ID 原文 译文
933 首先，采集人体多模态信号，采用多元经验模态分解对多通道信号进行自适应分解，得到一系列多元固有模态函数(Intrinsic ModeFunctions，IMFs)，依据 T 检验和相关系数从中选取最佳的 IMF 分量进行信号重构; First, the human multi-mode signal was collected. It was adaptively decom-posed by multi-empirical mode from which a series of (IMFs)were obtained. The best IMF components were selected ac-cording to the T-test and correlation coefficients which was used for signal reconstruction.
934 然后，采用多元多尺度熵算法提取特征，用 K-均值与支持向量机对比本文特征提取方法与两种传统特征提取方法在处理人体静态平衡能力评估问题时分类效果，并分析两种分类器的人体静态平衡能力评估效果; The multivariate multi-scale entro-py algorithm was used to extract the features. Finally, K-means and support vector machine were used to compare with This paper's methods about dealing with human body static balance problem, which was used to evaluate the optimal feature ex-traction method.
935 最后，得出本文最优的特征为基于多元经验模态分解的多元多尺度熵特征，最优的分类方法为支持向量机。 Results shows that MMSE based on MEMD and support vector machine are optimal for feature extractionand classification in this paper.
936 三维目标的形状变化给目标识别带来很大挑战，同时三维网格模型的不规则数据结构难以直接应用卷积运算提取三维目标特征。 3D object recognition with shape changes is a challenging task. The irregular data structure of the mesh model prevents the operation of the conventional convolution, which brings difficulties to feature extraction of the 3D non-rigid objects.
937 对此，本文提出了一种高效的三维形变目标的网格卷积特征表示方法，准确提取形状信息并进行分类。 In this paper, we propose a method of mesh convolution for 3D non-rigid objects to extract shape features and use them for classification.
938 首先通过网格卷积运算获得形变目标中典型局部曲面形状分布， Firstly, we obtain the distribution of typical patch shapes by the mesh convolution.
939 其次通过马尔科夫链对曲面形状的空间共现关系建模，从而形成三维模型的全局特征描述， Then, we mod-el the spatial co-occurrence relationship by Markov chains to complete the global feature description.
940 最后采用支持向量机实现形变目标分类。 Finally, we use the sup-port vector machine to classify the 3D objects.
941 该方法将连续多项式函数作为卷积模板，实现针对不规则数据结构的网格卷积运算，并且给出了卷积模板参数的无监督学习方法。 Our method adopts the continuous polynomial function as the convolution ker-nel for the irregular data structure, and learn the kernel by an unsupervised learning method.
942 在标准非刚性三维模型数据集 SHREC10 与 SHREC15 上的实验结果表明本文方法能有效提取三维网格模型的形状信息，分类准确率分别达到了 92.88% 与 96.54% 。 Experimental results on the standard non-rigid 3D model datasets show our method can effectively extract the features and achieve classification accuracyof 92. 88% on SHREC10 and 96. 54% on SHREC15, respectively.