在数据后处理方面，本文提出了加权最小二乘法，使维数计算更精确，更适合实际。
And the weighted least squares method is presented for gaining more accurate results of correlation dimensions.
从中发现，蠕变程度越严重的区域，其分形维数越小，在断裂的地方达到最小。
It follows from this that the fractal dimension is less while the creep is more serious, the value attains minimum in crack.
利用伪最邻近点法确定相空间重构的最小嵌入维数。
The minimum embedding dimension of reconstruction is confirmed by the false nearest neighbours method.
用高斯-牛顿误差最小法将六维观测量转化为四元数，作为观测量的一部分，显著减少了直接使用EKF的计算量。
Gauss-Newton error minimization is used to transform six-dimentional reference vector to quaternion as a part of observations for EKF, which significantly reduces the computational requirement.
运用降维技术探讨adr因果关系判断的最小因子数。
The minimum number of causality judgement indicators of ADR was determined by dimension reduction method.
分形维数不仅可以表征声发射的频度，而且分维最小值往往预示着一个大破裂的发生。
Not only can the fractal dimension characterize the frequency of acoustic emission but its least value often predicts a large breakage.
论文将对偶四元数法应用到三维物体识别的匹配算法中，利用最小二乘的思想提出了一种基于迭代最近点的匹配算法。
Last, we apply the dual quaternion algorithm to matching algorithm of 3d object recognition and make use of least-squares technique to propose a matching method based on iterative closest point.
论文将对偶四元数法应用到三维物体识别的匹配算法中，利用最小二乘的思想提出了一种基于迭代最近点的匹配算法。
Last, we apply the dual quaternion algorithm to matching algorithm of 3d object recognition and make use of least-squares technique to propose a matching method based on iterative closest point.
应用推荐