ID	原文	译文
4683	仿真实验表明，所提算法相对于传统调制识别算法以及目前基于波形和星座图的深度学习识别算法识别效果更好，当信噪比为 5 dB 时，识别性能可达 95%。	Finally, the signal modulation recognition task was completed.The simulation results show that compared with the traditional algorithms and deep learning algorithms, the proposedmethod has a better anti-noise performance, and the overall recognition rate of this algorithm can reach 95% when thesignal-to-noise ratio is 5 dB.
4684	针对次子空间信息准则函数缺乏的问题，通过对 Rayleigh 商函数添加惩罚项提出了新型的准则函数。	Aiming at the lack of information criterion functions of sub subspace, a novel criterion function was proposed byadding a penalty term to the Rayleigh quotient.
4685	平稳点分析表明，当且仅当神经网络权矩阵收敛到次子空间的一组基时，准则函数达到全局极大值。	Through analyzing the properties of all the stable points, it was proven that the criterion function exhibited the global maximum attained if and only if the weight matrices span the minor subspace.
4686	采用梯度上升法推导出一个新型的次子空间跟踪算法，并分析了算法的全局收敛性。	A minor subspace tracking algorithm was derived by gradient ascending method and its global convergence analysis was also ac-complished.
4687	仿真实验和实例应用验证了准则函数和导出算法的正确性。	Numerical simulations and real application verifies the correctness of the criterion function and derived algorithm.
4688	为应对运营商云数据中心多业务差异化流量管理要求，提升网络性能和业务体验，构建符合运营商云数据中心运营要求的多业务差异化流量管理模型（MSD），针对 MSD 模型改进斐波那契树优化（FTO）算法，提出运营商 SDN 云数据中心流量管理的 MSD-FTO 策略。	In order to cope with the traffic management for multi-service differentiated in cloud data centers, improvingnetwork performance and service experience, the multi-service differentiated (MSD) traffic management model was de-signed that can suit operational requirements in cloud data center. Fibonacci tree optimization (FTO) algorithm was im-proved according to the MSD model. MSD-FTO traffic management strategy was proposed in SDN cloud data center.Simulation results show that the strategy takes advantage of FTO global optimization ability and multi-modal adaptiveperformance.
4689	实验结果表明，该策略具备良好的全局优化能力和多模自适应特性，通过算法全局局部交替迭代寻优得到多个符合条件的差异化流量管理方案，可解决运营商云数据中心多业务差异化流量管理问题，有效提升云数据中心的网络性能和业务体验。	Through the global local alternating optimization of the algorithm, differentiation traffic managementschemes are obtained as needed, the problem of multi-services differentiated traffic management is solved in operatorcloud data center that improve network performance and service experience in cloud data center effectively.
4690	针对目前的频谱资源使用效率低的问题，提出了一种新的基于特征值的频谱感知融合算法，从而更好地实现动态频谱共享。	Aiming at the problem of inefficient use of spectrum resources, a fusion spectrum sensing algorithm based oneigenvalues was proposed to effectively achieve dynamic spectrum sharing.
4691	所提算法利用样本协方差矩阵的最大特征值、迹和所有特征值的几何均值构造了检测统计量。	The test statistics were constructed by em-ploying the maximum eigenvalue, the trace and the geometric mean of all eigenvalues of the sample covariance matrix.
4692	通过随机矩阵理论分析了所提算法的检测概率及虚警概率，并得到了理论门限的解析表示。	The detection probability and false alarm probability of the proposed method were analyzed using the random matrix theory, and the analytical representation of the theoretical threshold was obtained.