...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Signal processing >Adaptive complex-valued dictionary learning: Application to fMRI data analysis
【24h】

Adaptive complex-valued dictionary learning: Application to fMRI data analysis

机译：自适应复数值字典学习：在fMRI数据分析中的应用

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

Complex-valued signals arise naturally in a wide-range of applications such as radar, magnetic resonance imaging (MRI), functional MRI (fMRI), remote sensing, communication systems, etc. In this article, we propose an adaptive dictionary learning (DL) algorithm for such complex-valued signals. The algorithm is derived via adaptively penalized, sequential rank-1 matrix approximations using the l(1)-norm as sparsity inducing penalty. Instead of alternating between sparse coding and dictionary update stages, each atom and its support are updated alternately with both variables admitting simple closed form solutions. A comprehensive performance comparison on simulated as well as experimental task-fMRI datasets is provided between the proposed DL method, complex-valued independent component analysis-entropy bound minimization (ICA-EBM), and magnitude-only ICA (Infomax) algorithms. The results highlight superior performance accuracy of the proposed algorithm w.r.t. the ICA-EBM and Infomax algorithms, in terms of true and false positive rates of the recovered task-related and default mode network (DMN) components. Our method was able to recover good quality phase maps as well, which can be used to further identify and suppress unwanted voxels. (C) 2019 Elsevier B.V. All rights reserved.
机译：复数值信号在诸如雷达，磁共振成像（MRI），功能性MRI（fMRI），遥感，通信系统等广泛的应用中自然产生。在本文中，我们提出了一种自适应词典学习（DL） ）的算法来处理此类复数值信号。该算法是通过使用l（1）-范数作为稀疏性诱导惩罚通过自适应惩罚的顺序秩1矩阵近似导出的。取代稀疏编码和字典更新阶段之间的交替，每个原子及其支持都使用允许简单封闭形式解的两个变量交替更新。在拟议的DL方法，复数值独立分量分析-熵约束最小化（ICA-EBM）和仅幅度ICA（Infomax）算法之间，提供了模拟任务和实验任务fMRI数据集的综合性能比较。结果突出了所提出算法w.r.t. ICA-EBM和Infomax算法，根据已恢复的与任务相关和默认模式网络（DMN）组件的正确率和错误率。我们的方法也能够恢复高质量的相位图，可用于进一步识别和抑制不想要的体素。 （C）2019 Elsevier B.V.保留所有权利。

著录项

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