Hopfield神经网络算法求解路网最优路径

为了解决经典算法在求解大规模路网最优路径时运算时间长的问题,研究了Hopfield神经网络的特点,建立了一般路网的数学模型,根据Hopfield神经网络的特点设计了适合车辆诱导的路网Hopfield神经网络最优路径算法.采用动态邻接矩阵对该算法进行了优化,减少了运算时间.把该Hopfield神经网络算法应用于所研发的车辆诱导系统的最优路径求解中,并进行了实际路网测试,结果表明应用该算法能够正确求解路网的最优路径,且比经典算法的运算效率高.     

基于Hopfield混沌神经网络和压缩感知的可视化图像加密算法

目前大多数的图像加密算法直接将明文图像加密成无视觉意义的密文图像,而这类密文图像在传输过程中容易被黑客发现从而受到各种攻击。针对上述问题,结合Hopfield混沌神经网络与压缩感知技术提出了一种具有视觉意义的图像加密算法。首先,利用二维离散小波变换对明文图像进行稀疏化;其次,通过压缩感知对经过阈值处理的稀疏矩阵进行加密和测量;然后,在量化的中间密文图像中加入随机数并进行Hilbert置乱和扩散操作;最后,将生成的类噪声密文图像通过最低有效位（LSB）替换来嵌入到载体图像中的Alpha通道以生成具有视觉意义的隐写图像。与现有的可视化图像加密算法相比,所提算法展现出非常好的视觉安全性、解密质量以及鲁棒性,表明其具有广泛的应用场景。     

Global robust stability of interval delayed neural networks: Modified approach

A criterion for the global robust stability of Hopfield‐type delayed neural networks with the intervalized network parameters is presented. The criterion, which is derived by utilizing the idea of splitting the given interval into two intervals, is in the form of linear matrix inequality and, hence, computationally tractable. The criterion yields a less conservative condition compared with many recently reported criteria, as is demonstrated with an example. Copyright © 2008 John Wiley & Sons, Ltd.     

Channel routing using neural networking

Abstract

The channel routing problem in an integrated circuit layout design involves making interconnections among terminals located on opposite sides of a rectangular channel. This problem has been proven to be NP‐complete and most currently available algorithms are heuristic. This paper proposes a neural network to handle the channel routing problem. Neural networking has been successfully applied to many combinatorial optimization problems. However, applying this technique to the channel routing problem has not ever been reported. This network allows users to preroute any critical nets and then invoke the network to complete the rest. User intervention also can speedup the operation of the router significantly. Typical examples from published literature are taken for experiments. The theoretic lower bounds are achieved in all examples.     

基于可变步长的Hopfield神经网络盲检测算法

使用了一种新的激活函数,来提高Hopfield神经网络(Hopfield Neural Network,HNN)的抗干扰性能。为解决采用新激活函数后收敛速度较慢的问题,设计了一种基于可变步长的Hopfield神经网络(Variable Step Hopfield Neural Network,VSHNN)盲检测算法。仿真实验表明,与传统盲检测算法相比,VSHNN盲检测算法加快了能量函数收敛速度,提高了算法的抗干扰性能。     

基于双Sigmoid小波混沌神经网络的盲检测算法*1

接要:针对在盲检测环境中暂态混沌神经网络的缺陷,提出了基于双Sigmoid小波混沌神经网络的盲检测算法,构建了新网络的模型和能量函数,并分别在同步和异步更新模式下证明了该网络的稳定性.新网络的设计思想体现在:采用墨西哥帽小波函数和Sigmoid函数的组合作为网络的激励函数,再为每个神经元加一个激活函数构成双Sigmoid.仿真表明:由于小波函数较强的逼近能力以及双Sigmoid快速收敛的特性,提出的算法显著地提高了网络的全局寻优能力和寻优精度.     

应用Hopfield网络反演分层分区变形模量

提出了应用Ｈｏｐｆｉｅｌｄ网络来反演分层分区变形模量的方法，并对网络的构建、稳定性进行了探讨。     

用Hopfield模型求解组合优化问题的拟人策略

文章对Hopfield网络状态的更新准则，提出了一个自适应的拟人策略。数值模拟表明，引入拟人策略的Hopfield模型对求解组合优化问题非常有效。     

Scheduling flow shops in the environment of multi-functional machine tools

The concept of virtual machine tool (VMT) is introduced in this paper to specify machining resources of multi-functional machine tools. A two-level model for makespan minimization in a flow shop is developed in multi-functional machine tool environments. The model is first optimized with an Hopfield neural network to find the optimal processing sequence for components to visit all the necessary VMTs. Secondly, according to a set of shop floor control rules, the VMTs for components machining are matched with real machine tools. This procedure is driven by the events taking place in components machining, such as the arriving or the finishing of a component. Numerical experiments are conducted in a number of flow shop scheduling problems up to 8×8 and the mean relative optimizing rate is employed to assess the results of numerical experiments.     

基于Hopfield实现ATM网络路由选择的双重路由算法

研究神经网络用于ＡＴＭ网络路由调度问题,通过引入等效带宽的概念,以降低呼损率和提高网络利用率为优化目标,提出双重路由算法。根据不同的网络状态,采用不同基于Ｈｏｐｆｉｅｌｄ的路由方法。提出的算法不但逻辑控制及硬件实现较为简单,而且仿真结果表明,在各种呼叫分布及网络拓扑情况下,均有效降低呼员率和提高网络和利用率。很好优化 了系统性能。