计算机网络安全评价中对于神经网络的应用探究

知识经济的到来促进了信息化的发展,计算机和网络技术也在发展和变化,影响网络安全的不确定因素也日趋变化,种类形式增加.网络安全是当前网络应用者不可轻视和低估的问题,为了解决和减少越来越突出的网络安全问题,探讨计算机网络评价对于神经网络的应用价值是具有重要意义的.神经网络的应用可大幅度的降低计算机网络安全风险,降低其带来的损失.神经网络在计算机安全评价中具有很大的实际效用和价值.     

计算机网络安全评价中神经网络的应用研究

当前,科学技术快速发展,安全评价对安全生产以及管理具有重要的作用.事实证明,相关方法的选用对于安全评价的顺利进行十分重要,对于评价结果的客观性以及准确度都能够产生重要影响.在传统背景下,计算机网络安全评价方式存在较多问题,使得其对评价结果产生不利影响.为了应对这些方面的问题,将神经网络引入其安全评价之中,对于工作效率的提升具有重要的现实意义.     

Multiagent reinforcement learning applied to a chase problem in a continuous world

Reinforcement learning (RL) is one of the methods of solving problems defined in multiagent systems. In the real world, the state is continuous, and agents take continuous actions. Since conventional RL schemes are often defined to deal with discrete worlds, there are difficulties such as the representation of an RL evaluation function. In this article, we intend to extend an RL algorithm so that it is applicable to continuous world problems. This extension is done by a combination of an RL algorithm and a function approximator. We employ Q-learning as the RL algorithm, and a neural network model called the normalized Gaussian network as the function approximator. The extended RL method is applied to a chase problem in a continuous world. The experimental result shows that our RL scheme was successful. This work was presented in part at the Fifth International Symposium on Artificial Life and Robotics, Oita, Japan, January 26–28, 2000     

Using fuzzy logic to improve a clustering technique for function approximation

Clustering algorithms have been successfully applied in several disciplines. One of those applications is the initialization of radial basis function (RBF) centers composing a neural network, designed to solve functional approximation problems. The Clustering for Function Approximation (CFA) algorithm was presented as a new clustering technique that provides better results than other clustering algorithms that were traditionally used to initialize RBF centers. Even though CFA improves performance against other clustering algorithms, it has some flaws that can be improved. Within those flaws, it can be mentioned the way the partition of the input data is done, the complex migration process, the algorithm's speed, the existence of some parameters that have to be set in order to obtain good solutions, and the convergence is not guaranteed. In this paper, it is proposed an improved version of this algorithm that solves the problems that its predecessor have using fuzzy logic successfully. In the experiments section, it will be shown how the new algorithm performs better than its predecessor and how important is to make a correct initialization of the RBF centers to obtain small approximation errors.     

Improving the generalization performance of RBF neural networks using a linear regression technique

In this paper we present a method for improving the generalization performance of a radial basis function (RBF) neural network. The method uses a statistical linear regression technique which is based on the orthogonal least squares (OLS) algorithm. We first discuss a modified way to determine the center and width of the hidden layer neurons. Then, substituting a QR algorithm for the traditional Gram–Schmidt algorithm, we find the connected weight of the hidden layer neurons. Cross-validation is utilized to determine the stop training criterion. The generalization performance of the network is further improved using a bootstrap technique. Finally, the solution method is used to solve a simulation and a real problem. The results demonstrate the improved generalization performance of our algorithm over the existing methods.     

A novel parallel hybrid intelligence optimization algorithm for a function approximation problem

A novel parallel hybrid intelligence optimization algorithm (PHIOA) is proposed based on combining the merits of particle swarm optimization with genetic algorithms. The PHIOA uses the ideas of selection, crossover and mutation from genetic algorithms (GAs) and the update velocity and situation of particle swarm optimization (PSO) under the independence of PSO and GAs. The proposed algorithm divides the individuals into two equation groups according to their fitness values. The subgroup of the top fitness values is evolved by GAs and the other subgroup is evolved by the PSO algorithm. The optimal number is selected as a global optimum at every circulation which shows better results than both PSO and GAs, then improves the overall performance of the algorithm. The PHIOA is used to optimize the structure and parameters of the fuzzy neural network. Finally, the experimental results have demonstrated the superiority of the proposed PHIOA to search the global optimal solution. The PHIOA can improve the error accuracy while speeding up the convergence process, and effectively avoid the premature convergence to compare with the existing methods.     

Alternative diagnosis of corporate bankruptcy: A neuro fuzzy approach

Bankruptcy filings are as high today as ever, calling into question the efficacy of existing bankruptcy prediction models. This paper tries to provide an alternative for bankruptcy prediction by using neuro fuzzy, a hybrid approach combining the functionality of fuzzy logic and the learning ability of neural networks. The empirical results show that neuro fuzzy demonstrates a better accuracy rate, lower misclassification cost and higher detecting power than does logit regression, meaning neuro fuzzy could be a great help in providing warnings of impending bankruptcy. Also, its comprehensive explanation about mapping functions among variables presumably provides a foundation for further development of theory and testing of the membership function shape, the transfer function, the methods to aggregate, the methods to defuzzify, and so on.     

关于计算机网络应用安全问题的思考

当前,计算机行业蓬勃发展,社会各行业都已经将计算机技术应用到日常工作中来。在我们享受到计算机网络为我们带来的便捷同时,我们也应该考虑计算机网络在应用中所存在的安全问题。越是先进的网络技术,其潜在的安全隐患就越大。本文就计算机网络在应用中常见的安全问题进行分析,并结合实际情况探讨如何采取措施加强计算机网络在应用中的安全问题。     

Fast pattern recognition using a neurocomputer

This paper presents a new pattern recognition system based on moment invariants using a neurocomputer. The new pattern recognition system consists of a CCD video camera, an image processing system named FDM, a monitor, two stand lights, an NEC PC-9801 microcomputer and a RICOH RN-2000 neurocomputer; these two different types of computers can be considered to constitute an artificial brain. Experimental studies to recognize five dynamic patterns of Japanese chestnuts were performed. From the studies, a high speed of both learning and recognition has been achieved compared with the former pattern recognition system based on the software of artificial neural networks developed by us. This work was presented, in part, at the International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1996     

Execution of a remote sensing application on a custom neurocomputer

A radial basis function neural network was successfully applied to an area which is relatively new for neural networks: a remote sensing application that provides estimates of water vapor content, an important parameter for climate modeling. The neural network provided results which are up to 32% better than had been previously obtained using conventional statistical methods on the same data. These results have implications for improved short-term weather forecasting and for long-term global climate modeling. The neural network approach is compared with the past and present operating algorithms at the National Oceanic and Atmospheric Administration. The radial basis function network's performance is compared with sigmoidal backpropagation network. Low-power electronic implementations of the neural methodology were explored to demonstrate the feasibility of placing the network on a remote sensing platform. This would permit processing the raw sensor data into information on the platform, eliminating the need to store the raw data, and helping to contain the expected explosion of climate data.     

Adaptive multiple-surface sliding control for non-autonomous systems with mismatched uncertainties

In this paper, we propose a sliding mode-based controller for a class of single-input single-output nonlinear systems with mismatched uncertainties whose variation bounds are not given. The concept of multiple-surface sliding control is used to cope with the uncertainty mismatch problem, and the function approximation technique is introduced to transform the uncertainties into a finite combination of orthonormal basis functions. An adaptive controller can thus be designed using the Lyapunov approach to achieve output error convergence and boundedness of all signals. Simulation results of a benchmark problem have verified the performance and feasibility of the proposed control strategy.     

A sum-of-product neural network (SOPNN)

This paper presents a sum-of-product neural network (SOPNN) structure. The SOPNN can learn to implement static mapping that multilayer neural networks and radial basis function networks normally perform. The output of the neural network has the sum-of-product form ∑Npi=1∏Nvj=1 fij (xj), where xj's are inputs, Nv is the number of inputs, fij( ) is a function generated through network training, and Np is the number of product terms. The function fij(xj) can be expressed as ∑kwijkBjk(xj), where Bjk( ) is a single-variable basis function and Wijk's are weight values. Linear memory arrays can be used to store the weights. If Bjk( ) is a Gaussian function, the new neural network degenerates to a Gaussian function network. This paper focuses on the use of overlapped rectangular pulses as the basis functions. With such basis functions, WijkBjk(xj) will equal either zero or Wijk, and the computation of fij(xj) becomes a simple addition of some retrieved Wijk's. The structure can be viewed as a basis function network with a flexible form for the basis functions. Learning can start with a small set of submodules and have new submodules added when it becomes necessary. The new neural network structure demonstrates excellent learning convergence characteristics and requires small memory space. It has merits over multilayer neural networks, radial basis function networks and CMAC in function approximation and mapping in high-dimensional input space. The technique has been tested for function approximation, prediction of a time series, learning control, and classification.     

基于支持向量机函数逼近的性能研究

通过仿真分析比较支持向量机与前馈神经网络在非线性函数逼近的结果,得出在小样本下,SVM的样本依赖程度、抗噪声能力和泛化性能都优于前馈神经网络。     

一种基于神经网络基函数的新型遗传算法

该文提出了一种新型的遗传优化方法。由参数模型描述的神经元基函数作为遗传基因,利用每个神经元输出序列与网络训练目标以及神经元输出序列之间的相关性得到网络遗传优化方法的选择算子,根据不同参数的特点得到相应的交叉和变异算子,建立基函数的参数化模型,得到遗传算法的初始基因组;并根据初始基因组建立各参数基因组,通过合适的交叉变异算子对个各参数基因组进行交叉变异操作。这样得到的算法使输出误差分布较为均匀,能够大大提高网络的输出精度,简化网络的结构,信号跟踪与非线性系统逼近中得到很好的效果,提高了网络的适时学习能力。     

Assigning discounts in a marketing campaign by using reinforcement learning and neural networks

In this work, RL is used to find an optimal policy for a marketing campaign. Data show a complex characterization of state and action spaces. Two approaches are proposed to circumvent this problem. The first approach is based on the self-organizing map (SOM), which is used to aggregate states. The second approach uses a multilayer perceptron (MLP) to carry out a regression of the action-value function. The results indicate that both approaches can improve a targeted marketing campaign. Moreover, the SOM approach allows an intuitive interpretation of the results, and the MLP approach yields robust results with generalization capabilities.     

神经网络控制的现状与展望

对神经网络在控制中的应用进行了综述,特别对现阶段几种较重要的神经（网络）控制的现状进行了评述,并对神经控制的发展作了展望,最后对神经网络用于控制中存在的几个问题进行了探讨。     

Adaptive-intelligent control of intelligence flows as microheat transfer

From the point of view of microheat transfer, adaptive-intelligent controls (AIC) of intelligence flows by neural-network (NN)- and genetic-algorithm (GA)-systems are studied to breakthrough towards brain computing. Characteristics of information flows in NN- and GA-systems are derived. As an application computer-simulation system for nanostructured materials is constructed. AIC of intelligence flows are discussed.     

Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill

Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than −0.098 the second lower than 0.8058 and the third higher than −0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab.     

Convergence properties of cascade correlation in function approximation

Incremental neural networks have received increasing interest in the neural computing field, especially in reducing training time. Among various emerging algorithms, cascade correlation has become widely used. This algorithm gives satisfactory results in many applications: the reason for this, however, is still an open problem. In this paper, we prove a theorem which guarantees that the cascade correlation algorithm converges. Moreover, we prove that it has at least a speed of convergence of order O(1/n_h), where n_h is the number of hidden neurons, when approximating a function consisting of a series of sigmoids with a finite number of terms. This guarantees that, in applications where the well- known backpropagation gives a good representation of the training data, cascade correlation is able to obtain very similar results, saving a lot of computer time, as experienced in practice. Computer simulation shows the capability of the cascade correlation algorithm implemented to obtain this convergence speed.     

The design of a real-time neurocomputer based on RBF networks

The design of a real-time neurocomputer (RBF network) subsystem is described. The subsystem is integrated into an avionics system for surveillance and targeting functions. The design of a hardware module based on neurochips that directly support RBF networks, its use for signal peak detection, and the integrated training and testing environment used to train the RBF networks are presented.