本文给出了在混合噪声中非线性递归最小均方误差算法的性能分析。
This paper presents the performance analysis of recursive least square algorithm with error-saturation in mixture noise.
该算法实现了横摆角速度的线性最小均方误差估计，且可对汽车行驶过程中的系统噪声和观测噪声统计特性进行在线估计。
This algorithm can realize linear minimum mean square error estimation of yaw rate, and on-line estimate statistical characteristic of system noise and observation noise during vehicle running.
介绍了码分多址CD MA系统中码片级线性最小均方误差均衡器。
The chip level linear minimum mean square error (LMMSE) equalizer in CDMA systems is introduced.
WELCH（1983）给出了单响应线性模型均方误差准则下的最优试验设计。
WELCH(1983) has given a mean squared error criterion for optimal design of single-response linear model.
引出了子空间方法多用户检测的概念，并给出了线性解相关(dec)多用户检测和最小均方误差(MMSE)多用户检测的子空间表示。
Educe the concept of subspace approach for multi-user detection, give out the subspace expression about DEC and MMSE multi-user detection.
给出了线性分集均衡器和判决反馈分集均衡器两种结构的工作原理，并从理论上证明了后者的最小均方误差性能优于线性空间分集组合器；
The principles of the linearity diversity equalizer and decision feedback diversity equalizer are presented, and the MMSE of the latter is proved to be better than the former.
本文以多元线性回归模型的典则形式为研究对象，从减小均方误差的角度出发，在一定的范围内分析了岭参数K 的存在性和岭估计的优良性。
The investigation object of this paper is the standard canonical form. In order to the mean square error, I analyze the existence and choiceness of ridge regression K in some spectrum.
使用等效线性化技术与单模态近似得到响应的均方误差方程。
A response equation for the mean square deflection is obtained under a single mode approximation by using the equivalent linearization technique.
对于一般几何模型的非线性最小均方误差拟合，首先必须定义拟合误差，然后采用非线性最优化方法求解最小误差意义下的最优解。
Firstly, the error of fit must be defined for nonlinear least-square fitting of generalized geometry model. Then the nonlinear optimization algorithm can be used to obtain the optimum solution.
由于该方案是基于近似的线性最小均方误差估计准则而设计的，因此它是一种理论上的准最佳跟踪方案。
As the scheme is designed conforming to the criteria of approximate linear least-mean-square error estimation, it is theoretically quasi-optimal.
结果显示，该模型预测效果明显优于传统的线性自回归预测模型，各月平均的平均绝对误差（MAE）和均方误差（RMSE）达到41.8和55.7。
Results show that the RBFNN is obviously superior to the traditional linear model, and its MAE (mean absolute error) and RMSE (root mean square error) are 41.8 and 55.7, respectively.
结果显示，该模型预测效果明显优于传统的线性自回归预测模型，各月平均的平均绝对误差（MAE）和均方误差（RMSE）达到41.8和55.7。
Results show that the RBFNN is obviously superior to the traditional linear model, and its MAE (mean absolute error) and RMSE (root mean square error) are 41.8 and 55.7, respectively.
应用推荐