...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Sensors Journal, IEEE >Image Reconstruction Based on Convolutional Neural Network for Electrical Resistance Tomography
【24h】

Image Reconstruction Based on Convolutional Neural Network for Electrical Resistance Tomography

机译：基于卷积神经网络的电阻层析成像图像重建

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image reconstruction is a key problem for electrical resistance tomography (ERT). Because of the soft-field nature and the ill-posed problem in solving inverse problem, traditional image reconstruction methods cannot achieve high accuracy and the process is usually time consuming. Since deep learning is good at mapping complicated nonlinear function, a deep learning method based on convolutional neural network (CNN) is proposed for image reconstruction of ERT. To establish the database, 41122 samples were generated with numerical simulations. 10-fold cross validation was used to divide all samples into training set and validation set. The network structure was based on LeNet, and refined by applying dropout layer and moving average. After 346 training epochs, the image correlation coefficient (ICC) on validation set was 0.95. When white Gaussian noise with a signal-to-noise ratio of 30, 40, and 50 were added to validation set, the ICC was 0.79, 0.89, and 0.93, respectively, which proved the anti-noise capability of the network. The reconstruction results on samples which have more inclusions, different conductivity, and other shapes explained the network has good generalization ability. Furthermore, experimental data from a 16-electrode industrial ERT system was used to compare the accuracy of the proposed model with some typical reconstruction methods. Results show that the proposed CNN method has better reconstruction results than LBP, Tikhonov, and Landweber.
机译：图像重建是电阻层析成像（ERT）的关键问题。由于软场的性质和解决反问题的不适定问题，传统的图像重建方法无法达到很高的精度，并且该过程通常很耗时。由于深度学习擅长映射复杂的非线性函数，因此提出了一种基于卷积神经网络（CNN）的深度学习方法，用于ERT的图像重建。为了建立数据库，通过数值模拟生成了41122个样本。使用10倍交叉验证将所有样本分为训练集和验证集。网络结构基于LeNet，并通过应用辍学层和移动平均值进行完善。经过346个训练时期，验证集上的图像相关系数（ICC）为0.95。将信噪比分别为30、40和50的高斯白噪声添加到验证集时，ICC分别为0.79、0.89和0.93，证明了该网络的抗噪声能力。对具有更多夹杂物，不同电导率和其他形状的样本的重建结果说明该网络具有良好的泛化能力。此外，来自16电极工业ERT系统的实验数据被用于比较所提出模型与一些典型重建方法的准确性。结果表明，所提出的CNN方法具有比LBP，Tikhonov和Landweber更好的重建结果。

著录项

  • 来源
    《Sensors Journal, IEEE》 |2019年第1期|196-204|共9页
  • 作者

    Chao Tan; Shuhua Lv; Feng Dong; Masahiro Takei;

  • 作者单位

    Tianjin Key Laboratory of Process Measurement and Control, School of Electrical and Information Engineering, Tianjin University, Tianjin, China;

    Tianjin Key Laboratory of Process Measurement and Control, School of Electrical and Information Engineering, Tianjin University, Tianjin, China;

    Tianjin Key Laboratory of Process Measurement and Control, School of Electrical and Information Engineering, Tianjin University, Tianjin, China;

    Graduate School of Engineering, Chiba University, Chiba, Japan;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Image reconstruction; Training; Conductivity; Machine learning; Mathematical model; Sensors; Voltage measurement;

    机译：图像重建;训练;电导率;机器学习;数学模型;传感器;电压测量;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号