Name
Abstract | ||
|---|---|---|
With the Peak Ground Velocity 283 records in three dimensions, the velocity attenuation relationship with distance was discussed by neural network in this paper. The earthquake magnitude, epicenter distance, site intensity and site condition were considered as basic input element for the network. By using Bayesian Regularization Back Propagation Neural Networks (BRBPNN), the over-fitting phenomenon was reduced to some extent. The horizontal velocity was discussed. The PGV predicted by neural networks can simulate the detail difference with distance, while the PGV given by other traditional attenuation relationship only give a reduction relation with distance. The importance of each input factor was compared by the square weight of the input layer of the network. The order may be earthquake magnitude, epicenter distance and soil condition. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11893257_104 | ICONIP |
Keywords | Field | DocType |
soil condition,earthquake magnitude,neural network,west america region,artificial neural network,epicenter distance,site intensity,horizontal velocity,input factor,input layer,site condition,basic input element,peak ground velocity evaluation,bayesian regularization,three dimensions | Magnitude (mathematics),Computer science,Regularization (mathematics),Artificial intelligence,Epicenter,Peak ground acceleration,Attenuation,Artificial neural network,Backpropagation,Machine learning,Bayesian interpretation of regularization | Conference |
Volume | ISSN | ISBN |
4233 | 0302-9743 | 3-540-46481-6 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ben-yu Liu | 1 | 1 | 1.02 |
| Liao-yuan Ye | 2 | 7 | 1.97 |
| Mei-ling Xiao | 3 | 1 | 1.02 |
| Sheng Miao | 4 | 7 | 1.74 |