (eds.) Handbook of Statistics, vol. 2, pp. 317-345. North-Holland, Amsterdam (1982).