ID 原文 译文
18615 针对基于蓝牙信号的复杂室内环境定位问题，该文提出基于低成本阵列天线的室内定位方法， In order to solve the location problem in complex indoor environment based on Bluetooth signal, an indoor localization algorithm based on low-cost array antenna is developed.
18616 该方法利用单通道轮采极化敏感阵列天线对蓝牙信号进行采样，然后结合暗室测量获得的准确阵列流形和极化快收敛稀疏贝叶斯学习(P-FCSBL)算法实现信源的角度估计，最后通过角度实现定位。 The algorithm utilizes single-channel usingswitch-antenna polarization sensitive array to sample Bluetooth signal, then combines the accurate arraymanifold measured in dark room and the algorithm of Polarized Fast Converging Sparse Bayesian Learning (P-FCSBL) to estimate the source’s angle, and finally gets the target location by angle.
18617 该方法充分利用极化信息和角度信息来实现目标和多径信号的分离，同时对单信源的同时采样保证了估计的稳定性。 This algorithm makes fulluse of polarization information and angle information to separate target and multipath signal, and simultaneoussampling of one source ensures estimation stability.
18618 最后通过实测数据处理验证了该方法的有效性。 Finally, the effectiveness of the method is verified by thereal data.
18619 欺骗式干扰通过发射与真实卫星信号相似的信号误导接收机产生错误的定位结果，具有极大的危害。 Spoofing misleads the receiver to generate the wrong position information by trans-mitting signals similar to authentic satellite signals, which has great harm.
18620 该文针对转发式欺骗干扰，提出一种基于信号重构的单天线欺骗干扰抑制方法。 In this paper, a single-antenna spoofing mitigationalgorithm based on signal reconstruction is proposed for meaconing.
18621 该方法首先通过参数估计方法估计出欺骗信号载波频率和码相位，然后构建欺骗信号子空间正交投影矩阵以抑制干扰。 Firstly, the carrier frequency and codephase of spoofing signal are obtained by parameter estimation method, and then the orthogonal projectionmatrix of spoofing signal subspace is constructed to suppress spoofing.
18622 仿真实验结果表明该方法对欺骗干扰具有良好的抑制效果，能够保障接收机在干扰环境中实现有效定位，并具有较低的运算复杂度。 The simulation results show that thealgorithm has a good suppression effect on spoofing and ensure the receiver can locate effectively in theinterference environment, and the algorithm also has lower computational complexity.
18623 深度学习在人工智能领域已经取得了非常优秀的成就，在有监督识别任务中，使用深度学习算法训练海量的带标签数据，可以达到前所未有的识别精确度。 Deep learning has shown excellent performance in the field of artificial intelligence. In the supervised identification task, deep learning algorithms can achieve unprecedented recognition accuracy by training massive tagged data.
18624 但是，由于对海量数据的标注工作成本昂贵，对罕见类别获取海量数据难度较大，所以如何识别在训练过程中少见或从未见过的未知类仍然是一个严峻的问题。 However, owing to the high cost of labeling massive data and the difficulty of obtainingmassive data of rare categories, it is still a serious problem how to identify unknown class that is rarely or neverseen during training.