Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.1/4780
Título: A support vector machine seismic detector for early-warning applications
Autor: Ruano, A. E.
Madureira, G.
Barros, O.
Khosravani, H. R.
Ruano, M. Graca
Ferreira, P. M.
Palavras-chave: Smart systems
Actuators and distributed systems
Computational intelligence methods in modeling
Systems identification and control
Data: 2013
Editora: Elsevier, IFAC
Citação: Ruano, A. E.; Madureira, G.; Barros, O.; Khosravani, H.R.; Ruano, M.G.; Ferreira, P.M.A Support Vector Machine Seismic Detector for Early-Warning Applications, Trabalho apresentado em Intelligent Control and Automation Science, In 3rd IFAC International Conference on Intelligent Control and Automation Science (2013), Chengdu, 2013.
Resumo: This paper extends a Support Vector Machine (SVM) approach for the detection of seismic events, at the level of a seismic station. In previous works, it was shown that this approach produced excellent results, in terms of the Recall and Specificity measures, whether applied off-line or in a continuous scheme. The drawback was the time taken for achieving the detection, too large to be applied in a Early-Warning System (EWS). This paper shows that, by using alternative input features, a similar performance can be obtained, with a significant reduction in detection time. Additionally, it is experimentally proved that, whether off-line or in continuous operation, the best results are obtained when the SVM detector is trained with data originated from the respective seismic station.
Peer review: yes
URI: http://hdl.handle.net/10400.1/4780
DOI: http://dx.doi.org/ 10.3182/20130902-3-CN-3020.00082
ISSN: 9783902823458
Versão do Editor: http://www.ifac-papersonline.net/Detailed/63491.html
Aparece nas colecções:FCT2-Artigos (em revistas ou actas indexadas)

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
0082.pdf530,65 kBAdobe PDFVer/Abrir    Acesso Restrito. Solicitar cópia ao autor!


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.