基于人工神经网络的交通流量预测模型的研究

介绍了人工神经网络的BP算法，建立了基于Matlab神经网络工具箱的交通流量预测模型，并以实际道路交叉口为例进行2小时40分，分时段的数据采集，利用模型进行短时流量预测。     

一种基于聚合流的端到端统计时延界的新算法

为分析融合网络中聚合业务的端到端时延性能,提出一种基于聚合流的融合网络端到端统计时延界的新算法.该算法利用MGF(矩母函数)重新表征了网络端到端时延界的MGF形式的概率模型.数值分析结果表明了该算法的有效性和优越性,该算法很大程度上提高了独立统计复用,对融合网络性能评价具有参考意义.     

组合神经网络的网络流量预测研究

提出一种组合神经网络的网络流量预测模型.首先采用SMOF网络对网络流量数据进行聚类,然后采用Elman网络对聚类后的流量数据进行训练并预测,同时采用遗传算法对Elman网络的网络结构进行优化,提高网络流量预测精度.仿真结果表明,组合神经网络加快了网络流量预测速度,提高了网络流量预测精度,克服了单一预测模型不足,为网络流量预测提供了新的思路,具有很好的应用前景.     

一种基于小波变换和FIR神经网络的广域网网络流量预测模型

该文提出了一种基于小波变换和FIR神经网络的广域网网络流量预测模型,首先采用小波分解把网络流量数据分解成小波系数和尺度系数,即高频系数和低频系数,将这些不同频率成分的系数单支重构为高频流量分量和低频流量分量,利用FIR神经网络对这些分量分别进行预测,将合成之后的结果作为原始网络流量的预测。实验结果表明:采用该模型对实际的广域网网络流量数据进行预测,不仅可以得到较快的收敛效果,而且预测性能比现有的小波神经网络和FIR神经网络要好得多。     

基于神经网络的网络流量预测算法研究

网络流量预测有助于网络服务质量的提升和网络资源的合理分配,对优化网络管理与运营、保障用户体验质量至关重要.因特网业务的急剧增加和基础网络的快速发展导致网络流量变得更加复杂多样,传统网络流量预测模型难以保证较高的预测精度,而神经网络作为人工智能的重要分支,在预测复杂网络流量时具有显著优势.简述反向传播神经网络、径向基神经...     

ATM网络中突发业务的漏桶算法分析

统计复用可以使突发业务获得较高的频带利用率，但必须对输入的业务量进行恰当的控制，否则会造成严重的网络拥塞，漏桶法是ＡＴＭ网络基于速率调节进行业务量控制的一种重要的方法，本文对突发业务的漏桶算法进行了分析，得出了突发业务的漏桶性能与输入业务统计参数和漏桶参数之间关系的解析式，计算机模拟结果表明它与理论分析的一致性。     

基于人工神经网络的通信信号分类识别

通信信号的分类识别是一种典型的统计模式识别问题。系统地论述了通信信号特征选择、特征提取和分类识别的原理和方法。设计了人工神经网络分类器,包括神经网络模型的选择、分类器的输入输出表示、神经网络拓扑结构和训练算法,并提出了分层结构的神经网络分类器。     

小波分析与神经网络的网络流量预测模型

网络流量具有长相关、非平稳性与多时间尺度特性。提出了一种基于小波分析与AR(p)人工神经网络相结合的网络流量预测模型,即WPBP算法。该算法采用小波分析得到网络流量在不同尺度下的近似信号和细节信号,并运用AR(p)的相关性理论确定近似信号序列和细节信号序列的相关程度(p值),与神经网络进行耦合,以p+1划分数据,前p项作为输入,后一项作为输出对网络进行训练,从而使得神经网络的输入与输出的选择更加合理,预测的结果也更加准确。用小波重构得到最终的流量预测值,用实际网络流量对该模型进行验证。仿真结果表明,该模型的预测效果较好。     

Short-term traffic forecasting based on principal component analysis and a generalized regression neural network for satellite networks

With the rapid growth of satellite traffic, the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks, a forecasting algorithm based on principal component analysis and a generalized regression neural network (PCA-GRNN) is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically, it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data. Then, a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces, and the results show that the PCA-GRNN method achieves a higher forecasting accuracy, has a shorter training time and is more robust than other state-of-the-art algorithms, even for incomplete traffic datasets. Therefore, the PCA-GRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.     

Baselining network-wide traffic by time-frequency constrained Stable Principal Component Pursuit

The Internet traffic analysis is important to network management, and extracting the baseline traffic patterns is especially helpful for some significant network applications. In this paper, we study on the baseline problem of the traffic matrix satisfying a refined traffic matrix decomposition model, since this model extends the assumption of the baseline traffic component to characterize its smoothness, and is more realistic than the existing traffic matrix models. We develop a novel baseline scheme, named Stable Principal Component Pursuit with Time-Frequency Constraints (SPCP-TFC), which extends the Stable Principal Component Pursuit (SPCP) by applying new time-frequency constraints. Then we design an efficient numerical algorithm for SPCP-TFC. At last, we evaluate this baseline scheme through simulations, and show it has superior performance than the existing baseline schemes RBL and PCA.     

基于LatLRR和PCNN的红外与可见光融合算法

针对光谱差异较大的红外与可见光图像，本文提出一种基于潜在低秩表示（LatLRR）和脉冲式耦合神经网络（PCNN）的多尺度融合模型。首先，该算法利用非下采样剪切波变换（NSST）获取图像的低频与高频分量。鉴于图像的低频分量决定最终的融合效果，采用LatLRR算法挖掘源图像内在的显著特征对低频分量自适应加权融合。除此外，针对决定融合图像细节的高频分量，则利用双通道PCNN模型作为它的融合规则。其中平均梯度算子（AVG）和方向梯度和算子（SDG）分别作为PCNN的外界刺激与链接强度，它们能更好地表征图像的纹理特性。通过上述全新的融合规则，可将包含在红外图像内部的显著性特征与可见光图像的梯度特征完美结合，从而获取具有优良视觉效果的融合图像。本文采用3种不同的场景来测试所提方法的融合性能，与其他典型融合方法相比，本文提出的算法具有更佳的视觉效果，同时客观评价参数值增加约2%~5%。     

Improving reliability through architecture partitioning intelecommunication networks

The paper presents a new switching architecture to improve telecommunications reliability. The architecture is partitioned depending on the type of network used, reliability requirements, and expected traffic in the network. The partition size depends on the network reliability, bandwidth, and traffic. A reliability model for a telecommunication architecture is used to partition the network and to improve end-to-end reliability. The model defines critical components in the networking architecture and their connections. The component connections permit the propagation of faults from the component in which the fault originates to the other components. This propagation can cause failures in the chain (or in the tree) of components. The partitioned architecture limits the propagation of faults, simplifies fault detection, and preserves reliability of the remaining partitions. Examples of different networks are used to show the applications of the model     

Data truncation artifact reduction in MR imaging using a multilayer neural network

A magnetic resonance image (MRI) may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. A method for reducing the artifacts using a multilayer neural network is presented. The network consists of one linear output layer and at least one nonlinear hidden layer. The missing high-frequency components are predicted based on known low-frequency components and are used to reduce the truncation artifacts of the image. Results from a series of simulation experiments are discussed.     

The wavelet transform, time-frequency localization and signalanalysis

Two different procedures for effecting a frequency analysis of a time-dependent signal locally in time are studied. The first procedure is the short-time or windowed Fourier transform; the second is the wavelet transform, in which high-frequency components are studied with sharper time resolution than low-frequency components. The similarities and the differences between these two methods are discussed. For both schemes a detailed study is made of the reconstruction method and its stability as a function of the chosen time-frequency density. Finally, the notion of time-frequency localization is made precise, within this framework, by two localization theorems     

基于VMPSO-BP神经网络的话务量预测

为了更快速、准确地预测移动话务量,提出了速度变异的粒子群算法（VMPSO）,并与BP算法相结合,形成速度变异的粒子群—BP（VMPSO-BP）神经网络算法,用以训练神经网络,从而优化了神经网络的参数,最后对移动话务量进行预测。与传统BP神经网络方法和PSO-BP神经网络方法相比较,并且通过实验数据的分析以及对预测结果地比较,速度变异的粒子群—神经网络预测方法精度更高,收敛速度更快,从而更好地实现了对移动话务量地预测。     

A compressive sensing‐based network tomography approach to estimating origin–destination flow traffic in large‐scale backbone networks

A traffic matrix can exhibit the volume of network traffic from origin nodes to destination nodes. It is a critical input parameter to network management and traffic engineering, and thus it is necessary to obtain accurate traffic matrix estimates. Network tomography method is widely used to reconstruct end‐to‐end network traffic from link loads and routing matrix in a large‐scale Internet protocol backbone networks. However, it is a significant challenge because solving network tomography model is an ill‐posed and under‐constrained inverse problem. Compressive sensing reconstruction algorithms have been well known as efficient and precise approaches to deal with the under‐constrained inference problem. Hence, in this paper, we propose a compressive sensing‐based network traffic reconstruction algorithm. Taking into account the constraints in compressive sensing theory, we propose an approach for constructing a novel network tomography model that obeys the constraints of compressive sensing. In the proposed network tomography model, a framework of measurement matrix according to routing matrix is proposed. To obtain optimal traffic matrix estimates, we propose an iteration algorithm to solve the proposed model. Numerical results demonstrate that our method is able to pursuit the trace of each origin–destination flow faithfully. Copyright © 2014 John Wiley & Sons, Ltd.     

Network traffic prediction method based on wavelet transform and multiple models fusion

Accurate prediction of network traffic is an important premise in network management and congestion control. In order to improve the prediction accuracy of network traffic, a prediction method based on wavelet transform and multiple models fusion is presented. Mallat wavelet transform algorithm is used to decompose and reconstruct the network traffic time series. The approximate and detailed components of the original network traffic can be obtained. The characteristics of approximate components and detail components are analyzed by Hurst exponent. Then, according to the different characteristics of the components, autoregressive integrated moving average model (ARIMA) is chosen as the prediction model for the approximate component. Least squares support vector machine (LSSVM) is used to predict detail component. Meanwhile, an improved particle swarm optimization (PSO) algorithm is proposed to optimize the parameters of the LSSVM model. Gauss‐Markov estimation algorithm is adapted to fuse the predicted values of multiple prediction models. The variance of fusion prediction error is smaller than that of single prediction model, and the prediction accuracy is improved. Two actual datasets of network traffic are studied. Compared with other state‐of‐the‐art models, the case study results indicate that the proposed prediction method has a better prediction effect.     

Predictive dynamic bandwidth allocation for efficient transport ofreal-time VBR video over ATM

This paper presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. Video traffic statistics are measured in the frequency domain. The low-frequency signal captures the slow time-variation of consecutive scene changes while the high-frequency signal exhibits the feature of strong frame autocorrelation. Our queueing study indicates that the video transmission bandwidth in a finite-buffer system is essentially characterized by the low-frequency signal. We further observe in typical JPEG/MPEG video sequences that the time scale of video scene changes is in the range of a second or longer, which localizes the low-frequency video signal in a well-defined low-frequency band. Hence, in a network design it is feasible to implement dynamic allocation of video transmission bandwidth using on-line observation and prediction of scene changes. Two prediction schemes are examined: recursive least square method and time delay neural network method. A time delay neural network with low-complexity high-order architecture, called “pi-sigma network,” is successfully used to predict scene changes. The overall dynamic bandwidth-allocation scheme presented is shown to be promising and practically feasible in obtaining efficient transmission of real-time video traffic     

基于优化PCNN与区域特征引导法则的图像融合

针对传统红外与可见光图像融合算法存在着边缘信息缺失、目标特征不够突出等问题,本文提出一种基于优化脉冲耦合神经网络(PCNN)与区域特征引导法则的红外与可见光图像融合算法。首先,对红外与可见光图像分别进行非下采样剪切波变换(NSST),获取相应的低频分量和高频分量。其次,低频分量采用基于优化PCNN模型的融合规则进行融合;对于高频分量,利用图像的区域能量、改进空间频率和区域方差匹配度等特征,提出自适应的区域方差匹配度阈值和调节因子,构造区域特征引导法则完成融合。最后,对融合后的低高频分量进行NSST逆变换,获取融合图像。实验结果表明,本文算法可有效综合图像的优势信息,并在主观视觉和客观指标上均具有明显的优势。