基于泛函网络求解随机优化问题的EM算法

研究了一类带有随机变量的不确定优化问题。为了解决这类随机优化问题,首先用随机仿真为泛函网络产生训练样本,用泛函网络逼近随机函数的均值,将随机函数的均值转为不含随机变量的确定性函数,然后用类电磁算法求解确定性函数的最优解。最后,给出一些数值例子验证了所提算法的有效性。     

基于随机时变图的时间确定性网络路由算法

针对天地一体化网络环境中网络时变性和业务时延确定性保障之间的矛盾,构建了随机时变图模型,并基于该模型提出了时间确定性网络路由算法.首先,将空间信息网络最大概率时延保障路由计算问题建模为非线性规划问题.为解决该问题,提出了随机时变图模型,联合表征了由业务随机性导致的链路、存储与时间资源的随机特征,并且表征了存储与链路资源...     

基于K均值聚类的拓扑生成算法

针对目前网络仿真常用的Waxman随机网络拓扑模型存在的网络节点疏密不当、度数难以控制等问题,提出了一种基于K均值聚类的随机图拓扑生成算法KRT和一种基于K均值聚类的层次结构拓扑生成算法KHT.仿真实验表明使用基于K均值聚类的随机网络和层次结构拓扑生成器得到的网络拓扑图避免了两个节点间距离过近的情况发生,节点分布均匀且疏密得当,边的分布也比较均衡.     

一类网络环境下的离散线性系统的可靠性滤波器设计研究

 本文对一类网络环境下的离散线性系统进行了可靠性滤波器设计,其中用一组随机变量来表示传感器的概率性失真,并综合考虑网络环境的时滞、错序、丢包等非理想服务质量,建立了包含传感器随机失真的系统模型;通过使用李亚普诺夫泛函稳定性理论和线性矩阵不等式技术给出了可靠性滤波器设计算法存在可行解的充分性条件,最后通过数值算例验证本文给出方法的有效性.     

基于多核PC的人工蜂群并行算法的研究与实现

针对人工蜂群算法搜索时间长、收敛速度缓慢、搜索后期极易陷入局部最优等问题,提出了一种人工蜂群并行算法(PRP-ABC).首先引入随机摄动因子和全局最优解两个策略得到串行式RP-ABC算法;然后应用OpenMP并行技术,采用主从式调度方式对串行算法并行改写;最后在多核PC上将三种算法在复杂函数优化问题上测试比较.结果表明,该算法有效提高了收敛速度和优化性能,尤其适用于高维复杂函数的优化问题.     

采用全局相似性测量的彩色图像分割

本文提出一种新的采用全局相似性测量的彩色图像分割算法。该算法将图像分割问题表述为求解能量泛函最小化的问题。利用Bhattacharyya距离测量前景和背景之间的概率分布函数的全局相似性,并将Bhattacharyya系数作为最终的能量泛函。由于高阶能量项的引入,该能量的最小化通常是一个NP难题,为了能够有效的优化该能量泛函,本文提出一个辅助上界函数并且利用graph cuts对该函数进行优化求解。该辅助函数在优化的过程中能够保证能量递减。该算法能够应用于多种分割问题,包括交互式分割、显著性分割等。实验结果表明,算法具有全局分割的特点,能够对彩色图像进行较准确的分割。      

The Analysis of Continuous Particle Swarm Optimization Algorithm's Mean Square Convergence

粒子群优化算法是基于生物群体内个体间的合作与竞争等复杂行为产生的群体智能优化算法,已有的理论分析多在确定性的情况下进行算法收敛性分析.本文基于随机系统的矩方程法分析了连续型粒子群优化算法的均方收敛性,并给出了能够保证算法均方收敛域,最后通过仿真实验分析验证了相关结论.     

连续型粒子群优化算法的均方收敛性分析

粒子群优化算法是基于生物群体内个体间的合作与竞争等复杂行为产生的群体智能优化算法,已有的理论分析多在确定性的情况下进行算法收敛性分析.本文基于随机系统的矩方程法分析了连续型粒子群优化算法的均方收敛性,并给出了能够保证算法均方收敛域,最后通过仿真实验分析验证了相关结论.     

MIMO阵列恒定包络波形设计

提出了MIMO阵列系统利用白高斯随机过程设计恒定包络波形算法,实现给定发射波形的协方差矩阵.该算法首先对白高斯随机过程去白化得到高斯随机变量,建立恒定包络波形相关矩阵与高斯随机变量相关矩阵之间的关系,再采用无记忆性非线性投影函数把高斯随机变量投影到恒定包络随机变量,从而解出恒定包络波形.与现有的阵列系统波形设计算法相比...     

可重构智能表面辅助的非正交多址接入网络鲁棒能量效率资源分配算法

为提高非正交多址接入(NOMA)网络的鲁棒性和系统能效(EE),考虑了不完美信道状态信息,该文提出一种可重构智能表面(RIS)辅助的NOMA网络鲁棒能效最大资源分配算法。考虑用户信干噪比(SINR)中断概率约束、基站的最大发射功率约束以及连续相移约束,建立了一个非线性的能效最大化资源分配模型。用Dinkelbach方法将分式形式的目标函数转换为线性的参数相减的形式,利用S-procedure方法将含有信道不确定性的SINR中断概率约束转换成确定性形式,利用交替优化算法将多变量耦合的非凸优化问题分解成多个凸优化子问题,最后用CVX对分解出的子问题进行求解。仿真结果表明,在EE方面,所提算法比无可重构智能表面(RIS)算法提高了7.4%。在SINR中断概率方面,所提算法比非鲁棒算法降低了85.5%。     

具有二维状态转移结构的随机逻辑及其在神经网络中的应用

随机计算是一种特殊的基于概率数据码流的数学计算方法,其优点在于可以采用非常简单的数字逻辑完成复杂数学运算,从而大幅降低硬件实现成本。该文首先讨论了随机计算的基本原理和主要运算逻辑,论述了传统线性状态机的不足,并分析了一种2维状态转移拓扑结构,推导了通过2维有限状态机实现高斯函数的方法。在此基础上,提出一种随机径向基函数神经网络模型,其硬件实现成本非常低,而性能与传统神经网络相当。两类模式识别实验结果显示,所提出的随机径向基函数神经网络的输出值均方误差与相应结构传统神经网络的差别小于1.3%。FPGA实验结果显示,数据宽度为12位时,随机中间神经元的电路面积仅为传统插值查表结构的1.2%、坐标旋转数字计算方法(CORDIC)的2%。通过改变输入码流长度,该神经网络可以在处理速度、功耗和准确性之间作出平衡,具有应用灵活性,适用于对成本、功耗要求较高的应用如嵌入式、便携式、穿戴式设备。     

Study on distributed and dynamic resource management for delay-sensitive sensor network

The delay-aware dynamic resource management problem was investigated in sensor network,with a focus on resource allocation among the sensors and power control along the time.By taking account of average delay requirements and power constraints,the considered problem was formulated into a stochastic optimization problem.Inspired by Lyapunov optimization theory,the intractable stochastic optimization problem was transformed into a tractable deterministic optimization problem,which was a mixed-integer resource management problem.By exploiting the specific problem structure,the mixed-integer resource management problem was equivalently transformed into a single variable problem,and the cooperative distributed method was present to effectively solve it with guaranteed global optimality.Finally,a dynamic resource management algorithm was proposed to solve the original stochastic optimization problem.Simulation results show the performance of the proposed dynamic algorithm and reveal that there exists a fundamental tradeoff between delay requirements and power consumption.     

基于随机演化博弈模型的网络防御策略选取方法

针对攻防博弈系统中存在攻防策略集和系统运行环境改变等各类随机干扰因素的问题,传统确定性博弈模型无法准确描述攻防博弈过程.利用非线性Itó随机微分方程构建随机演化博弈模型,用于分析攻防随机动态演化过程.通过求解,并根据随机微分方程稳定性判别定理对攻防双方的策略选取状态进行稳定性分析,设计出基于随机攻防演化博弈模型的安全防御策略选取算法.最后,通过仿真验证了不同强度的随机干扰对攻防决策演化速率的影响,且干扰强度越大,防御者更倾向于选择强防御策略,攻击者更倾向于选择强攻击策略.本文模型和方法能够用于网络攻击行为预测和安全防御决策.     

基于空间分布熵的随机辐射源布局优化

针对微波凝视关联成像中,随机辐射源布局优化以随机辐射场矩阵的有效秩最大化为准则时面临目标函数计算复杂、效率太低的问题,提出了一种基于空间分布熵的布局优化方法。首先,构建了一种以空间分布熵来定量表征随机辐射源布局随机性的方法,并通过仿真分析验证了随机辐射源的空间分布熵与随机辐射场矩阵的有效秩之间的总体正相关性;然后,采用遗传算法以空间分布熵最大化为准则对随机辐射源布局进行了优化;最后,通过成像仿真验证了随机辐射源布局优化能有效提高微波凝视关联成像性能。     

Iterative algorithms for state estimation of jump Markov linearsystems

Jump Markov linear systems (JMLSs) are linear systems whose parameters evolve with time according to a finite state Markov chain. Given a set of observations, our aim is to estimate the states of the finite state Markov chain and the continuous (in space) states of the linear system. In this paper, we present original deterministic and stochastic iterative algorithms for optimal state estimation of JMLSs. The first stochastic algorithm yields minimum mean square error (MMSE) estimates of the finite state space Markov chain and of the continuous state of the JMLS. A deterministic and a stochastic algorithm are given to obtain the marginal maximum a posteriori (MMAP) sequence estimate of the finite state Markov chain. Finally, a deterministic and a stochastic algorithm are derived to obtain the MMAP sequence estimate of the continuous state of the JMLS. Computer simulations are carried out to evaluate the performance of the proposed algorithms. The problem of deconvolution of Bernoulli-Gaussian (BG) processes and the problem of tracking a maneuvering target are addressed     

Research of stochastic weight strategy for extended particle swarm optimizer

To improve the performance of extended particle swarm optimizer, a novel means of stochastic weight deployment is proposed for the iterative equation of velocity updation. In this scheme, one of the weights is specified to a random number within the range of [0, 1] and the other two remain constant configurations. The simulations show that this weight strategy outperforms the previous deterministic approach with respect to success rate and convergence speed. The experiments also reveal that if the weight for global best neighbor is specified to a stochastic number, extended particle swarm optimizer achieves high and robust performance on the given multi-modal function.     

A New Design Concept for High-Performance Fading Channel Simulators Using Set Partitioning

In this paper, we introduce a new technique for the design of high-performance Rayleigh fading channel simulators. The proposed design method uses set partitioning – a technique, which plays a key role in the design of trellis-coded modulation schemes. We show how set partitioning can be used to design multiple uncorrelated fading waveforms enabling the simulation of Rayleigh fading channels. For the important case of isotropic scattering, we show that the sample average of the generated waveforms results in a deterministic process, the autocorrelation function (ACF) of which tends to the zeroth-order Bessel function of the first kind as the number of sample functions increases. The proposed procedure is completely deterministic. The comparison with a stochastic procedure using Monte Carlo techniques will be made. A study of the performance shows clearly that the new technique using set partitioning outperforms by far existing Monte Carlo methods.     

Near‐optimal online routing in opportunistic networks

In opportunistic networks, nodes communicate intermittently based on store‐carry‐forward paradigm while exploiting node mobility. The challenge is to determine the ideal nodes to deliver the messages since there is no end‐to‐end connectivity. The nodes might make this decision based on the data sensed from the network. This technique is not ideal in scenarios where the speed of changes in the network topology is greater than the speed at which the nodes can collect info on the network, which might, in turn, be restricted due to usage constraints and uncertainty of knowledge about future contacts. To tackle the problems raised by the non‐deterministic environments, in this paper, a stochastic optimization model and corresponding algorithm are developed to find the optimal routes by considering the short and long‐term impact of choices, ie, the next hop. Herein, we first propose a stochastic model to resolve the routing problem by identifying the shortest path. In the second step, we show that the optimal solution of the proposed model can be determined in polynomial time. An online algorithm is then proposed and analyzed. The algorithm is O( lognρ ) competitive considering the number of nodes and their associated energy. This model can take advantage of the unexpected meets to make the routing more elastic in a short time of contact and with less of a burden on the buffer. The simulation results, against the prominent algorithms, demonstrate significant improvement of the proposed approach in delivery and average delay ratio.