000009960 001__ 9960
000009960 005__ 20141205154134.0
000009960 04107 $$aeng
000009960 046__ $$k2008-10-12
000009960 100__ $$aFadavi Amiri, M.
000009960 24500 $$aNew Method for Generation of Artificial Earthquake Record

000009960 24630 $$n14.$$pProceedings of the 14th World Conference on Earthquake Engineering
000009960 260__ $$b
000009960 506__ $$arestricted
000009960 520__ $$2eng$$aIn this paper, the use of wavelet analysis and artificial neural networks for generating artificial earthquake accelerograms from the target spectra is suggested as a new method. This procedure uses the learning capabilities of neural network to expand the knowledge of the inverse recording from response spectra to earthquake accelerogram. In the first step, wavelet analysis is used to decompose earthquake accelerograms to several levels in which each level covers a special range of frequencies, and then for every level a neural network is trained to learn to relate the response spectra to wavelet coefficients. Finally, the generated accelerogram using inverse discrete wavelet transform is obtained. An example is presented to demonstrate the effectiveness of the proposed method.

000009960 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000009960 653__ $$aArtificial accelerogram, target spectra, wavelet analysis, neural network 

000009960 7112_ $$a14th World Conference on Earthquake Engineering$$cBejing (CN)$$d2008-10-12 / 2008-10-17$$gWCEE15
000009960 720__ $$aFadavi Amiri, M.$$iAkbari, A.$$iGhodrati Amiri, Gholamreza
000009960 8560_ $$ffischerc@itam.cas.cz
000009960 8564_ $$s437228$$uhttps://invenio.itam.cas.cz/record/9960/files/14-0114.pdf$$yOriginal version of the author's contribution as presented on CD, Paper ID: 14-0114.
000009960 962__ $$r9324
000009960 980__ $$aPAPER