Please use this identifier to cite or link to this item:
http://hdl.handle.net/2122/4157
Authors: | Masotti, M.* Campanini, R.* Mazzacurati, L.* Falsaperla, S.* Langer, H.* Spampinato, S.* |
Title: | TREMOrEC: a software utility for automatic classification of volcanic tremor | Journal: | Geochemistry Geophysics Geosystems | Series/Report no.: | 4/9 (2008) | Publisher: | AGU and the Geochemical Society | Issue Date: | 3-Apr-2008 | DOI: | 10.1029/2007GC001860 | URL: | http://www.agu.org/journals/gc/ | Keywords: | Volcanic tremor Etna Support Vector Machine classification |
Subject Classification: | 04. Solid Earth::04.06. Seismology::04.06.08. Volcano seismology | Abstract: | We describe a stand-alone software utility named TREMOrEC, which carries out training and test of a Support Vector Machine (SVM) classifier. TREMOrEC is developed in Visual C++ and runs under Microsoft Windows operating systems. Ease of use and short time processing, along with the excellent performance of the SVM classifier, make this tool ideal for volcano monitoring. The development of TREMOrEC is motivated by the successful application of the SVM classifier to volcanic tremor data recorded at Mount Etna in 2001 [Masotti et al,. 2006]. In that application, spectrograms of volcanic tremor were divided according to their recording date into four classes associated with different states of activity, i.e., pre-eruptive, lava fountain, eruptive, or post-eruptive. During the training, SVM learned the a-priori classification. The classifier’s performance was then evaluated on test sets not considered for training. The classification results matched the actual class membership with less than 6% of error. |
Appears in Collections: | Article published / in press |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
2008_G3_Masotti_et_al.pdf | main article | 630.16 kB | Adobe PDF |
WEB OF SCIENCETM
Citations
50
6
checked on Feb 10, 2021
Page view(s)
341
checked on Apr 20, 2024
Download(s)
25
checked on Apr 20, 2024