| ID | 原文 | 译文 |
| 3973 | 所提方案在满足信道状态较差节点速率的条件下，推导出信号功率分配的表达式，并得出系统中断概率的数学表达式，最后通过选取合适的时间分配参数来提升中断性能。 | In the proposed scheme, theexpression of signal power distribution was obtained under the condition of satisfying the quality of service (QoS) rate of the node with poor channel state, and then the relation between the interruption probability and the time distribution of the system was deduced, the time allocation parameter was adjusted to affect the outage probability. |
| 3974 | 仿真结果表明，所提系统模型具有比正交多址接入（OMA）系统更好的中断性能，所提优化方案可有效降低系统的中断概率，提高系统性能。 | The simulation re-sults show that the constructed NOMA system has better outage performance than orthogonal multiple access (OMA)system, and the proposed joint signal power and time allocation outage scheme can effectively reduce the interruptionprobability of the system and improve the system performance. |
| 3975 | 针对传统多维度文本聚类算法把文本表示与聚类过程分离，忽略了维度间的互补特性的问题，提出了一种差异互补的迭代式多维度文本聚类算法——CMDC，实现文本聚类与特征调整过程的统一优化。 | In response to the problems traditional multi-view document clustering methods separate the multi-view doc-ument representation from the clustering process and ignore the complementary characteristics of multi-view document clustering, an iterative algorithm for complementary multi-view document clustering——CMDC was proposed, in which the multi-view document clustering process and the multi-view feature adjustment were conducted in a mutually unified manner. |
| 3976 | CMDC 算法挑选维度聚类间结果的互补文本，基于局部度量学习算法利用互补文本促进聚类的特征调优，以维度的度量一致性来解决多维度文本聚类的划分一致性。 | In CMDC algorithm, complementary text documents were selected from the clustering results to aid adjustingthe contribution of view features via learning a local measurement metric of each document view. The complementary text document of the results among the dimensionality clusters was selected by CMDC, and used to promote the featuretuning of the clusters. The partition consistency of the multi-dimensional document clustering was solved by the measure consistency of the dimensions. |
| 3977 | 实验结果表明，CMDC 算法有效地提升了多维度聚类性能。 | Experimental results show that CMDC effectively improves multi-dimensional clusteringperformance. |
| 3978 | 针对边缘算力受限，难以部署复杂结构的人脸检测深度神经网络的问题，为减少资源消耗，并保证人脸在多尺度变化、遮挡、模糊、光照等复杂场景下的检测精度，提出了多尺度感知的轻量化人脸检测算法。 | Aiming at the problem that face detectors with complex deep neural structures are difficult to deploy in the re-source-constrained edge computing environment, to reduce the resource consumption while maintain the accuracy incomplex scenes such as multi-scale face changes, occlusion, blur, and illumination, SDPN(multi-scale aware dual pathnetwork) for face detection was proposed. |
| 3979 | 采用改进的人脸残差神经网络作为特征提取网络，并提出双分支浅层特征提取模块，并行分支理解图像多尺度信息，进而由深浅特征融合模块将底层图像信息与高层语义特征融合，配合多尺度感知的训练策略监督多分支学习差异化特征。 | The Face-ResNet (face residual neural network) was improved, and a dual pathshallow feature extractor was used to understand the multi-scale information of the image through parallel branches. Thenthe deep and shallow feature fusion module, a combination of the underlying image information and the high-level se-mantic feature, was used in conjunction with the multi-scale awareness training strategy to supervise the multi-branchlearning discriminating features. |
| 3980 | 实验结果表明，所提算法可有效提取多样化的特征，在保持模型高效性和低推理时延的同时，有效提升了算法的精度和稳健性。 | The experimental results show that SDPN can extract more diversified features, whicheffectively improve the accuracy and robustness of face detection while maintaining the efficiency of the model and lowinference delay. |
| 3981 | 针对现有范围查询方案进行多维数据查询时缺乏隐私保护的问题，提出了一种带有隐私保护特性的面向雾增强型工业物联网多维安全查询方案。 | In view of the fact that most of the existing range query schemes for fog-enhanced IoT cannot achieve bothmulti-dimensional query and privacy protection, a privacy-preserving multi-dimensional secure query scheme forfog-enhanced IIoT was proposed. |
| 3982 | 该方案首先将用户待查询的多个维度区间映射成一个查询矩阵； | Firstly, the multiple ranges to be queried were mapped into a certain query matrix. |