NEURAL NETWORKS FOR BLIND SOURCES SEPARATION OF STROMBOLI EXPLOSION QUAKES

F. Acernese 1 , A. Ciaramella 2;3 , S. De Martino 4;6 , M. Falanga 4 , R. Tagliaferri 2;3;5, 4 Dipartimento di Fisica, Universit`a di Salerno, 84081 Baronissi (SA), Italia
3 INFM unit`a di Salerno, 84081 Baronissi (SA), Italia. E­mail:robtag@unisa.it, 6 INFN gruppo collegato di Salerno, 84081 Baronissi (SA), Italia. E­mail:demartino@sa.infn.it

Independent Component Analysis (ICA) is used to ana­ lyze the seismic signals produced by explosions of Strom­ boli Volcano. It has been experimentally proved that it is possible to extract the most significant components from seismometer recorders. In particular, the signal, generally thought as generated by the source, is cor­ responding to the higher power spectrum, isolated by our analysis.