对于带未知模型参数和噪声方差的多传感器系统,基于分量按标量加权最优融合准则,提出了自校正解耦融合Kalman滤波器,并应用动态误差系统分析(Dynamic error system analysis,DESA)方法证明了它的收敛性.作为在信号处理中的应用,对带有...对于带未知模型参数和噪声方差的多传感器系统,基于分量按标量加权最优融合准则,提出了自校正解耦融合Kalman滤波器,并应用动态误差系统分析(Dynamic error system analysis,DESA)方法证明了它的收敛性.作为在信号处理中的应用,对带有色和白色观测噪声的多传感器多维自回归(Autoregressive,AR)信号,分别提出了AR信号模型参数估计的多维和多重偏差补偿递推最小二乘(Bias compensated recursive least-squares,BCRLS)算法,证明了两种算法的等价性,并且用DESA方法证明了它们的收敛性.在此基础上提出了AR信号的自校正融合Kalman滤波器,它具有渐近最优性.仿真例子说明了其有效性.展开更多
An important and hard problem in signal processing is the estimation of parameters in the presence of observation noise.In this paper, adaptive finite impulse response （FIR） filtering with noisy input-output data is...An important and hard problem in signal processing is the estimation of parameters in the presence of observation noise.In this paper, adaptive finite impulse response （FIR） filtering with noisy input-output data is considered and two developed bias compensation least squares （BCLS） methods are proposed.By introducing two auxiliary estimators, the forward output predictor and the backward output predictor are constructed respectively.By exploiting the statistical properties of the cross-correlation function between the least squares （LS） error and the forward/backward prediction error, the estimate of the input noise variance is obtained; the effect of the bias can thereafter be removed.Simulation results are presented to illustrate the good performances of the proposed algorithms.展开更多
基金Supported by the National Natural Science Foundation of China for Distinguished Young Scholars (Grant No 60625104)the Ministerial Foundation of China (Grant No A2220060039)the Fundamental Research Foundation of BIT (Grant No 1010050320810)
文摘An important and hard problem in signal processing is the estimation of parameters in the presence of observation noise.In this paper, adaptive finite impulse response （FIR） filtering with noisy input-output data is considered and two developed bias compensation least squares （BCLS） methods are proposed.By introducing two auxiliary estimators, the forward output predictor and the backward output predictor are constructed respectively.By exploiting the statistical properties of the cross-correlation function between the least squares （LS） error and the forward/backward prediction error, the estimate of the input noise variance is obtained; the effect of the bias can thereafter be removed.Simulation results are presented to illustrate the good performances of the proposed algorithms.
