Applications of neural networks to ocean acoustic tomography

[1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering Pub Date : 1900-01-01 DOI:10.1109/ICNN.1991.163333

W. Gan

引用次数: 0

Abstract

Ocean acoustic tomography differs from medical ultrasound tomography and seismic tomography in that one must first understand the forward problem, that is, how the sound channel and the mesoscale feature refracts sound in three dimensions and how such refraction alters the pulse-arrival sequence. The parabolic equation (PE) model is used in the forward problem. A neural network is used to perform the inversion of tomography data. The author uses the feedforward neural network to implement the filtered back projection algorithm. The advantages are that one does not need to assume weak scattering and the instability problem of the frequency domain interpolation algorithm does not exist.<>

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

神经网络在海洋声层析成像中的应用

海洋声层析成像与医学超声层析成像和地震层析成像的不同之处在于，人们必须首先了解正向问题，即声道和中尺度特征如何在三维上折射声音，以及这种折射如何改变脉冲到达序列。正演问题采用抛物方程(PE)模型。利用神经网络对层析成像数据进行反演。作者利用前馈神经网络实现滤波后的反投影算法。其优点是不需要假设弱散射，也不存在频域插值算法的不稳定性问题。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

[1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering

自引率

0.00%

发文量

期刊最新文献

Evaluation of neural network and conventional techniques for sonar signal discrimination The potential of a neural network based sonar system in classifying fish Neural network for underwater target detection Design of an intelligent control system for remotely operated vehicles All neural network sonar discrimination system