ID	原文	译文
1683	构建 FIR 滤波器滤除所需线性加速度中的噪声，并检测引航员登离船过程中的姿态信息;最终与攀爬防护装置进行联动配合实现。	Then the FIR filter had been constructed to filter the noise in the linear acceleration, and had detected the attitude information during the pilot＇s departure, and Realization of Linkage with Safety Climbing Protective Device.
1684	实验结果表明:该检测方法实现了引航员登离船姿态判断，降低了姿态判断的误操作率，能够较好地区分其他误动作。	The experimental results show the detection method realizes the attitude judgment of pilotboarding ship and reduces the incorrect operation rate, being better divided into other incorrect behavior.
1685	低频通信中脉冲型噪声会严重降低通信性能。	Impulsive noise can greatly degrade the performance of long wave communications.
1686	针对脉冲型噪声的抑制问题，本文提出高斯拖尾零记忆非线性(Gaussian-tailed Zero Memory Nonlinearity，GZMNL)函数的最优化设计方法。	This paper proposes the optimal design of the Gaussian-tailed zero memory nonlinearity (GZMNL)function to suppress impulsive noise.
1687	GZMNL 函数含有两个参数，分别控制其线性范围和拖尾程度，故适用于多种噪声分布。	The GZMNL function which was proposed for the symmetric α-stable (SαS)noise is not robust in applications, because of the lack of adaptive parameters.
1688	本文提出 GZMNL 设计以效能最大化为优化目标，采用自适应搜索算法来寻找 GZMNL 参数的最佳值。	This paper proposes to design the GZMNL parameters adaptively to control the linear range and the tails, so that the GZMNL can be effective for various noise distributions. In the GZMNL design, the efficiency is em-ployed as the objective function which is maximized over the GZMNL parameters.
1689	然后讨论了 GZMNL 在 SαS(Symmetric α-Stable，SαS)噪声分布下的快速设计方法，以及在未知噪声分布时的稳健设计方法。	To solve this optimization problem, we develop a derivative-free optimization algorithm which searches the maximum efficacy adaptively. Considering practical ap-plications, we propose two fast algorithms for the GZMNL design in the SαS noise, as well as a robust method for theGZMNL design in unknown noise distributions.
1690	最后，仿真 SαS 噪声和实测大气噪声数据的处理结果表明:本文设计方法在检测性能上能够接近最优非线性，且能够有效抑制未知分布的噪声。	Simulation results based on the SαS noise and real atmospheric noise show that the GZMNL design achieves almost the best nonlinearity in known noise distributions. The GZMNL design is effectiveand robust for unknown noise distributions.
1691	如何将带有大量标记数据的源域知识模型迁移至带有少量标记数据的目标域是少样本学习研究领域的热点问题。	How to migrate a source domain knowledge model with a large amount of tagged data to a target domain with a small amount of tagged data is a hot issue in few-shot learning.
1692	针对现有的少样本学习算法在源域数据与目标域数据的特征分布差异较大时存在的泛化能力较弱的问题，提出一种基于伪标签的半监督少样本学习模型 FSLSS(Few-Shot Learning based on Semi-Supervised)。	For the problems that the existing few-shot learning algorithm have weak generalization ability when the difference between the feature distribution of the source domain data andthe target domain data is large, a few-shot learning model based on semi-supervised FSLSS(Few-Shot Learning based on Semi-Supervised) is proposed.