Digital library of construction informatics
and information technology in civil engineering and construction


Paper w78-2000-95:
Predicting ground otion descriptions through artificial neural networks

Facilitated by the SciX project

Bento J, Azevedo J, Oliveira C S

Predicting ground otion descriptions through artificial neural networks

Abstract: "The present paper addresses the problem of predicting the description of an expected earthquake through the associated ground motion record that would be recorded at a given site. For that purpose, a number of previous ground motion records referring to 100 different earthquakes occurring within a reasonably small geographic area (Northern California) have been acquired and processed in order to extract some of the features that could describe them more synthetically than the full records. The attributes thus generated were used to train a feedforward network in order to map them into what can be called higher level descriptors of each earthquake, such as the magnitude or the peak accelerations, for example. Once such mapping is obtained, one may infer a number of attributes that would allow the artificial generation of the accelerograms corresponding to ""expected earthquakes"" described resorting to those higher level descriptors"



Full text: content.pdf (408,837 bytes) (available to registered users only)

Series: w78:2000 (browse)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.analysis (0.031791)
Similar papers:
Sound: read aloud.

Permission to reproduce these documents have been graciously provided by Icelandic Building Research Institute. The assistance of the editor, Mr. Gudni Gudnason, is gratefully appreciated


hosted by University of Ljubljana



© itc.scix.net 2003
Home page of this database login Powered by SciX Open Publishing Services 1.002 February 16, 2003