ID 原文 译文
14315 实验结果表明：新算法在不破坏海杂波混沌特性的前提下,极大地抑制了海杂波。 The experimental results show that:
14316 新算法的检测性能稳定,低信杂比下的检测性能显著优于传统算法,证明新算法能快速实现对漂浮小目标的有效检测。 1) The new algorithm greatly suppresses the sea clutter without destroyingthe chaotic characteristics of the sea clutter;
14317 在同等条件下,与传统混沌预测算法相比,训练时间短、预测精度高。 2) Under the same conditions the training time is shorter andthe prediction accuracy is higher compared with that of the traditional chaos prediction algorithms;
14318 高光谱图像在国防军事和民用领域都有大量的应用,特别是异常目标检测不需要任何先验信息,使其成为高光谱图像处理和信息提取的关键技术和研究热点之一。 Hyperspectral imagery has a lot of applications in the national defense and civil fields． Especially, the anomaly target detection does not need any prior information and thus has become one of the key technologiesand research hotspots in hyperspectral image processing and information extraction．
14319 通过系统的梳理、分析和研究,对现有的异常目标检测算法进行了深入的归纳和总结,并对高光谱图像异常目标检测涉及到的关键问题、未来的技术发展方向(如稀疏表示、张量分解和深度学习等)以及算法存在的问题进行了分析评价,提出了一些具有创新性的观点并预测了未来的研究趋势。 Through systematic researchand analysis this paper summarizes the existing anomaly target detection algorithms in detail analyzes andevaluates the key problems involved in anomaly target detection gives the future development direction ofthe technology such as sparse representation，tensor decomposition and deep learning etc． and presents theexisting problems of the algorithms． Some innovative ideas and future research trends are also proposed．
14320 全空域球面相控阵测控系统是一类新的测控系统。 Spherical phased array space telemetry，tracking and command( TT＆C) system in hemisphericalcoverage is a new type of TT＆C system．
14321 在介绍该系统角跟踪技术特点的基础上，概述了角跟踪系统设计方法以及单脉冲角跟踪、圆锥扫描跟踪、变口径跟踪、多目标跟踪和过顶跟踪等技术，可供该领域相关人员参考。 This paper introduces the characteristics of angle tracking of this system，and outlines the design methods of angle tracking system，as well as monopulse tracking，cone scantracking，variable aperture tracking，multi-target tracking and passing zenith tracking，in hope fo providing reference for those engaged in this field．
14322 针对战机型号快速准确识别问题，提出一种利用梯度提升树的战机型号快速识别方法。 To fast recognize aircraft types，a method based on gradient boosting decision tree is proposed．
14323 以多传感器融合的战机航迹解译信息为数据基础，通过分析航迹数据特征，构建战机航迹数据特征工程，利用 boosting 集成学习思想，训练基于梯度提升决策树的战机型号分类器，可准确识别每个航迹点对应的战机型号。 Specifically，the aircrafts’traces，interpreted by the results from multi-sensors fusion，are used as the rawdata source． Then，after data are cleaned and labelled，multiple elementary features are designed by analyzing the data characteristics for seeking an appropriate expression of statistic distribution of the data． Finally，a classifier based on gradient boosting decision tree is designed，which has the capability to recognizeaircraft types at each trace point time instance．
14324 实测数据实验结果表明，所提模型识别准确率达到 95． 76% ，较卷积神经网络( Convolutional Neural Network，CNN) 方法识别准确率 90． 32% 提高了 5． 44% ; 所提模型平均单点识别计算耗时为 408． 1 μs，较 CNN 方法耗时 5 385． 5 μs 快 13． 19 倍，证明了所提算法能够快速有效地辨识战机型号，满足准确性和实时性需求。 The real-data experimental results illustrate that the trainedmodel using the proposed method achieves the accuracy of 95． 76% ，which is 5． 44% higher than that ofthe convolutional neural network( CNN) model，and the average calculation time cost of a single trace pointis tested as 408． 1 μs，which is 13． 19 times faster than that of the CNN model，5385． 5μs，proving the goodperformance of the proposed method both on the classification accuracy and the real time．