ID	原文	译文
25845	随着模型的迭代更新，标签可信数据的权重将会逐渐变大，而噪声数据的权重将会被抑制。	As the model is up-dated iteratively, the weight of clean data will gradually increase, while the weight of noise data will be suppressed．
25846	本文通过在多个标注数据集上的实验验证了所提出的噪声抑制深度学习策略的有效性。	Experiments on multiple benchmark data sets demonstrate the effectiveness of the proposed deep learning strategy for noise suppression．
25847	局部特征尺度分解( LCD) 是为克服经验模态分解( EMD) 中均值曲线构造的不足而提出的一种自适应信号分解方法，已被应用于机械故障诊断领域。	Local characteristic-scale decomposition ( LCD) is an adaptive signal decomposition method proposed to overcome the shortcomings of mean curve construction in empirical mode decomposition ( EMD) and has been applied to mechanical fault diagnosis．
25848	但 LCD 存在与 EMD 类似的模态混叠问题，为此，基于均匀相位差掩膜信号构造，提出了自适应掩膜信号集成局部特征尺度分解( AMSELCD) ，该方法不仅能够将一个复杂信号自适应地分解为若干个本征模态函数和一个剩余项之和，而且能够有效地解决 LCD 的模态混叠现象。	However, LCD also has the mode mixing problem that exists in EMD. Based on the construction of masking signal with uniform phase difference, the adaptive mask signal ensemble local characteristic-scale decomposition ( AMSELCD) is proposed in this paper to adaptively decompose a complex signal into several intrinsic mode functions anda residue, which can effectively alleviate the mode mixing phenomenon of LCD．
25849	通过仿真信号分析，将 AM-SELCD 与现有多种抑制模态分解方法进行了对比，结果表明了所提方法的有效性和优越性。	AMSELCD is compared with various existing methods for restraining mode mixing through simulation signal analysis and the results show the effectiveness and superiority of the proposed method．
25850	最后，针对滚动轴承和转子碰摩故障振动信号的调制特征，将所提 AMSELCD 方法应用于转子碰摩和滚动轴承的故障诊断，对比和实验分析结果进一步验证了所提方法的有效性和优越性。	Finally, aiming at the modulation characteristics of fault signals of rolling bearing and rotorrubbing, the proposed AMSELCD method is applied to the fault diagnosis of rotor rubbing and rolling bearing, and the experimental comparison analysis results further verify the effectiveness and superiority of AMSELCD．
25851	云接入网(Cloud Radio Access Network，C-RAN)中有限带宽的前程链路无法有效应对高铁场景下乘客大量集中式的网络资源请求。	The cloud radio access network (C-RAN) with limited-capacity fronthauls cannot cope with the large-scale centralized passenger resource requests efficiently in high-speed railway (HSR) scenarios．
25852	针对这一不足，本文对 C-RAN 架构中的射频拉远头(Remote Radio Head，RRH)配置缓存设备使其具有存储转发资源的功能，利用列车运行信息可预知的先验条件，针对乘客数据通信提出基于缓存机制的预下载方案以提升网络系统的吞吐量。	As such, this paper adds a cache device to the remote radio head (RRH) to enable the function of storing and forwarding resources. Moreover, a cache-based pre-downloading scheme for passenger data communication is proposed to improve the network throughput by using the predictive information of the train．
25853	仿真结果表明，在前程链路拥挤情况下，基于缓存的预下载方案可明显提升资源的平均传输速率和高铁通信网络的吞吐量，进而提升了乘客的在途通信服务质量(Quality of Service，QoS)。	The simulation results show that the proposed scheme can significantly boost the average transmission rate of resources, enhance the throughput of HSR communication network and improve passengers in-jour-ney communication quality of service (QoS) when the fronthaul link is congested．
25854	端到端的驾驶决策是无人驾驶领域的研究热点。	The end-to-end driving decision making is a research hots pot in the field of autonomous driving．