ID 原文 译文
47076 针对通信辐射源的个体识别问题，提出一种基于希尔伯特—黄变换（HHT, Hilbert-Huang transform）和多尺度分形特征的新方法。 For communication emitter identification, a novel method based on Hilbert-Huang transform (HHT) and mul-ti-scale fractal features was proposed.
47077 首先，通过 HHT 得到时频能量谱，将其视为三维空间中的复杂曲面，即 3D-Hilbert能量谱； First, the time frequency energy spectrum was derived via HHT, which was called acomplicated curved surface in the three-dimension space, namely, 3D-Hilbert energy spectrum.
47078 然后，利用分形理论通过多尺度分块提取差分盒维数和多重分形维数二维特征组成特征向量； Then, the differential boxdimension and the multi-fractal dimension was extracted to compose the feature vector under multi-scale segmentationusing fractal theory.
47079 最后，采用支持向量机分类器结合二维特征向量实现通信辐射源的个体分类。 Finally, communication emitter individual identification was obtained using the two dimensions offeatures above and the support vector machine (SVM).
47080 分别利用仿真信号和调制方式相同的实际通信信号，验证并对比了所提方法与另外 2 种方法在 2 类及 3 类目标情况下的识别性能。 Moreover, the novel method was compared with two existing me-thods to identify simulated and actual signals with different and the same modulation modes, respectively.
47081 实验结果表明，所提方法的识别率远高于其他 2 种方法，能够克服低信噪比和少训练样本数量对识别性能的负面影响， Results showthat the identification rate of the novel method is higher than that of the two other methods.
47082 证明了所提特征的稳定性、充分性及可分性。 The features extracted by thenovel method have high stability, sufficiency, and identifiability, also outweigh the negative effects of the change of sig-nal-to-noise ratio and the number of training samples and emitters.
47083 提出了一种改进的文本表示模型提取文本特征词向量方法。 Method of text representation model was proposed to extract word-embedding from text feature.
47084 首先构建基于词典索引和所对应的词性索引的 double word-embedding 列表的 word-embedding 词向量， Firstly, theword-embedding of the dual word-embedding list based on dictionary index and the corresponding part of speech indexwas created.
47085 其次，利用在此基础上 Bi-LSTM 循环神经网络对生成后的词向量进一步进行特征提取， Then, feature vectors was obtained further from these extracted word-embeddings by using Bi-LSTM recur-rent neural network.