| Seismic liquefaction potential assessment by using relevance vector machine |
| |
| 作者姓名： | Pijush Samui |
| |
| 作者单位： | Department of |
| |
| 摘 要： | Determining the liquefaction potential of soil is important in earthquake engineering. This study proposes the use of the Relevance Vector Machine (RVM) to determine the liquefaction potential of soil by using actual cone penetration test (CPT) data. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. The results are compared with a widely used artifi cial neural network (ANN) model. Overall, the RVM shows good performance and is proven to be more accurate than the ANN model. It also provides probabilistic output. The model provides a viable tool for earthquake engineers to assess seismic conditions for sites that are susceptible to liquefaction.
|
| 关 键 词： | 液化过程 锥形渗透性测试 支撑向量机械 人造神经网络 |
| 收稿时间： | 2 August 2007 |
| 修稿时间： | 24 October 2007 |
Seismic liquefaction potential assessment by using Relevance Vector Machine |
| |
| Pijush Samui.Seismic liquefaction potential assessment by using relevance vector machine[J].Earthquake Engineering and Engineering Vibration,2007,6(4):331-336. |
| |
| Authors: | Pijush Samui |
| |
| Institution: | Department of Civil Engineering,Indian Institute of Science,Bangalore 560012,India |
| |
| Abstract: | Determining the liquefaction potential of soil is important in earthquake engineering. This study proposes the use of the Relevance Vector Machine (RVM) to determine the liquefaction potential of soil by using actual cone penetration test (CPT) data. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. The results are compared with a widely used artifi cial neural network (ANN) model. Overall, the RVM shows good performance and is proven to be more accurate than the ANN model. It also provides probabilistic output. The model provides a viable tool for earthquake engineers to assess seismic conditions for sites that are susceptible to liquefaction. |
| |
| Keywords: | liquefaction cone penetration test relevance vector machine artifi cial neural network |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
