...
首页> 外文期刊>Automatic Control, IEEE Transactions on >A Weighted Least-Squares Approach to Parameter Estimation Problems Based on Binary Measurements
【24h】

A Weighted Least-Squares Approach to Parameter Estimation Problems Based on Binary Measurements

机译:基于二元测量的参数估计加权最小二乘方法

获取原文
           

摘要

We present a new approach to parameter estimation problems based on binary measurements, motivated by the need to add integrated low-cost self-test features to microfabricated devices. This approach is based on the use of original weighted least-squares criteria: as opposed to other existing methods, it requires no dithering signal and it does not rely on an approximation of the quantizer. In this technical note, we focus on a simple choice for the weights and establish some asymptotical properties of the corresponding criterion. To achieve this, the assumption that the quantizer's input is Gaussian and centered is made. In this context, we prove that the proposed criterion is locally convex and that it is possible to use a simple gradient descent to find a consistent estimate of the unknown system parameters, regardless of the presence of measurement noise at the quantizer's input.
机译:我们提出了一种基于二进制测量的参数估计问题的新方法,其动机是需要向微型设备中添加集成的低成本自检功能。该方法基于原始加权最小二乘标准的使用:与其他现有方法相反,它不需要抖动信号,并且不依赖于量化器的近似值。在本技术说明中,我们专注于权重的简单选择,并建立了相应准则的一些渐近性质。为了实现这一点,假设量化器的输入是高斯且居中。在这种情况下,我们证明了提出的准则是局部凸的,并且有可能使用简单的梯度下降来找到未知系统参数的一致估计,而不管量化器输入端是否存在测量噪声。

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