ID 原文 译文
58198 提出了一种基于主成分分析的图像哈希算法. A novel image Hashing based on principal component analysis ( PCA) was proposed.
58199 采用主成分分析对样本进行降维，取位于变换矩阵顶端最具有识别信息的少量特征向量构造投影矩阵，再对降维后样本进行局部保持映射，同时，对主成分分析投影矩阵进行随机旋转，形成多个小投影矩阵，采用矩阵拼接方法将小投影矩阵合并构造编码投影矩阵; PCAwas introduced to reduce dimension of samples，and the projection matrix was achieved by choosing several eigenvectors which have higher recognition ability. Based on which，the reduced-sample was mappedwith locality preserving projection ( LPP) . Meanwhile，the projection matrix of principal component analysis was randomly rotated to form a series of transformational matrixes. The matrix stitching was adoptedto construct the final code projection matrix.
58200 最后，将训练样本投影到编码投影矩阵，得到降维样本，并对其进行哈希编码，得到最终的二进制编码. Finally，the original samples were projected into the codeprojection matrix to get a reduced dimensional sample，and the Hashing code was used to achieve the final binary encoding.
58201 实验结果证明，同其他经典算法相比，该算法具有较好的稳定性，可降低内存消耗，并提高效率. Experiments show that the proposed method has better stability，lower memory consumption and higher efficiency compared with other traditional methods.
58202 第 5 代移动通信系统( 5G) 子带滤波正交频分复用技术( F-OFDM) 存在较高峰均功率比( PAPＲ) 问题，传统选择性映射算法候选序列数量少，对此，提出量子混沌扩展序列算法，以解决 5G F-OFDM 系统 PAPＲ 较高的问题. High peak to average power ratio ( PAPＲ) is a main problem of the fifth generation of mobilecommunications system( 5G) filtered- orthogonal frequency division multiplexing ( F-OFDM) systems. Aiming at the shortcomings of traditional selective mapping algorithm，such as limited number of candidate sequences，the quantum chaotic extended sequence algorithm was proposed to solve the high PAPＲproblem of 5G F-OFDM systems.
58203 采用分割方法将原始信号分割为实部信号和虚部信号，用量子 Logistic 混沌映射分别与实部信号和虚部信号进行点乘，实部候选序列与虚部候选序列线性组合后再计算 PAPＲ，选择最小 PAPＲ 进行传输. The original signal was divided into real part signal and imaginary partsignal by segmentation method，which were respectively multiplied the quantum logistic chaotic map. ThePAPＲ was calculated by linear superposition of real sequences and the imaginary part candidate，and theminimum PAPＲ was selected for transmission.
58204 仿真结果表明，提出的算法降低了系统的 PAPＲ，扩展了候选序列数量，降低了计算复杂度. The simulation results show that the proposed algorithmreduces the PAPＲ of 5G F-OFDM system，increases the number of candidate signals and reduces thecomputational complexity. The proposed scheme has a broad application prospect in 5G multicarrier modulation technology.
58205 针对通信资源调度场景下的多智能体强化学习( MAＲL) 问题，提出了对称 MAＲL 问题以及三类对称性的定义和条件，并定义了策略融合和策略误差; Considering multi-agent reinforcement learning ( MAＲL) theory in communication resourcescheduling scenario，the symmetrical MAＲL problem was proposed with definitions for three types of symmetry properties and analysis of policy estimation error.
58206 针对强对称 MAＲL 问题，定义了三类评价指标，并对策略估计误差进行分析，提出了强对称 MAＲL 问题的策略误差定理及推论. The policy estimation error theorem for strongsymmetrical MAＲL was presented.
58207 针对无线通信的接入控制问题建立了 MAＲL 问题，仿真结果验证了强对称 MAＲL 问题策略估计误差的特性. Simulation results based on the admission control problem in wirelesssystem were modeled by MAＲL，which testify the characteristics of policy estimation error for strong symmetrical MAＲL problems.