基于神经网络算法的无线网络安全模型设计

为实现对无线网络的有效保护,文章运用BP神经网络和GA遗传算法,完成对无线网络安全模型设计。首先,将BP神经网络与GA遗传算法进行有效的融合,提出一种GABP神经网络算法。其次,针对无线网络安全问题,运用该算法,从无线网络拓扑结构设计、无线网络入侵检测单位模型构建入手,完成对无线网络安全模型的设计。最后,对该模型进行仿真分析。结果表明:将BP神经网络与GA遗传算法应用到无线网络攻击类型中从而提高识别率,降低了误报率,确保了无线网络的安全性和可靠性。笔者希望该研究可以为相关人员提供有效的借鉴和参考。

基于限时免费换乘的公交线网优化模型与求解算法

针对"限时免费换乘"政策的提出,为了使轨道交通与地面常规公共交通线网构成的综合公共交通网络更加合理,以公交线网系统总费用最小为目标,将"限时免费换乘"条件作为乘客乘车成本因子,以公交单条线路长度、线路非直线系数、线路重叠系数、换乘次数为约束条件,建立了城市轨道交通与地面常规公共交通线网优化模型。考虑"限时免费换乘"条件,从信息素的累积与惩罚机理着手改进了蚁群算法,并给出了将该算法求解城市轨道交通与地面常规公共交通线网优化模型的算法流程。所建立的模型与改进的蚁群算法为优化轨道交通与常规公共交通系统构成的综合公共交通网络提供了一种新方法。

基于居民出行需求的公交线网优化模型研究

公交线网优化模型是整个线网优化的基础。通过对居民公交出行需求进行研究,找出影响居民公交出行的主要因素,从而构建了线网优化模型。通过对模型及约束条件的分析,得出以换乘次数最少为主要目标,所经过的公交站点数最少为次要目标的线网优化模型。

城市公交线网优化模型研究

通过对居民公交出行需求的研究,找出影响居民公交出行的主要因素,构建以换乘次数最少为第一目标,所经过的公交站点数最少为第二目标的线网优化模型,该模型对城市公交的发展具有重要的意义。

基于城市空间结构的轨道交通线网生成方法

为破解目前轨道交通线网规划方法主观随意性较大,形成的方案与城市发展和延伸方向不符,以及交通供给与需求难以在时空上很好匹配的问题,提出一种基于城市空间结构的城市轨道交通线网生成方法。首先,采用反距离修正的Infomap算法划分城市组团;其次,对线网数据进行前置数据处理,缩小模型的计算范围并推算得到线网密度、客流强度和线网规模3项关键参数;然后,构建线网生成模型,按照“组团间线网生成—组团内线网生成—线网整合与优化”的技术路线生成线网。依托某市实际数据构建算例,验证该线网生成方法的效果。结果表明:相比于该市的实际线网,前述方法得到的线网在布局上的延伸性更优,覆盖面积率提升68%,线网吸引范围内的公交站点数量更多,增加了639个,线网的全局可达性更高;增加的组团划分步骤,能够显著提升线网覆盖的中心城区面积率,生成线网的辐射力度和带动作用更强。

无线网络信号模型的自回归参数估计

以傅里叶变换为基础的传统技术所提供的频率分辨率是非常有限的,而基于有理传递函数模型的技术则可以提供更高的频率分辨率。有理传递函数模型比较适合在连续频谱条件下建模,而对于离散频谱,则采用谐波模型更加合适。

页岩气体积压裂缝网模型分析及应用

对低渗透页岩储层进行体积压裂改造以形成复杂裂缝网络是获得页岩气经济产能的关键,压裂改造体积和缝网导流能力是评价体积压裂施工效果的关键指标,同时对压裂优化设计、压后产能预测及经济评价也具有重要意义。为此,在分析页岩气体积压裂特点的基础上,对两种主要页岩气体积压裂缝网模型的假设、数学方程及参数优化方法进行了比较分析,并结合美国Marcellus页岩区块现场参数对页岩储层压裂方案进行了优选。结果表明:离散化缝网模型及线网模型均能有效表征复杂缝网几何特征,模拟缝网的扩展规律和缝网中压裂液流动及支撑剂运移,获得缝网几何形态参数,可优选压裂施工方案;天然裂缝发育的页岩层是体积压裂改造的重点,水平地应力差越小则越易形成复杂缝网,施工排量越大,压裂液泵入总量越大,则储层改造体积范围越大,缝网导流能力越高,页岩气产能就越高。

页岩气体积压裂数值模拟研究

为建立合理的页岩气体积压裂水平井产能模拟模型,同时研究压裂裂缝参数及地层性质对压裂井产能的影响,通过油藏数值模拟的方法,以某口页岩气井基本参数为基础,利用椭球体状的线网模型模拟复杂的裂缝网络,并利用不可流动油中的溶解气模拟页岩中的吸附气,建立页岩气体积压裂水平井的产能预测模型。在建立模型的基础上分析页岩气体积压裂水平井储层改造体积、网状裂缝导流能力、改造体积的复杂程度等参数对产能的影响,并研究了地层渗透率非均质性等对改造井的影响。结果表明,所建模型能高效模拟实际页岩气体积压裂水平井产能。研究显示改造体积越大,裂缝的导流能力越强,主、次裂缝的间距越小,页岩气体积压裂水平井的产能越高。地层渗透率各向异性对气井产能的影响较小。所建模型对页岩气体积压裂开发效果的预测有积极意义。

基于OPNET的车用Ad hoc网可靠性评估研究

通过搭建车用Ad hoc网络(VANET)的仿真平台,将一个真实的车辆节点移动模型与标准的无线移动Ad hoc网络模型进行结合来对车用网络的可靠性进行评估。反映了车辆的移动特性对整个VANET可靠性的影响,利于更详细、更直观地刻画VANET的重要特性,为将来VANET相关协议的设计提供具体、详实的参考数据和建议。

A Reduced-Order Modeling of Multi-Port RC Networks by Means of Graph Partitioning

A modified reduced-order method for RC networks which takes a division-and-conquest strategy is presented.The whole network is partitioned into a set of sub-networks at first,then each of them is reduced by Krylov subspace techniques,and finally all the reduced sub-networks are incorporated together.With some accuracy,this method can reduce the number of both nodes and components of the circuit comparing to the traditional methods which usually only offer a reduced net with less nodes.This can markedly accelerate the sparse-matrix-based simulators whose performance is dominated by the entity of the matrix or the number of components of the circuits.

Security analysis of newly ameliorated WAPI protocol

Based on thorough researches on the Chinese wireless local area network （WLAN） security standard, i. e., WLAN authentication and privacy infrastructure （WAPI）, the security of the authentication access process is analyzed with the CK （Canetti-Krawczyk） model and the BAN （Burrows-Abadi- Needham） logic. Results show that it can achieve the alleged authentication and key negotiation goals. Besides those alleged, further analyses indicate that the authentication access process can satisfy other security requirements, such as mutual identity authentication, mutual key control, key confirmation, message integrity check, etc. If the used elliptic curve encryption algorithm and the hash algorithm are secure enough, the protocol can efficiently realize mutual authentication between STAs （station） and APs （access point）. Therefore, WAPI can be applied to replace the security mechanism used in the original WLAN international standard to enhance its security.

Identification of Hammerstein Model Using Hybrid Neural Networks

The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a multi layer feed forward neural network (MFNN) in cascade with a linear neural network (LNN). A unified back propagation (BP) algorithm is proposed to estimate the weights and the biases of the MFNN and the LNN simultaneously. Numerical examples are provided to show the efficiency of the proposed method.

网络仿真及OPNET应用研究

网络仿真技术是进行网络规划与设计的有效方法和工具。本文在系统地分析网络仿真基本方法和仿真流程的基础上,阐述了网络仿真平台OPNET的主要特性、建模机制及其仿真方法和步骤。基于OPNET对一个点对点的无线网络模型进行仿真,给出仿真结果并对其进行了分析。

THE MODEL VALIDATION OF DYNAMIC NEURAL NETWORKS

This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.

Pore-scale simulation of gas-water flow in low permeability gas reservoirs

A novel method was developed to establish a realistic three dimensional(3D) network model representing pore space in low permeability sandstone.Digital core of rock sample was established by the combination of micro-CT scanning and image processing,then 3D pore-throat network model was extracted from the digital core through analyzing pore space topology,calculating pore-throat parameters and simplifying the shapes of pores and throats.The good agreements between predicted and measured porosity and absolute permeability verified the validity of this new network model.Gas-water flow mechanism was studied by using pore-scale simulations,and the influence of pore structure parameters,including coordination number,aspect ratio and shape factor,on gas-water flow,was investigated.The present simulation results show that with the increment of coordination number,gas flow ability in network improves and the effect of invading water on blocking gas flow weakens.The smaller the aspect ratio is,the stronger the anisotropy of the network is,resulting in the increase of seepage resistance.It is found that the shape factor mainly affects the end points in relative permeability curves,and for a highly irregular pore or throat with a small shape factor,the irreducible water saturation(Swi) and residual gas saturation(Sgr) are relatively high.

A Hybrid Handover Forecasting Mechanism Based on Fuzzy Forecasting Model in Cellular Networks

As the increasing demand for mobile communications and the shrinking of the coverage of cells, handover mechanism will play an important role in future wireless networks to provide users with seamless mobile communication services. In order to guarantee the user experience, the handover decision should be made timely and reasonably. To achieve this goal, this paper presents a hybrid handover forecasting mechanism, which contains long-term and short-term forecasting models. The proposed mechanism could cooperate with the standard mechanisms, and improve the performance of standard handover decision mechanisms. Since most of the parameters involved are imprecise, fuzzy forecasting model is applied for dealing with predictions of them. The numerical results indicate that the mechanism could significantly decrease the rate of ping-pong handover and the rate of handover failure.

Neural Network for Prediction of Thermal Elastomer Quality

Aim To predict the indexes of quality of the thermal elastomer by polymerization process data. Methods Neural networks were used for learning the relationship between the product quality and the polymerization process condition variables in an industrial scale batch polymerization reactor. Results The indexes of quality of the product were inferred with acceptable accuracy from easy to measure reaction process condition variables. Conclusion The method proposed in this paper provides on line soft sensors of the indexes of quality of the thermal elastomal.

Generalized Physical Layer Channel Model for RelayBased Super Dense Networks

The κ-μ fading model is an advanced channel model in super dense wireless networks.In this paper,we evaluate the performance of the system over κ-μ fading channel in super dense relay networks with consideration of multiple independent but not necessarily identically distributed(i.n.i.d.) cochannel interference(CCI) under interferencelimited environment.More specifically,we derive a useful and accurate cumulative distribution function(CDF) expression of the end-to-end signal-to-interference plus noise(SINR) ratio.Moreover,we derive novel analytical expressions of the outage probability(OP),average bit error probability(ABEP) and average capacity for binary modulation types and arbitrary positive values of κ-and μ of such system.Furthermore,we propose asymptotic analysis for both the OP and ABEP to give physical insights.A simplified analytical form for the ABEP at high-SNR regimes is provided as well.Finally,the accuracy of the derived expressions is well validated by Monte Carlo simulations.

Two States CBR Modeling of Data Source in Dynamic Traffic Monitoring Sensor Networks

Real traffic information was analyzed in the statistical characteristics and approximated as a Gaussian time series. A data source model, called two states constant bit rate (TSCBR), was proposed in dynamic traffic monitoring sensor networks. Analysis of autocorrelation of the models shows that the proposed TSCBR model matches with the statistical characteristics of real data source closely. To further verify the validity of the TSCBR data source model, the performance metrics of power consumption and network lifetime was studied in the evaluation of sensor media access control (SMAC) algorithm. The simulation results show that compared with traditional data source models, TSCBR model can significantly improve accuracy of the algorithm evaluation.

Spectrum Sensing Model for Wireless Internet of Things

In the last few years, the number of devices operating in wireless Internet of Things （IoT） has experienced tremendous growth. On the other hand, the growth results in spectrum scarcity. Cog- nitive Radio （CR） systems have been proposed to efficiently exploit the spectra that have been assigned but are underutilized. In this paper, a spectrum sensing model based on Markov chain is proposed to predict the spectrum hole for CR in wireless IoT. Theoretical analysis and simulation results have been evaluated that a Markov model with two- state or four-state works well enough in wireless loT whereas a model with more states is not necessary for it is complex.