ID 原文 译文
20435 在充分考虑信道特性的基础上，通过最大化用户接收信号能量和迫零思想分别设计有用信号的模拟和数字波束成形矩阵； Based on the channel characteristics, the analog and digital beamformingmatrices of useful signals are designed by maximizing the user’s received signal energy and Zero-Forcing (ZF).
20436 然后，通过SVD分解设计人工噪声的基带数字预编码矩阵，将人工噪声置于合法用户零空间。 Then, the artificial noise baseband digital precoding matrix is designed by Singular Value Decomposition(SVD), and the artificial noise is placed in null space of the legal users and worsening eavesdropping channel.
20437 仿真结果表明，人工噪声辅助的安全混合波束成形算法有效解决了存在具有多用户译码能力窃听者时系统的安全问题。 Simulation results show that the artificial noise-assisted secure hybrid beamforming algorithm solves effectivelythe security problem of the system when there are multi-user decoding ability eavesdroppers.
20438 灰狼优化算法(GWO)是一种新的基于灰狼捕食行为的元启发式算法，被证明是一种具有高水平的探索和开发能力的算法。 The Grey Wolf Optimizer (GWO) algorithm mimics the leadership hierarchy and hunting mechanismof grey wolves in nature, and it is an algorithm with high level of exploration and exploitation capability.
20439 但是存在开发和探索不平衡的问题，以至于其优化性能并不理想。 This algorithm has good performance in searching for the global optimum, but it suffers from unbalance between exploitation and exploration.
20440 该文将混沌理论引入GWO中，用于平衡GWO的探索和开发，提出一种改进的混沌灰狼优化算法(CGWO)，并应用于多层感知器(MLPs)的训练。 An improved Chaos Grey Wolf Optimizer called CGWO is proposed, for solving complex classification problem.
20441 首先，基于Cubic混沌理论对GWO的位置更新公式进行改进，以增加个体的多样性，增大跳出局部最优的概率和对解空间进行深入的搜索； In the proposed algorithm, Cubic chaos theory is used to modify the position equation of GWO, which strengthens the diversity of individuals in the iterative search process.
20442 其次，设计一种非线性收敛因子，用于协调和平衡CGWO算法在不同迭代进化时期的探索和开发能力； A novel nonlinear convergence factor is designed to replace the linear convergence factor of GWO, so that it can coordinate the balance of exploration and exploitation in the CGWO algorithm.
20443 最后，将CGWO算法作为MLPs的训练器，用于对3个复杂分类问题进行分类实验。 The CGWO algorithm is used as the trainer of the Multi-Layer Perceptrons (MLPs), and 3 complex classification problems are classified.
20444 结果表明：CGWO在分类准确率，避免陷入局部最优，全局收敛速度和鲁棒性方面相较于其他对比算法均具有较好的性能。 The statistical results prove the CGWO algorithm is able to provide very competitive results in terms of avoiding local minima, solution precision, converging speed and robustness.