Açık Akademik Arşiv Sistemi

Application of k-means and Gaussian mixture model for classification of seismic activities in Istanbul

Show simple item record

dc.contributor.authors Kuyuk, HS; Yildirim, E; Dogan, E; Horasan, G;
dc.date.accessioned 2020-03-06T08:08:20Z
dc.date.available 2020-03-06T08:08:20Z
dc.date.issued 2012
dc.identifier.citation Kuyuk, HS; Yildirim, E; Dogan, E; Horasan, G; (2012). Application of k-means and Gaussian mixture model for classification of seismic activities in Istanbul. NONLINEAR PROCESSES IN GEOPHYSICS, 19, 419-411
dc.identifier.issn 1023-5809
dc.identifier.uri https://doi.org/10.5194/npg-19-411-2012
dc.identifier.uri https://hdl.handle.net/20.500.12619/67299
dc.description.abstract Two unsupervised pattern recognition algorithms, k-means, and Gaussian mixture model (GMM) analyses have been applied to classify seismic events in the vicinity of Istanbul. Earthquakes, which are occurring at different seismicity rates and extensions of the Thrace-Eskisehir Fault Zone and the North Anatolian Fault (NAF), Turkey, are being contaminated by quarries operated around Istanbul. We have used two time variant parameters, complexity, the ratio of integrated powers of the velocity seismogram, and S/P amplitude ratio as classifiers by using waveforms of 179 events (1.8 < M < 3.0). We have compared two algorithms with classical multivariate linear/quadratic discriminant analyses. The total accuracies of the models for GMM, k-means, linear discriminant function (LDF), and quadratic discriminant function (QDF) are 96.1 %, 95.0 %, 96.1 %, 96.6 %, respectively. The performances of models are discussed for earthquakes and quarry blasts separately. All methods clustered the seismic events acceptably where QDF slightly gave better improvements compared to others. We have found that unsupervised clustering algorithms, for which no a-prior target information is available, display a similar discriminatory power as supervised methods of discriminant analysis.
dc.language English
dc.publisher COPERNICUS GESELLSCHAFT MBH
dc.subject Physics
dc.title Application of k-means and Gaussian mixture model for classification of seismic activities in Istanbul
dc.type Article
dc.identifier.volume 19
dc.identifier.startpage 411
dc.identifier.endpage 419
dc.contributor.department Sakarya Üniversitesi/Mühendislik Fakültesi/İnşaat Mühendisliği Bölümü
dc.contributor.saüauthor Küyük, Hüseyin Serdar
dc.contributor.saüauthor Yıldırım, Eray
dc.contributor.saüauthor Doğan, Emrah
dc.contributor.saüauthor Horasan, Gündüz
dc.relation.journal NONLINEAR PROCESSES IN GEOPHYSICS
dc.identifier.wos WOS:000310480700002
dc.identifier.doi 10.5194/npg-19-411-2012
dc.contributor.author Küyük, Hüseyin Serdar
dc.contributor.author Yıldırım, Eray
dc.contributor.author Doğan, Emrah
dc.contributor.author Horasan, Gündüz


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record