对SVM多元非线性回归泛化性能进行测试，其均方根相对误差为1.06%，平均绝对相对误差为0.96%，最大绝对相对误差为1.16%。

The root mean square relative error, mean absolute relative error and maximize absolute relative error of SVM model generalization performance are 1.06%, 0.96% and 1.16%, respectively.

youdao

仿真实验表明该算法能够将航迹平均周期提高一倍，在航迹中断期间对比最小二乘方法能够较大幅度地减小跟踪位置和速度的均方根误差。

Simulation results show that the proposed algorithm doubles the mean track life and yields significant improvements in position and speed RMS errors during the track breakage.

youdao

对多聚焦图像和多光谱彩色图像分别采用计算图像信息熵和均方根误差、计算图像平均梯度的方法对融合的性能进行评价。

There is explicit characteristic of correspondence reflecting the droplet transfer among the electric, spectral and image information based on time information fusion.

youdao