ID 原文 译文
12854 采用双向抛物方程(two-way parabolic equation, 2WPE)法来预测复杂海洋环境中的电波传播特性，用双向有限差分(two-way finite-difference, 2WFD)法求解2WPE，考虑了海岛等不规则地形引的电波后向传播和大气波导的影响,并在前向和后向电波传播预测中引入一种改进的分形海面模型来模拟起伏波动的实际海面边界，且能模拟海面的大尺度浪涌特性和毛细波细微结构特性。 In this paper the two-way parabolic equation (2WPE) is used to predict the propagation characteristics of electromagnetic waves in complex sea envronments, and the two-way ;initbdifference(2WFD) method is used to solve the 2WPE. The effects of backward electromagnetic waves caused by irregular terran such as islands and the mfluence of atmospheric duct on electromagnetic waves are considered. An improved fractal sea surface model is introduced in the prediction of forward and backward wave propagation to simulate the actual sea surface boundary.
12855 在典型的数值算例中， 我们将采用改进分形模型处理海面边界时计算得到的双向电波传播因子和采用Mlller-Brown模型处理海面边界时计算得到的双向电波传播因子进行对比和分析，数值分析结果表明，在相同风速条件下，采用改进分形模型处理海面边界时计算得到的双向电波传播因子波动更剧烈，能更准确地反映出实际起伏波动海面对电磁波传播的影响。 This model can simulate characteristics of the large-scale surge and capillary of the sea surface. The two way propagaiion factors calculated by improved fractal sea surface mode! are compared with those calculated by the Mlller-Brown model. The numerical simulaiion results show that under the same wind speed condition, the twcrdi- mensiona! electric wave propagaiion factor calculated by using the improved fractal mode! to deal with the sea surface boundary is more severe, which can more accurately reflect the influence of the actual undulating sea on the electromagnetc wave propagaton.
12856 特征提取是合成孔径雷达(synthetic aperture radar, SAR)目标识别中的关键因素之一。文中提出联合多层次单演谱特征的SAR目标识别方法,采用单演信号对原始SAR图像进行分解,获得不同层次 的单演谱成分。 Feature extraction is one of the key factors in synthetic aperture radar (SAR) target recognition. This paper proposes a SAR target recognition method by jomtly using multi-level monogenic components. The monogenic signa is empHoyed to decompose the originaH SAR images to obtain monogenic spectral components at different levels.
12857 基于斯皮尔曼等级相关分析分解的谱成分与原始SAR图像的相关性,设置相似度门限来选取若干具有较强鉴别力的谱成分。 Afterwards, the Spearman rank correlaion is used to evaluate the s8mlartes between different monogenic components and the original SAR8mage. A threshold is set to select those components with higher similarities with the original image.
12858 采用联合稀疏表示(joint sparse representation, JSR)对筛选得到的谱成分进行表征和分类,并基于MSTAR公开数据集在标准操作条件(standard operating conditions, SOC)和若干扩展操作条件下对多类地面车辆目标进行分类测试。 Then, the joint sparse representation is employed to classify the selected monogenic components for the classitication. The proposed method is tested on the MSTAR public dataset under the standard operating condition (SOC) and several extended operating conditions (EOC) for the recognition task of a few ground vehicles.
12859 实验结果表明：本文方法在SOC下对10类目标的 平均识别率达到98.52% %对30。和45。俯仰角下的10类目标平均识别率分别为98.15%和72. 06%；在噪声干扰条件下也可以保持良好的稳健性。 According to the experimental results, the proposed method could achieve an average recognition of 98. 52% on ten classes of targets under SOC. The average recognition rates at 30° and 45° depresson angles reach 98. 15% and 72. 06% , respectively. In addition, the proposed method could achieve good robustness under noise corruption.
12860 综合对比,提出的方法相比现有几类SAR目标识别方法具有一定的性能优势。 In comparson, the proposed method acheves superiority over several existing SAR target recognition methods.
12861 针对复杂电磁环境下通信辐射源个体识别问题,提出了一种小样本条件下基于深度置信网络的通信辐射源个体识别方法。 Aimmg at the problem of individual identification of communication radiation sources in complex electromagnetic environment, we propose a method of mutual modulation interference recognition of communication radiation sources based on deep confidence network under small sample conditions.
12862 首先分析通信辐射源信号频带内互调干扰信号的幅度和相位特性,建立基于 互调干扰信号的通信辐射源个体特征。 Firstly, we analyze the amplitude and phase characteristics of intermodulation interference of communication radiation sources, which can be used as individual characteristics to distinguish communication radation sources.
12863 然后对辐射源信号进行预处理得到通信辐射源信号的矩形积分双谱, 再采取对比散度的方法,利用高阶谱自底向上训练每个受限玻尔兹曼机,通过多次迭代得到合适的权重、隐藏层的偏差和可见层的偏差,从而提取出辐射信号的互调干扰信号特征。 Then, the square integrated bispectra of communication radiation source adopts contrast divergence method to train each restricted Boltzmann machne from the bottom up, through which the appropriate weights,the deviation of the hidden layer and the deviation of the visible layer are obtaned, which represent the intermodulation interference characteristics of the radiation source signal.