ID 原文 译文
16755 主要通过不同体制的雷达利用认知技术感知和学习外界复杂的电磁环境，合理地分配发射功率、控制编码序列、设计波形、研究检测和跟踪方法以及分配雷达通信资源等。 Different radar systems make use of cognitive techniques perceive and learn the complex electromagnetic environment, and reasonably allocate transmitting power, control coding sequence, design waveform, investigate detection and tracking methods and allocate resources of radar communication etc.
16756 这样雷达既节约发射所消耗的功率，又可以自适应地搜索和跟踪目标而不被敌方所发现，从而使雷达在复杂多变的现代战场环境中达到自身最优的性能。 In this way, radar can notonly reduce power consumption, but also search and track the target without being detected by the enemy.Thus, radar can achieve its optimal performance in the complex and changeable modern battlefieldenvironment.
16757 最后，对认知雷达抗干扰中的博弈论分析研究进行总结和展望，并指出了一些博弈论在认知雷达抗干扰策略应用中所面临的潜在问题和挑战。 Finally, game theory in cognitive radar anti-jamming is summarized and prospected, and it alsopoints out some potential problems and challenges of game theory in cognitive radar anti-jamming.
16758 得益于计算机硬件以及计算能力的进步，自然、简单的动态手势识别在人机交互方面备受关注。 Benefits from the progress of computer hardware and computing power, natural and simple dynamic gesture recognition gets a lot of attention in human-computer interaction.
16759 针对人机交互中对动态手势识别准确率的要求，该文提出一种融合双流3维卷积神经网络(I3D)和注意力机制(CBAM)的动态手势识别方法CBAM-I3D。 In view of the requirement of theaccuracy of dynamic gesture recognition in human-computer interaction, a method of dynamic gesturerecognition that combines Two-stream Inflated 3D (I3D) Convolution Neural Network (CNN) with theConvolutional Block Attention Module (CBAM-I3D) is proposed.
16760 并且改进了I3D网络模型的相关参数和结构，为了提高模型的收敛速度和稳定性，使用了批量归一化(BN)技术优化网络，使优化后网络的训练时间缩短。 In addition, relevant parameters andstructures of the I3D network model are improved. In order to improve the convergence speed and stability ofthe model, the Batch Normalization (BN) technology is used to optimize the network, which shortens thetraining time of the optimized network.
16761 同时与多种双流3D卷积方法在开源中国手语数据集(CSL)上进行了实验对比， At the same time, experimental comparisons with various Two-stream3D convolution methods on the open source Chinese Sign Language (CSL) recognition dataset are performed.
16762 实验结果表明，该文所提方法能很好地识别动态手势，识别率达到了90.76%，高于其他动态手势识别方法，验证了所提方法的有效性和可行性。 The experimental results show that the proposed method can recognize dynamic gestures well, and therecognition rate reaches 90.76%, which is higher than other dynamic gesture recognition methods. The validityand feasibility of the proposed method are verified.
16763 针对Z向转发(ZF)协作所有中继节点均参与协作转发导致的能耗利用不合理问题， 该文提出了一种适用于多中继场景下的门限辅助判决快速Z转发(DT-FZF)协作。 In consideration of improper power allocation and insufficient relay selection in the current Z-Forward (ZF) scheme, an efficient Decision Threshold-aided Fast Z-Forward (DT-FZF) scheme is proposed toimprove power and transmission efficiency.
16764 当中继节点处接收信号对数似然比(LLR)的绝对值小于门限时，中继节点不参与协作转发； When the absolute value of the Log-Likelihood Ratio (LLR) of asource-relay reception is less than the decision threshold, the relay remains quiet.