STRONG CONVERGENCE THEOREMS FOR NONEXPANSIVE MAPPING

This paper introduces a composite iteration scheme for approximating a fixed point of nonexpansive mappings in the framework of uniformly smooth Banach spaces and the reflexive Banach spaces which have a weakly continuous duality map, respectively, we establish the strong convergence of the composite iteration scheme. The results improve and extend those of Kim, Xu, Wittmann and some others.     

A penalty function method for solving ill-posed bilevel programming problem via weighted summation

For ill-posed bilevel programming problem, the optimistic solution is always the best decision for the upper level but it is not always the best choice for both levels if the authors consider the model＇s satisfactory degree in application. To acquire a more satisfying solution than the optimistic one to realize the two levels＇ most profits, this paper considers both levels＇ satisfactory degree and constructs a minimization problem of the two objective functions by weighted summation. Then, using the duality gap of the lower level as the penalty function, the authors transfer these two levels problem to a single one and propose a corresponding algorithm. Finally, the authors give an example to show a more satisfying solution than the optimistic solution can be achieved by this algorithm.     

宽带正交频分复用系统的记忆型预失真器

提出了一种自适应预失真器及其迭代算法,可同时解决宽带OFDM发射机中功率放大器的非线性和记忆效应问题。该预失真器由均衡器和基于查询表(LUT)的无记忆预失真器串联组成,首先通过窄带训练序列,获得无记忆预失真器的参数,抵消功率放大器的非线性,然后通过迭代算法修改均衡器的参数,补偿功率放大器的记忆效应。与以往解决OFDM功率放大器记忆效应的预失真器相比,迭代算法简单,便于实现。仿真结果表明该预失真器可有效校正和抵消宽带OFDM系统中功率放大器的非线性和记忆效应。     

关于整数线性规划代理对偶间隙的注记

将有效不等式的概念应用于整数线性规划的代理对偶问题 ,给出弥合整数线性规划的代理对偶间隙的方法 .数值例子表明所给出的方法在改进定界结果方面是有效的 .     

三维局部多层快速多极子算法

为了进一步加速多层快速多极子算法求解电大尺寸目标电磁散射,提出了一种基于局部耦合技术计算矩阵矢量相乘的多层快速多极子方法。通过在迭代过程中设置与迭代误差相关的最初层,每次迭代仅仅需要考虑局部的耦合区域。该方法在保证合理计算精度的同时大大降低了迭代过程中矩阵矢量相乘的计算复杂度,提高了多层快速多极子方法计算效率。数值结果说明了所提方法的有效性。     

A Superlinearly Convergent Combined PhaseⅠ-PhaseⅡ Subfeasible Method

ＡＳｕｐｅｒｌｉｎｅａｒｌｙＣｏｎｖｅｒｇｅｎｔＣｏｍｂｉｎｅｄＰｈａｓｅⅠ－ＰｈａｓｅⅡＳｕｂｆｅａｓｉｂｌｅＭｅｔｈｏｄＪＩＡＮＪｉｎｂａｏ（ＭａｔｈｅｍａｔｉｃｓａｎｄＩｎｆｏｒｍａｔｉｏｎＳｃｉｅｎｃｅＤｅｐａｒｔｍｅｎｔｏｆＧｕａｎｇｘｉＵ...     

基于改进遗传算法的正交匹配追踪信号重建方法

针对压缩传感现有重建算法的缺陷:重建速度慢,在给定迭代次数的条件下进行重建,缺乏自适应性等,提出了一种改进的遗传算法与正交匹配追踪算法相结合的方法来构造重建矩阵。首先采用改进的遗传算法从测量矩阵的列中以最优染色体的形式选出与当前冗余向量最大程度相关的列,然后从测量矩阵中减去最优染色体部分并反复迭代,直到满足重建精度。实验结果表明,与现有的重建算法相比,在满足相同的重建精度条件下,该方法所需要的重建时间减少了5 s左右,所需要的测量矩阵规模减小了约10%,而且能在待重建信号稀疏度未知时自适应地控制迭代停止时间。     

基于迭代无迹卡尔曼滤波的SLAM算法仿真研究

对迭代无迹卡尔曼滤波算法在SLAM问题中的应用进行仿真研究。通过仿真分析发现,与一般的无迹卡尔曼滤波算法相比,迭代的算法有时无法提高SLAM的精度,继而探讨了SLAM问题中选择采用迭代算法的条件;同时针对迭代算法的观测更新阶段,用阻尼的高斯-牛顿迭代方法改进完全高斯-牛顿迭代方法,从而提出一种改进的基于迭代无迹卡尔曼滤波的SLAM算法。仿真实验对提出的迭代条件进行了验证,仿真结果表明提出的SLAM算法与无迹卡尔曼滤波算法相比,可以进一步提高SLAM问题的估计精度。     

基于蜂群算法的坦克阵地部署与火力分配模型

为了解决坦克分队进攻战斗中的兵力部署和火力协同问题,提出坦克阵地部署模型和坦克火力分配模型,前者解决坦克分队从集结区域到作战区域的兵力分配问题,后者解决坦克接敌后的火力协同问题.针对坦克作战中的对抗特性,建立确定型火力对抗模型,在火力分配模型中体现敌我动态对抗过程.为了求取坦克阵地部署和火力分配最优方案,采取双层迭代策...     

基于修正超指数迭代算法的双模式盲均衡算法仿真研究

收敛速度和剩余均方误差是评价盲均衡算法性能优劣的主要参数之一。超指数迭代盲均衡算法收敛速度快，但是，该算法对高阶QAM信号具有较大的剩余均方误差。针对数字无线电信道的盲均衡问题，提出了一种修正的超指数迭代盲均衡算法，该算法可校正无线电信道引入的载波相位旋转，并具有较快的收敛速度。在此基础上又提出了一种双模式盲均衡算法，该算法在收敛阶段采用修正的超指数迭代算法，之后根据某一切换准则，切换到判决导引算法，可有效减小超指数迭代算法对高阶信号的剩余均方误差。通过仿真证明了本算法的有效性。     

全相位相位差测量中的系统误差及其校正

分析了负频率分量对全相位离散傅里叶变换（all-phase discrete Fourier transform, apDFT）测量相位差的性能的影响,提出了迭代延时-补偿法来抑制负频率分量带来的系统误差,讨论了加窗对迭代延时-补偿法系统误差抑制性能的影响。当采用apDFT算法测量相位差时,负频率分量引起度量级的系统误差。迭代延时-补偿法与apDFT算法的结合,能够在离散傅里叶变换（discrete Fourier transform, DFT）运算点数为1 024时,将最大系统误差在全频段范围内降至0.01°量级,且DFT运算点数越大,抑制效果越好。对原始数据加余弦窗,能够进一步改善迭代延时-补偿法的系统误差抑制性能及容差性。     

一种基于分数采样的混合盲均衡算法仿真研究

在数字通信中,盲均衡是克服多径衰落信道导致的码间干扰的一种有效方法。超指数盲均衡算法的迭代算法收敛速度快,且便于跟踪时变信道。同时由于实际信道往往为非最小相位系统,此时线性均衡器性能不佳。因此针对严重频率衰落和非线性相位失真信道,提出了一种分数采样的混合盲均衡算法,并获得了较快的收敛速度和较小的剩余均方误差。仿真结果证明了该算法的有效性。     

基于时间相关性的梯度追踪多用户检测算法

为降低大规模机器类型通信基站端多用户检测的复杂度, 结合活跃设备在相邻时隙间的相关性和梯度追踪算法提出了相关性辅助的梯度追踪多用户检测(correlation-assisted gradient pursuit multi-user detection, CAGP-MUD)算法, 不仅避免了矩阵求逆的过程, 还减少了除第一时隙的其他时隙的迭代次数。为了进一步降低多用户检测算法的复杂度, 在CAGP-MUD算法框架内引入决策衰弱的思想, 对梯度最大值进行衰弱, 并以此作为阈值, 每次迭代可挑选出多个活跃设备, 以减少迭代次数, 称为相关性辅助的组梯度追踪多用户检测算法。对提出的两种算法进行了复杂度计算。理论分析和仿真实验表明, 和同类算法相比, 这两种算法的计算消耗降低了60%以上。     

Super-resolution processing of passive millimeter-wave images based on adaptive projected Landweber algorithm

Passive millimeter wave （PMMW） images inherently have the problem of poor resolution owing to limited aperture dimension. Thus, efficient post-processing is necessary to achieve resolution improvement. An adaptive projected Landweber （APL） super-resolution algorithm using a spectral correction procedure, which attempts to combine the strong points of all of the projected Landweber （PL） iteration and the adaptive relaxation parameter adjustment and the spectral correction method, is proposed. In the algorithm, the PL iterations are implemented as the main image restoration scheme and a spectral correction method is included in which the calculated spectrum within the passband is replaced by the known low frequency component. Then, the algorithm updates the relaxation parameter adaptively at each iteration. A qualitative evaluation of this algorithm is performed with simulated data as well as actual radiometer image captured by 91.5 GHz mechanically scanned radiometer. From experiments, it is found that the super-resolution algorithm obtains better results and enhances the resolution and has lower mean square error （MSE）. These constraints and adaptive character and spectral correction procedures speed up the convergence of the Landweber algorithm and reduce the ringing effects that are caused by regularizing the image restoration problem.     

一种具有动态最优学习率的BP算法

提出具有动态最优学习率的BP算法，动态最优学习率是通过迭代的方式得到的，这种算法具有运算简单，收敛速度快，精度高特点。仿真结果说明此算法是有效的。     

Super-resolution processing of passive millimeter-wave images based on adaptive projected Landweber algorithm

Passive millimeter wave(PMMW)images inherently have the problem of poor resolution owing to limited aperture dimension.Thus,efficient post-processing is necessary to achieve resolution improvement.An adaptive projected Laadweber(APL)super-resolution algorithm using a spectral correction procedure,which attempts to combine the strong points of all of the projected Landweber(PL)iteration and the adaptive relaxation parameter adjustment and the spectral correction method,is proposed.In the algorithm,the PL iterations are implemented as the main image restoration scheme and a spectral correction method is included in which the calculated spectrum within the passband is replaced by the known low frequency component.Then,the algorithm updates the relaxation parameter adaptively at each iteration.A qualitative evaluation of this algorithm is performed with simulated data as well as actual radiometer image captured by 91.5 GHz mechanically scanned radiometer.From experiments,it is found that the super-resolution algorithm obtains better results and enhances the resolution and has lower mean square error(MSE).These constraints and adaptive character and spectral correction procedures speed up the convergence of the Landweber algorithm and reduce the ringing effects that are caused by regularizing the image restoration problem.     

TOA模式下TLS辅助泰勒级数展开的蜂窝定位新算法

提出了一种到达时间(time of arrival, TOA)模式下总体最小二乘(total least square, TLS)辅助泰勒级数展开的蜂窝定位新算法。该算法针对泰勒级数展开对初始迭代参考点依赖性强的问题,综合考虑观测量误差和观测站位置误差,利用TLS估计初始参考点,然后在估计值处对观测方程组实施泰勒级数展开,并使用加权最小二乘进行多次迭代运算,实现对移动终端的高精度定位。仿真结果表明,该算法在平均迭代次数和定位精度方面具有接近基于真实位置的泰勒级数展开算法的性能,并且在不同的几何精度因子(geometrical dilution of precision, GDOP)下,均具备良好的抗观测量误差和观测站位置误差的特性。     

动态神经网络学习算法中的参数估值

以一种简单的动态ＢＰ网络作为并联模型,运用卡尔曼滤波原理,提出了一种新的神经网络辨识算法．该算法的学习速度是由带时间参数的Ｒｉｃｃａｔｉ方程来确定的,从而大大减少了学习的迭代次数．仿真结果表明此算法是有效可行的     

用于双基地雷达目标定位的全局收敛高斯-牛顿法

考虑了双基地雷达目标定位问题中的非线性最小二乘方程组的迭代解法。用高斯 牛顿迭代法解非线性最小二乘方程组计算量小、收敛快,但所得解的正确性及精度依赖于选取的迭代初值与真值的靠近程度,及方程组的非线性强度。给出了两种变步长全局收敛策略,与高斯-牛顿法相结合可得到对初值不敏感的迭代算法。仿真结果表明,用全局收敛的高斯 牛顿法解最小二乘方程组能得到更准确的解,且迭代次数较少。     

A new <Emphasis Type="Italic">ɛ</Emphasis>-generalized projection method of strongly sub-feasible directions for inequality constrained optimization

In this paper, the nonlinear optimization problems with inequality constraints are discussed. Combining the ideas of the strongly sub-feasible directions method and the ɛ-generalized projection technique, a new algorithm starting with an arbitrary initial iteration point for the discussed problems is presented. At each iteration, the search direction is generated by a new ɛ-generalized projection explicit formula, and the step length is yielded by a new Armijo line search. Under some necessary assumptions, not only the algorithm possesses global and strong convergence, but also the iterative points always get into the feasible set after finite iterations. Finally, some preliminary numerical results are reported.