ID	原文	译文
21495	实验结果证明，该算法相比采用欧式距离和DTW距离度量的聚类算法能提高4%的准确度，与采用medoids聚类质心的聚类算法相比计算时间少了一个量级。	The experimental results show that this method can improve the accuracy of 4% compared with clustering algorithm using the Euclidean distance metric or DTW metric, and the calculation time of this method is less a quantity degree than clustering algorithm using medoids centroids.
21496	采用该算法对实网环境中获取的用户流量数据处理证明了该算法拥有可行的应用价值。	This method is used to deal with user traffic data obtained in physical network which proves its application value.
21497	目标跟踪易受光照、遮挡、尺度、背景及快速运动等因素的影响，还要求较高的实时性。	Object tracking is easily influenced by illumination, occlusion, scale, background clutter, and fast motion, and it requires higher real-time performance.
21498	目标跟踪中基于压缩感知的跟踪算法实时性好，但目标外观变化较大时跟踪效果不理想。	The object tracking algorithm based on compressive sensing has a better real-time performance but performs weakly in tracking when object appearance is changed greatly.
21499	该文基于压缩感知的框架提出多模型的实时压缩跟踪算法(MMCT)，采用压缩感知来降低跟踪过程产生的高维特征，保证实时性能；	Based on the framework of compressive sensing, a Multi-Model real-time Compressive Tracking (MMCT) algorithm is proposed, which adopts the compressive sensing to decrease the high dimensional features for the tracking process and to satisfy the real-time performance.
21500	通过判断前两帧的分类器最大分类分数的差值来选择最合适的模型，提高了定位的准确性；	The MMCT algorithm selects the most suitable classifier by judging the maximum classification score difference of classifiers in the previous two frames, and enhances the accuracy of location.
21501	提出新的模型更新策略，按照决策分类器的不同采用固定或动态的学习率，提高了分类精度。	The MMCT algorithm also presents a new model update strategy, which employs the fixed or dynamic learning rates according to the differences of decision classifiers and improves the precision of classification.
21502	MMCT引入的多模型没有增加计算负担，表现出优异的实时性能。	The multi-model introduced by MMCT does not increase the computational burden and shows an excellent real-time performance.
21503	实验结果表明，MMCT算法能够很好地适应光照、遮挡、复杂背景及平面旋转的情况。	The experimental results indicate that the MMCT algorithm can well adapt to illumination, occlusion, background clutter and plane-rotation.
21504	针对近场源的定位及阵列幅相误差校正问题，该文提出一种基于均匀对称阵列利用辅助阵元矢量重构解耦合的幅相误差校正方法。	In order to solve the problem of near-field source localization and array gain-phase error calibration, a method of gain-phase error calibration is proposed based on uniform array symmetry.