ID	原文	译文
2753	仿真结果说明了在最佳中继功率分配比的条件下可以得到最大的和速率，同时给出了和速率与中继天线数和用户对数的关系，	The simulation results show that the maximum sum ratecan be obtained under the optimal relay power allocation ratio, and the relationship between the sum rate with the number ofrelay antennas and the number of users is given.
2754	并表明了在用户总功率一定的条件下，能量收集中继系统的性能优于传统的没有能量收集的中继系统。	What's more, the performance of the relay system based on energy harves-ting outperforms that without energy harvesting.
2755	针对如何有效使用多源域的决策知识去预测目标域样例标签的问题，提出一种平衡域与样例信息的多源迁移学习算法。	When transfer learning attempts to leverage the decision knowledge effectively from multiple source do-mains to predict the labels of instances accurately in target domain, it should consider how to well balance source and target domains, and their instances in both domains.
2756	为实现上述目的，本文提出了一种基于域与样例平衡的多源迁移学习方法(Multi-source TransferLearning by Balancing both Domains and Instances，MTL-BDI)。	In this paper, a novel multi-source transfer learning method called mlti-sourcetransfer learning by balancing both domains and instances (MTL-BDI)is proposed to achieve the above goal.
2757	该方法的基本思想是将域层面和样例层面的双加权平衡项嵌入到迁移学习的原始目标函数中，然后利用交替优化技术对提出的目标函数进行有效求解。	The basic ideaof the proposed method is to embed the doubly weighted domain-level and instance-level balance term into the original ob-jective function of transfer learning and then solve the proposed objective function effectively by using the alternating optimi-zation technique.
2758	在文本和图像数据集上的大量实验表明，该方法在分类精度方面确实优于现有的多源迁移学习方法 MCC-SVM(Multiple Convex Combinationof SVM)、A-SVM(Adaptive SVM)、Multi-KMM(Multiple Kernel Mean Matching)和 DAM(Domain Adaptation Machine)。	Extensive experiments on text and image datasets indicate that the proposed method indeed outperformsseveral existing multi-source transfer learning methods MCC-SVM (Multiple Convex Combination of SVM), A-SVM (A-daptive SVM), Multi-KMM (Multiple Kernel Mean Matching)and DAM (Domain Adaptation Machine)in the sense of classification accuracy on target domain.
2759	本文针对矢量基二维 DCT 修剪提出内存存取减少方法。	This paper proposes a novel memory reference reduction method for vector-radix 2D DCT pruning.
2760	该方法旨在减少计算中因权重因子和信号输入而导致的内存存取。	this method aims to reduce the memory reference owing to weighting factors and signal input.
2761	它首先利用权重因子的属性将计算流程图内每相邻两阶段内的蝴蝶运算单元进行融合，然后再以较少的权重因子来计算。	The proposed method merges the butterflies at every neighboring two stages in the computation diagram, and then computes them with fewer weighting fac-tors.
2762	本文采用通用 DSP 处理器来验证该方法对矢量基二维 DCT 修剪算法的有效性。	Hardware platform based on general purpose processor is used to verify the effectiveness of the proposed method forvector-radix 2-D FCT pruning implementation.