ID 原文 译文
18985 进一步，利用凸优化理论和拉格朗日对偶分解方法得到功率分配策略。 Furthermore, the power allocation policy is obtained by utilizing successive convexoptimization theory and Lagrange dual decomposition method.
18986 最后，仿真结果表明，该文算法可以满足不同用户的服务质量(QoS)需求，并在保证网络稳定性前提下提高系统能效。 Finally, the simulation results show that the proposed algorithm can improve the system energy efficiency and ensure the Quality of Service (QoS)requirements of different users and network stability.
18987 多元医学信号的典型代表有多模态睡眠图和多通道脑电图等，采用无监督深度学习表征多元医学信号是目前健康信息学领域中的一个研究热点。 Learning unsupervised representations from multivariate medical signals, such as multi-modality polysomnography and multi-channel electroencephalogram, has gained increasing attention in health informatics.
18988 为了解决现有模型没有充分结合医学信号多元时序结构特点的问题，该文提出了一种无监督的多级上下文深度卷积自编码器(mCtx-CAE)。 In order to solve the problem that the existing models do not fully incorporate the characteristics of the multivariate-temporal structure of medical signals, an unsupervised multi-Context deep Convolutional AutoEncoder (mCtx-CAE) is proposed in this paper.
18989 首先改进传统卷积神经网络结构，提出一种多元卷积自编码模块，以提取信号片段内的多元上下文特征； Firstly, by modifying traditional convolutional neural networks, a multivariate convolutional autoencoder is proposed to extract multivariate context features within signal segments.
18990 其次，提出采用语义学习技术对信号片段间的时序信息进行自编码，进一步提取时序上下文特征； Secondly, semantic learning is adopted to auto-encode temporal information among signalsegments, to further extract temporal context features.
18991 最后通过共享特征表示设计目标函数，训练端到端的多级上下文自编码器。 Finally, an end-to-end multi-context autoencoder istrained by designing objective function based on shared feature representation.
18992 实验结果表明，该文所提模型在两种应用于不同医疗场景下的多模态和多通道数据集(UCD和CHB-MIT)上表现均优于其它无监督特征学习方法，能有效提高多元医学信号的融合特征表达能力，对提高临床时序数据的分析效率有着重要意义。 Experimental results conducted on two public benchmark datasets (UCD and CHB-MIT) show that the proposed model outperforms the state-of-the-art unsupervised feature learning methods in different medical tasks, demonstrating the effectiveness of the learned fusional features in clinical settings.
18993 针对行人再识别中由于外观差异不显著导致特征描述不准确的问题，该文提出一种基于双向参考集矩阵度量学习(BRM2L)的行人再识别算法。 To solve the problem of inaccurate feature representation caused by indistinctive appearancedifference in person re-identification domain, a new Matrix Metric Learning algerithm based on BidirectionalReference (BRM2L) set is proposed.
18994 首先通过互近邻算法获得每个摄像头下的互近邻参考集，为保证参考集的鲁棒性，联合考虑各摄像头下的互近邻参考集获得双向参考集。 Firstly, reciprocal-neighbor reference sets in different camera views are respectively constructed by the reciprocal-neighbor scheme. To ensure the robustness of reference sets, thereference sets in different camera views are jointly considered to generate the Bidirectional Reference Set(BRS).