网络节点数

和Dijkstra算法相比，算法大大减小搜索空间，提高搜索速度，时间复杂性不超过O（N），N为网络节点数。

Compared with Dijkstra algorithm , the algorithm can reduce seeking space and can raise seeking speed greatly , and its time complexity can not exceed O ( N ), while N is the number of road net points .

出货的网络节点数每年以150%以上的惊人速度增长。

The seled node number is increasing in 150 % every year .

得出任意两个节点名字相同概率在极小的条件下，网络节点数和名字空间大小两者间的函数关系。

The algorithm reveals the relation between the size of name space and the node number .

仿真结果显示既使网络节点数较多，这一算法仍运行良好且能以较大的概率找到全局最优解。

Our simulation study shows that the proposed algorithm performs well and can find the optimum solution with high probability .

并且由于路由表的规模控制在网络节点数的对数量级内，路由信息汇聚迅速，所以建立和维护路由表的代价（更新时间，带宽占用，路由器资源的耗费等）相比传统路由方法大幅度降低。

Also , since the routing table scale is reduced and the cost of the setup and maintenance of routing table is low .

研究表明，给定传感器网络节点数和重连概率后，当网络的近邻节点数取合适的值时，平均路径长度还将进一步降低。继续增大近邻节点数则网络平均路径长度变化不大。

It is shown that for a given number of sensor nodes and rewired probability , the average path length of a network can be further reduced dramatically at some reasonable neighboring nodes .

在网络节点数不变时，则可大大减少网络节点的排队时延，缓和网络中各通信节点对数据信道波长使用权的竞争矛盾，使网络吞吐量增加1～3倍，有效地改善网络性能。

Under the same number of nodes , the delay of network can be greatly lowered , the throughput can be increased 1 ~ 3 times , the properties of network can be efficiently improved .

使用传统方法的计算时间为O（n2logn）（其中n为网络的节点数）。

The traditional algorithm runs in time O ( n2logn ) .

利用遗传算法，对神经网络输入节点数、径向基函数分布系数及网络训练误差进行了优化，得到了最优的RBF网络预测模型。

The genetic algorithm ( GA ) is used to optimize the node number of input layer , the spread coefficient of radial basis function , and training error , in order to obtain the optimum forecasting model of RBF network .

当线性电网络的节点数保持不变时，若在i、k两节点间插入线性、无独立源二端网络时，研究它对网络传输性能的影响问题。

Under the conditions that the number of the nodes of linear electrical network remains unchanged and a linear , non-independent source , two-terminal network between the nodes I and k of original network is inserted , the effects on the transfer property of the network has been researched into .

仿真的内容有网络存活节点数和网络剩余能量。

The simulation includes the network lifetime network lifetime number of nodes .

结果表明，改进后高优先级数据的传输时延明显降低，网络死亡节点数减少了近30%，延长了生存时间。

The experiments showed that the delay of higher-priority data is lower obviously , and the dead nodes are reduced to almost 30 % in network , and lifetime of WSN is also prolonged .

在第一层图像预处理阶段提取人体轮廓，标定其为感兴趣区域并进行缩放操作，降低数据维度。提出了金字塔型架构的网络层节点数选择方案，节省计算开支。

In first layer , recognise body contours in image preprocessing stage , mark it as interested area and operate zooming in or out , deduct data dimensions presenting pyramid network node optional program cutting down the budget .

确定RBF神经网络隐层节点数的最大矩阵元法

Maximal Matrix Element Method for Determining the Number of Hidden Nodes of RBF Neural Networks

针对BP神经网络中隐层节点数难以确定的问题，提出了一种基于权值拟熵的快速OBS剪枝算法。该算法对OBS剪枝算法进行了改进，能够大大提高网络的剪枝速度。

A fast OBS pruning algorithm based on pseudo-entropy of weights is proposed to resolve the problems of the number of hidden neurons which is difficult to be determined in BP neural networks , the OBS pruning algorithm is improved , and the speed of pruning is improved greatly .

一种确定神经网络隐层节点数的新方法

A New Method to Determine Hidden Note Number in Neural Network

前向神经网络隐含层节点数的一种优化算法

An Optimization Algorithm on the Number of Hidden Layer Nodes in Feed-forward Neural Network

确定前向神经网络隐层节点数的模糊聚类分析法

Fuzzy Cluster Analysis Method for Determining the Number of Hidden Nodes of Feedforward Neural Networks

探讨了不同预处理方法组合及神经网络隐含层节点数对所建模型的影响。

The influences of different pre-processing combinations and nodes number of hidden layers to the models were discussed .

换句话说，网络中的节点数按照算术法则提升，而网络的价值则按照指数法则提升。

In other words , as the number of nodes in a network increases arithmetically , the value of the network increases exponentially .

无标度网络的初始节点数决定了网络中大节点的数量，初始节点数与拟合延迟函数的平均延迟时间是负相关的。

The initial nodes of scale-free network determine the number of major nodes in the network , and the initial number of nodes is negatively related to the average delay time of fitting delay function .

选取重构相空间中的饱和嵌入维数作为神经网络的输入节点数，适当选择非线性反馈项，能使网络的动力学在权空间具有混沌行为。

Taking the saturation inset dimension of reconstructed phase space as the input node number of artificial neural network and suitable nonlinear feedback terms are selected , the dynamics of network become chaotic in the weight space .

研究表明，若给定耦合强度，则在这两种网络中混沌节点数占总节点数的初始比例对最终的比例曲线均具有两个相变过程。

The research suggests that in the two different networks , as the initial proportion of chaotic nodes increases , there are two phase change process of the final proportion of chaotic node for a given coupling strength .

然而，当感兴趣体积分数区被分成更多的子区域或混合气体组分数多于2时，模式类别数目的急剧增加使网络的输出节点数也大增。

However , when the volume fraction area of interest divides into more sub-areas or the component number of gas mixture is more than two , the number of pattern classification will increase rapidly , and cause the great increase of output nodes of ANN .

通过对柴油机供油系统柱塞磨损故障的自动分类和诊断，表明该系统能有效地减少神经网络的输入节点数，克服了神经网络规模过于庞大及分类识别速度慢等缺点。

Through automatic fault classification and diagnosis for plunger abrasion fault in fuel injection system of diesel engine , the example shows that this system reduces input node number and overcomes some shortcomings , such as neural network scale is too large and the rate of classification is slow .

同时采用基于优化原理的HCM算法实现聚类过程，来确定RBF网络的隐含层节点数，使网络的利用效率较高。

Meanwhile optimization theory based HCM clustering algorithm is used to cluster sample data to determine the number of node of hidden layer , so that the efficiency of RBF network in use is high .

本文提出一种同图论中可达矩阵和区域划分思想相结合的模糊聚类方法，以此来确定RBF网络的隐含层节点数。

A way of fuzzy cluster is provided , which is combined with reachability matrix and the idea of region partition in graph theory , in order to find out the number of the hidden layer nodes of RBF neural network .

对于BP神经网络的隐含层节点数难以确定的问题，根据已有的隐含层节点数确定的经验公式，提出了一种改进公式，在实际应用中证明了改进公式的实用性和有效性。

Aiming at the problem of the hidden layer nodes of BP neural network is difficult to determine , in this paper , an improved algorithm formula used to confirm the hidden layer nodes is brought forward . It is proved that the improved formula is very practicality and effectiveness .

分析了在多跳的通信模式下，网络中的节点个数与链路容量之间的关系，通过在MAC层对节点的发送次序进行调度，获得了与虚多天线技术相同的容量扩展级。

For multi-hop networks , the relation between the number of sensors and the link capacity is analyzed , and the same capacity scaling law as that with the virtual multi-antenna technique is achieved by scheduling the transmission order of different nodes in the MAC layer .

本方法也为多隐层人工神经网络隐层神经元节点数的确定奠定了理论基础。

This method provided theory foundation for the structure establishment of hide-layer neural cell of artificial neural network also .