Dissimilarity-based classification of seismic signals at nevado del ruiz volcano

Automatic classification of seismic signals has been typically carried out on feature-based representations. Recent research works have shown that constructing classifiers on dissimilarity representations is a more practical and, sometimes, a more accurate solution for some patternrecognition problems. In this paper, we consider Bayesian classifiers constructed on dissimilarity representations. We show that such classifiers are a feasible and reliable alternative for automaticclassification of seismic signals. Our experiments were conducted on a dataset containing seismic signals recorded by two selected stations of the monitoring network at Nevado del Ruiz Volcano. Dissimilarity representations were constructed by calculating pairwise Euclidean distances and a non-Euclidean measure on the normalized spectra, which is based on the difference in area between spectral curves. Results show that even though Euclidean dissimilarities have advantageous properties, non-Euclidean measures can be beneficial for matching spectra of seismic signals.

• Autores: Orozco, Mauricio; García, Marcelo E.; P.W. Duin, Robert; G. Castellanos, César
• Tipo de recurso: Article of journal
• Fecha de publicación: 2006
• Institución: Universidad Nacional de Colombia
• Repositorio: Universidad Nacional de Colombia
• Idioma: spa
• OAI Identifier: oai:repositorio.unal.edu.co:unal/34018
• Acceso en línea: https://repositorio.unal.edu.co/handle/unal/34018; http://bdigital.unal.edu.co/24098/
• Rights: openAccess
• License: Atribución-NoComercial 4.0 Internacional