检索结果-南通市图书馆

Range estimation of few-shot underwater sound source in shallow water based on transfer learning and residual CNN

Journal of Systems Engineering and Electronics 2023年第4期34卷 839-850页

作者： YAO Qihai WANG Yong YANG Yixin School of Marine Science and Technology Northwestern Polytechnical UniversityXi’an 710072China Shaanxi Key Laboratory of Underwater Information Technology Xi’an 710072China

Taking the real part and the imaginary part of complex sound pressure of the sound field as features,a transfer learning model is *** on the pre-training of a large amount of underwater acoustic data in the preselected sea area using the convolutional neural network(CNN),the few-shot underwater acoustic data in the test sea area are retrained to study the underwater sound source ranging *** S5 voyage data of SWellEX-96 experiment is used to verify the proposed method,realize the range estimation for the shallow source in the experiment,and compare the range estimation performance of the underwater target sound source of four methods:matched field processing(MFP),generalized regression neural network(GRNN),traditional CNN,and transfer *** data processing results show that the transfer learning model based on residual CNN can effectively realize range estimation in few-shot scenes,and the estimation performance is remarkably better than that of other methods.

关键词： transfer learning residual convolutional neural network(CNN) few shot vertical array range estimation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A modified normalized input-output minimization (Mod-NIOM) method for seismic wave propagation modeling

引用

Earthquake Engineering and Engineering Vibration 2010年第4期9卷 481-491页

作者： Santa Man Shrestha Hideji Kawakami Eric Augustus Tingatinga Hidenori Mogi Department of Civil and Environmental Engineering Saitama University Geosphere Research Institute Saitama University Institute of Civil Engineering University of the Philippines Diliman

A new method for wave propagation modeling is introduced in this paper. By using the constraint optimization （Lagrange multiplier） method, the sum of weighted squared Fourier amplitudes is minimized when subjected to a constraint. The sum of the maximum amplitudes obtained from all output models is normalized to unity and is taken as a constraint. In this method, all the actual time histories are considered as outputs and dealt with equally. Independently of the combinations of time histories （or the first time history selected） during the analysis, the method captures the relationship of actual time histories by showing clear peaks. This paper describes the formulation of the models and illustrates the advantage of this method over the normalized input-output minimization （NIOM） method. The Mod-NIOM is then used to analyze the time histories of the Hyogoken-nanbu earthquake recorded at the Port Island vertical array site in Kobe, which suffered from liquefaction caused by the strong motions during the main shock. This method showed good correlations between the observed time histories at the site even though the surface time history was greatly modified by the liquefaction.

关键词： wave propagation constraint optimization S-wave velocity liquefaction amplification vertical array Hyogoken-nanbu earthquake

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：