首页> 外文会议>37th annual conference on information sciences and systems (CISS 2003) >Desired-Signal-Present SMI Filters with Near Desired-Signal-AbsentPerformance in Data Limited Environments
【24h】

Desired-Signal-Present SMI Filters with Near Desired-Signal-AbsentPerformance in Data Limited Environments

机译:数据受限环境中具有接近期望的信号缺失 r n性能的期望的信号存在SMI过滤器

获取原文
获取原文并翻译 | 示例

摘要

In this paper we quantify theoreticallyrnthe effect of the desired-signal power level onrnthe mean-square filter estimation error and the normalizedrnoutput signal-to-interference-plus-noise ratiorn(SINR) of sample matrix inversion (SMI)-type estimatesrnof the minimum mean-square-error (MMSE)rnand the linearly constrained minimum variancern(LCMV) filters. We prove that in finite data supportrnsituations filters that utilize a sample average estimaternof the desired-signal-absent input correlation matrixrnexhibit superior normalized filter output SINR andrnmean square filter estimation error when comparedrnto filters that utilize a sample average estimate of therndesired-signal-present input correlation matrix. Finally,rnwe investigate pilot-assisted adaptive filter implementationsrnthat exhibit near desired-signal-absentrnSMI-filtering performance while they are trained usingrndesired-signal-present data/observations.
机译:本文从理论上量化了期望信号功率水平对均方滤波器估计误差和归一化样本矩阵求逆(SMI)型估计的输出信噪比(SINR)的影响-平方误差(MMSE)rn和线性约束最小方差(LCMV)滤波器。我们证明,在有限数据支持下,利用样本平均估计值的滤波器与期望信号缺失输入相关矩阵相比,当与利用样本中期望信号-当前输入相关性的样本平均估计值的滤波器进行比较时,表现出较高的归一化滤波器输出SINR和均方滤波器估计误差矩阵。最后,我们研究了飞行员辅助自适应滤波器的实现方式,这些实现方式在使用期望的信号存在数据/观测值进行训练时,表现出接近期望的信号缺失SMI滤波性能。

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