ID 原文 译文
24345 由于概率分布是非线性、多峰值的，采用带有惯性权重的粒子群算法去求解。 Because of the nonlinear and multi-peak features of the probability distribution, the standard particle swarm optimization method is adopted to solve the problem.
24346 仿真实验结果表明，所提方法能够在节点失效的情况下获得较高的目标定位性能，具有较好的鲁棒性。 Simulations indicate that the proposed method avoids effectively the influence of the invalid anchors on the performance of localization, and has better accuracy and robustness compared with other cross-bearing localization methods in the complex underwater environment.
24347 该文针对瑞利衰落信道中采用 Chase 合并混合自动重传请求(CC-HARQ)协议的多跳中继网络提出一种基于跨层设计的能量效率优化策略。 The cross-layer optimum scheme of Energy Efficiency (EE) for a multihop relay network with Chase-Combining based Hybrid Automatic Repeat reQuest (CC-HARQ) in Rayleigh fading channels is proposed.
24348 为实现能量效率的最大化，基于对数域线性阈值的平均误帧率模型，推导出多跳CC-HARQ 系统能量效率的闭合表达式，进而设计了最优发送帧长策略和最优发送功率分配方案，其次，针对发送帧长和发送功率分析了两者的联合优化方案。 In order to maximize EE, a closed-form expression of Energy Efficiency in a multihop CC-HARQ system is derived, which is obtained via an average frame error rate model adopting a new log-domain linear threshold method. Then optimal frame length scheme and optimal transmission power allocation method are further designed, towards the frame length and transmission power, and a joint optimization metric of those two parameters is considered.
24349 仿真结果验证了理论分析的正确性和可行性，仿真对比实验表明所提跨层优化设计方案可以有效提升实际多跳网络的能量效率性能。 Simulation results verify the correctness and feasibility of the analytical solutions, meanwhile, simulation experiments of comparisons show that the proposed cross-layer optimization design is able to improve the EE performance of practical multihop networks.
24350 为了将无监督特征学习应用于小样本量的图像情绪语义分析，该文采用一种基于卷积稀疏自动编码器进行自学习的领域适应方法对少量有标记抽象图像进行情绪性分类。 To apply unsupervised feature learning to emotional semantic analysis for images in small sample size situations, convolutional sparse autoencoder based self-taught learning for domain adaption is adopted for affective classification of a small amount of labeled abstract images.
24351 并且提出了一种采用平均梯度准则对自动编码器所学权重进行排序的方法，用于对基于不同领域的特征学习结果进行直观比较。 To visually compare the results of feature learning on different domains, an average gradient criterion based method is further proposed for the sorting of weights learned by sparse autoencoders.
24352 首先在源领域中的大量无标记图像上随机采集图像子块并利用稀疏自动编码器学习局部特征，然后将对应不同特征的权重矩阵按照每个矩阵在 3 个色彩通道上的平均梯度中的最小值进行排序。 Image patches are first randomly collected from a large number of unlabeled images in the source domain and local features are learned using a sparse autoencoder. Then the weight matrices corresponding to different features are sorted according to the minimal average gradient of each matrix in three color channels.
24353 最后采用包含池化层的卷积神经网络提取目标领域有标记图像样本的全局特征响应，并送入逻辑回归模型进行情绪性分类。 Global feature activations of labeled images in the target domain are finally obtained by a convolutional neural network including a pooling layer and sent into a logistic regression model for affective classification.
24354 实验结果表明基于自学习的领域适应可以为无监督特征学习在有限样本目标领域上的应用提供训练数据，而且采用稀疏自动编码器的跨领域特征学习能在有限数量抽象图像情绪语义分析中获得比底层视觉特征更优秀的辨识效果。 Experimental results show that self-taught learning based domain adaption can provide training data for the application of unsupervised feature learning in target domains with limited samples. Sparse autoencoder based feature learning across different domains can produce better identification effect than low-level visual features in emotional semantic analysis of a limited number of abstract images.