自适应脉冲耦合神经网络在图像处理中应用

尽管Johnson 提出的PCNN模型具有强大的图像处理功能,以时间序列进行特征提取时具有旋转、尺度、平移、扭曲不变性,可实践中发现依然存在着不足,特别对图像亮度、对比度比较敏感.添加了误差反向传播(Error Back Propagation, EBP)学习准则的自适应脉冲耦合神经网络模型能自适应设定模型参数,是脉冲耦合神经网络模型研究的主要内容.特别地,应用这种自适应模型进行特征提取时,能弥补原来PCNN模型对亮度、对比度敏感的缺陷,而且具有一定的泛化能力,有效克服了亮度、对比度对图像识别精度的影响.     

Interaction model of artificial fish in virtual environment

Conventional artificial fish has some shortages on the interaction with environment, other fish, and the animator. This article proposes a multi-tier interaction control model of artificial fish, realizes the interaction model through integration of virtual reality technology and Markov sequence, and provides a virtual marine world to describe the interaction between artificial fish and the virtual environment and the interaction between the artificial fish and the animator. Simulation results show that the interaction model owns not only the basic characteristics of virtual biology, but also has high trueness interaction function.     

基于MCMC模拟的相关系数平稳序列模型及其应用

提出了基于MCMC方法来估计相关系数平稳序列模型的参数;给出基于贝叶斯分布的相关系数平稳序列模型参数的算法;在无信息先验分布下,模拟证明了用此方法估计相关系数平稳序列模型参数的优良效果。最后对实际的广西电网-月负荷数据,分别用基于相关系数平稳序列模型的MCMC方法和极大似然估计法以及基于经典的ARMA模型建模,结果表明采用MCMC方法得到的模型给出的预测是最好的。     

Analysis for MIMO correlated frequency-selective channel in the presence of interference

The space time spreading, superimposed training sequences, and space-time coding are used to present a multiple input and multiple output （MIMO） systems model, and a closed-form of average error probability upper bound expression for MIMO correlated frequency-selective channel in the presence of interference （co-channel interference and jamming signals） is derived. Moreover, the correlation at both ends of the wireless link that can be incorporated equivalently into correlation at the transmit end is also derived, which is significant to analyze space-time link algorithm of MIMO systems.     

灰色T型关联度的改进

通过对现有灰色关联度及T型关联度模型的分析,提出了灰色T型关联度的改进模型,改进后的关联度模型能够反映序列的正、负相关关系,并且具有对称性、唯一性、可比性和无量纲化后的保序性.通过实例表明了改进的灰色T型关联度能够更真实地反映序列曲线的关联程度,所得关联分析结果较为客观可靠,并且易于在计算机上实现.     

基于BDD的多态系统概率安全评估方法研究

由于传统的概率安全评估方法难以处理多态系统,本文通过一个煤气泄漏多态系统实例提出了一种基于BDD的多态系统概率安全评估方法.首先将多态事件树中的事故序列用多态布尔表达式进行描述,进而将多态布尔表达式转化为BDD,给出了一种基于不交化思想的BDD定量算法.在此基础上,提出了实用的基于BDD的多态系统概率安全评估步骤,并通过实例说明了BDD定量算法的正确性.     

一类非线性切换系统观测器设计的新方法

针对一类切换规则为时间依赖型的Lipschitz非线性切换系统,采用驻留时间方法研究了状态观测器设计问题.该切换系统同时含有可观测子系统与不可观测子系统,通过构造合适的Lyapunov函数,并利用矩阵不等式技术得到了保证状态观测器状态估计误差收敛的条件.并给出了观测器设计步骤.进一步,通过矩阵变换将观测器增益求解转化为LMI形式.最后给出了仿真算例说明了该设计方法的有效性.     

Closed circle DNA algorithm of change positive-weighted Hamilton circuit problem

Chain length of closed circle DNA is equal. The same closed circle DNA's position corresponds to different recognition sequence, and the same recognition sequence corresponds to different foreign DNA segment, so closed circle DNA computing model is generalized. For change positive-weighted Hamilton circuit problem, closed circle DNA algorithm is put forward. First, three groups of DNA encoding are encoded for all arcs, and deck groups are designed for all vertices. All possible solutions axe composed. Then, the feasible solutions axe filtered out by using group detect experiment, and the optimization solutions are obtained by using group insert experiment and electrophoresis experiment. Finally, all optimization solutions are found by using detect experiment. Complexity of algorithm is concluded and validity of DNA algorithm is explained by an example. Three dominances of the closed circle DNA algorithm are analyzed, and characteristics and dominances of group delete experiment axe discussed.     

贝叶斯网络推理的一种高精度仿真算法

简要分析了贝叶斯网络推理算法的现状,提出了基于马氏链随机拟蒙特卡罗算法(MCRQMC)的推理方法.在给出高精度推理结果的同时,该推理算法亦能给出推理结果的标准偏差.从理论上对MCRQMC算法与现有的算法进行了比较分析,并采用随机Halton序列、Sobol序列和普通随机序列进行了推理实验.结果表明MCRQMC算法在同样样本数量的情况下,推理精度显著优于现有算法.     

时间Petri网与遗传-蚁群算法相结合的并行测试研究

自动测试系统中并行测试任务调度方案一直是尚未解决的难题.在基于Petri网理论的基础上,建立了并行测试的时间Petrl网模型,并且首次将遗传-蚁群算法引入到时间Petri网的变迁序列的寻找过程中,快速地求得了最优调度方案.仿真结果表明,该算法能够以较大的收敛概率快速地收敛,最终得到最优变迁序列.