基于神经网络的遥感影像超高分辨率目标识别

现有遥感图像的许多分类方法大都忽略了混合像元存在的事实,通过理解遥感影像像元点目标的空间分布特性,提出基于Hopfield神经网络的遥感图像超分辨率目标识别算法。在Hopfield神经网络模型下,利用模糊分类技术进行模糊分类,然后用分类结果约束Hopfield神经网络的方法获取超高分辨率的遥感图像,能够提高遥感图像的目标分辨率,使其目标特征信息更清晰。     

基于贝叶斯网络的编队对地攻击损伤评估研究

随着武器的高科技化、战场环境的复杂化、战斗节奏的加快,战斗损伤评估系统在现代战争中占有越来越重要的地位。针对战场战斗损伤评估信息的多样性、不确定性和模糊性,基于贝叶斯网络易于进行不确定性推理的优点,提出应用贝叶斯网络对对地攻击效果进行分析评价,建立了编队对地攻击损伤评估的贝叶斯网络模型,给出了基于贝叶斯网络的损伤评估的推理决策方法,并且对该方法进行了仿真分析。仿真实例表明,基于贝叶斯网络的损伤评估模型能够提高损伤评估的准确度,而且推理简单,易于实现。     

含作业到达时间的同类机调度问题启发式算法

研究了目标函数是最小化完成时间和的同类机调度问题,其中作业到达时间可能不同.此问题被证明是强NP-hard问题.由于同类机调度是一种重要的平行机调度问题,而最小完成时间和目标是最常见的正则目标之一,因此完成时间和的同类机调度问题在相关研究领域具有非常重要的地位.为此问题建立数学模型,通过对单机和同型机的相应问题研究成果的推广,提出6个启发式算法,给出算例及其计算结果,并通过实验对算法的性能及算法适应的情形进行了分析.     

Multi-agent cooperative intrusion response in mobile adhoc networks

The nature of adhoc networks makes them vulnerable to security attacks. Many security technologies such as intrusion prevention and intrusion detection are passive in response to intrusions in that their countermeasures are only to protect the networks, and there is no automated network-wide counteraction against detected intrusions. the architecture of cooperation intrusion response based multi-agent is propose. The architecture is composed of mobile agents. Monitor agent resides on every node and monitors its neighbor nodes. Decision agent collects information from monitor nodes and detects an intrusion by security policies. When an intruder is found in the architecture, the block agents will get to the neighbor nodes of the intruder and form the mobile firewall to isolate the intruder. In the end, we evaluate it by simulation.     

TDMA体制下的移动自组织网时隙同步方法

在TDMA体制下的移动网状自组织网络中,为了解决网络时隙同步问题,提出了一种不依赖GPS授时的网络时隙互同步算法。各节点通过计算相邻节点的时隙偏差,通过加权计算并调整本节点的时隙位置,使网内各节点的时隙起始都调整到同一位置上,达到时隙的互同步。通过仿真和实验,分析并验证了移动自组织网络时隙互同步的收敛性能和抗干扰性能。     

Stability analysis of BAM neural networks with time-varying delays

Some new criteria for the global asymptotic stability of the equilibrium point for the bi-directional associative memory neural networks with time varying delays are presented. The obtained results present the structure of linear matrix inequality which can be solved efficiently. The comparison with some previously reported results in the literature demonstrates that the results in this paper provide one more set of criteria for determining the stability of the bi-directional associative memory neural networks with delays.     

Dynamic spreading behavior of homogeneous and heterogeneous networks

The detailed investigation of the dynamic epidemic spreading on homogeneous and heterogeneous networks was carried out. After the analysis of the basic epidemic models, the susceptible-infected-susceptible (SIS) model on homogenous and heterogeneous networks is established, and the dynamical evolution of the density of the infected individuals in these two different kinds of networks is analyzed theoretically. It indicates that heterogeneous networks are easier to propagate for the epidemics and the leading spreading behavior is dictated by the exponential increasing in the initial outbreaks. Large-scale simulations display that the infection is much faster on heterogeneous networks than that on homogeneous ones. It means that the network topology can have a significant effect on the epidemics taking place on complex networks. Some containment strategies of epidemic outbreaks are presented according to the theoretical analyses and numerical simulations.     

Hierarchical Neural Networks Method for Fault Diagnosis of Large-Scale Analog Circuits

A novel hierarchical neural networks (HNNs) method for fault diagnosis of large-scale circuits is proposed. The presented techniques using neural networks(NNs) approaches require a large amount of computation for simulating various faulty component possibilities. For large scale circuits, the number of possible faults, and hence the simulations, grow rapidly and become tedious and sometimes even impractical. Some NNs are distributed to the torn sub-blocks according to the proposed torn principles of large scale circuits. And the NNs are trained in batches by different patterns in the light of the presented rules of various patterns when the DC, AC and transient responses of the circuit are available. The method is characterized by decreasing the over-lapped feasible domains of responses of circuits with tolerance and leads to better performance and higher correct classification. The methodology is illustrated by means of diagnosis examples.     

双向联想记忆神经网络的全局指数稳定性

在研究双向联想记忆神经网络时,通常都假设输出响应函数是光滑的增函数,但实际应用中遇到的大多数函数都是非光滑函数。因此,本文将双向联想记忆神经网络的输出响应函数连续可微的假设削弱为满足Lipschitz条件,通过引入Lyapunov函数,利用不等式的方法,证明了双向联想记忆神经网络全局指数稳定性的一个定理。     

时滞细胞神经网络的指数稳定性

研究了时滞细胞神经网络(DCNNs)平衡点的全局渐近稳定性,去掉了有关文献中关于激活函数的有界性、单调性和可微性的条件,运用拓扑度理论和M-矩阵理论给出了更弱的判定平衡点的存在唯一性及全局指数稳定性的条件.