ART-2神经网络及其在入侵检测中的应用

在分别对ART-2神经网络和入侵检测原理进行介绍的基础上,指出用ART-2神经网络作为入侵检测系统检测算法的可行性.利用KDD CUP-99数据集对算法进行了Matlab仿真.实验表明,该入侵检测算法可实现较高的检测率和较低的误检率.     

一种提高ART-2神经网络分类器性能的方法

ART神经网络是按照自适应谐振理论建立的一种自组织的人工神经网络。本文通过分析ART神经网络的结构，发现其在用于模式识别中有很好的聚类特性，但是在数据处理过程中有部分数据量丢失的现象，也就是说，非常重要的幅度信息没有被考虑到。本文提出一种新的结构，并成功地把这种结构用到分类器设计中．实验表明新的网络结构用作模式分类时能适应更一般的情况．     

基于ART神经网络的垃圾邮件过滤技术

本文讨论了自适应谐振理论ART,分析了ART的工作原理,给出了ART的具体算法。以神经网络ART作为分类器来过滤垃圾邮件,ART克服了IBP网络的缺点,可以对垃圾邮价进行更有效地过滤,更好的解决了垃圾邮件特征不断变化而过滤方法相对固定的矛盾。并以实例详述了ART在邮件过滤中的工作过程,获得了很好的结果。     

改进ART-2A神经网络在故障自诊断中的应用

ART-2A神经网络可以很好地应用于模式识别中的分类问题,但由于算法结构的不足,存在分类漂移现象,导致网络不稳定,严重影响了网络的工程应用.对标准ART-2A网络结构和算法过程进行了深入研究,分析了引起分类漂移的原因,提出了一种ART-2A神经网络改进算法,并通过故障自诊断实验进行网络稳定性和实用性验证.实验证明改进ART-2A神经网络能长期稳定工作,准确进行故障判别,实现系统的故障诊断自动化.     

一种改进的神经网络自适应控制方法

本文提出了一种改进的神经网络的控制方法，该方法引入一个神经网络辨识器同时作了为神经网络控制器的输出层，从而可以直接通过系统的期望输出和实际输出之差来神经网络控制器的权值，更好地适应对象的非线性和变化。     

基于改进的模糊神经网络自适应控制

为了提高模糊神经网络的运行效率,针对一类离散时间非线性系统,提出了一种优化的模糊神经网络(fuzzy neural network,FNN)自适应控制方法.采用动量梯度下降算法改进模糊神经网络,设计模糊神经网络的参数调整迭代过程,在代价函数中加入正则项,实现参数的更新,提高网络收敛速度以及泛化能力,设计自适应动态控制方...     

一种融合相位估计的深度卷积神经网络语音增强方法

在时频域的语音增强中,幅度估计和相位估计都是影响语音增强性能的重要因素.为了在基于深度学习的语音增强方法中融合对相位的估计,本文将含噪语音短时傅里叶变换（STFT）的实部和虚部特征作为两个通道输入深度卷积神经网络,通过建立一个同步估计纯净语音STFT的实部和虚部特征的多任务学习模型,实现了对幅度和相位的同步估计.实验结果表明,相比仅考虑幅度估计的方法,本文方法具有更好的噪声抑制能力,在低信噪比条件下,显著提高了语音增强性能.     

改进的结构光相位三维测量方法

随着三维测量技术的不断发展,如何快速、精准地测量大场景物体三维形貌成为研究热点。对相位测量轮廓术进行改进,运用改进的相位计算方法对物体三维信息进行测量,并结合幅度信息解决了相位测量轮廓术仅能测量表面信息,但不能确切测出所在物体的位置的问题,该方法适合测量大场景中各物体的三维信息。实验结果表明：所提方法原理简单,对不连续物体的测量结果较好,既可以确定物体位置,也可测量物体表面三维信息。     

模糊信息处理与模糊神经网络

模糊神经网络结合模糊逻辑具有较强的结构性知识表达能力（即描述系统定性知识的能力）,神经网络具有强大的自学习与定量数据的直接处理能力,从而具有一定的处理定性与定量知识的技术和方法。     

基于遗传算法的神经网络自适应控制器的研究

提出了一种基于遗传算法的神经网络自适应控制器的设计方法。该控制器主要由2部分组成，第一部分利用遗传算法搜索出一组神经网络控制器的初始权值，第二部分用历史输入输出数据训练神经网络自适应控制器，经过训练后其达到稳定的控制效果。通过Matlab仿真表明，该控制策略克服了BP算法对初始值敏感的问题，有效提高神经网络的控制效果，和常规PID控制器相比较，超调量小、抗干扰性强和鲁棒性好。     

LOGICAL ANALYSIS FOR NEURAL NETWORKS

By comparison with constraint satisfaction networks, this paper presents an essential frame of the logical theory for continuous-state neural networks, and gives the quantitative analyzing method for contradiction. The analysis indicates that the basic reason for the alternation of the logical states of the neurons is the existence of superior contradiction inside the networks. The dynamic process for a neural network to find a solution corresponds to eliminating the superior contradiction.     

基于神经网络的混沌信号源的设计及同步

该文应用具有全局最优的BP改进算法和神经网络的强大学习能力、逼近任意非线性能力和权值调整的灵活性来优化混沌信号源的设计,采用非线性负反馈实现了神经网络混沌信号源之间的同步。计算机仿真结果表明:由于该模型充分利用了逼近任意非线性能力和网络权值调整的灵活性,比单一混沌映射能产生更多的、具有良好相关性能的混沌信号,且易于同步。     

Adaptive audio streaming in mobile ad hoc networks using neural networks

We design a transport protocol that uses artificial neural networks (ANNs) to adapt the audio transmission rate to changing conditions in a mobile ad hoc network. The response variables of throughput, end-to-end delay, and jitter are examined. For each, statistically significant factors and interactions are identified and used in the ANN design. The efficacy of different ANN topologies are evaluated for their predictive accuracy. The Audio Rate Cognition (ARC) protocol incorporates the ANN topology that appears to be the most effective into the end-points of a (multi-hop) flow, using it to adapt its transmission rate. Compared to competing protocols for media streaming, ARC achieves a significant reduction in packet loss and increased goodput while satisfying the requirements of end-to-end delay and jitter. While the average throughput of ARC is less than that of TFRC, its average goodput is much higher. As a result, ARC transmits higher quality audio, minimizing root mean square and Itakura–Saito spectral distances, as well as several parametric distance measures. In particular, ARC minimizes linear predictive coding cepstral (sic) distance, which closely correlates to subjective audio measures.     

STABILITY OF BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DELAYS

In this paper the globally asymptotic stability of more general two-layer nonlinear feedback associative memory neural networks with time delays is examined. The sufficient conditions of existence, uniqueness and globally asymptotic stability of the equilibrum position are given. Finally, two interesting examples to illustrate the theory are given.     

A NEW METHOD FOR EIGENSTRUCTURES EXTRACTION AND ITS NEURAL NETWORKS IMPLEMENTATION

The cost function for eigenstructures extraction is discussed in detail in this paper, one can obtain the largest eigenvector by minimizing the cost function. In order to obtain other eigenvectors, a covariance matrix series is constructed. If one compares the cost function with the energy function of a neural networks, the neural networks can be easily introduced to extract the eigenvectors. Theoretical analysis and computer simulations show that the proposed method is reasonable and feasible.     

QUALITATIVE ANALYSIS OF BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS

In this paper, the global exponential stability of an equilibrium position for general bidirectional associative memory neural networks are studied. The sufficient conditions of existence and uniqueness of the equilibrium position are given. The method of energy function is examined. Two examples are given to illustrate the theory.     

A data mining method based on constructive neural networks

~~A DATA MINING METHOD BASED ON CONSTRUCTIVE NEURAL NETWORKS[1] Jiawei Han, Micheline Kamber. Data Mining Concept and Techniques. Beijing, Higher Education Press, chapters 1 and 7. [2] Simon Haykin. Neural Networks: A Comprehensive Foundation. 2nd ed. Beijing, Tsinghua University Press, chapters 1, 4, 12 and 14. [3] Zhang Ling, Zhang Bo. A geometrical representation of McCulloch-Pitts neural model and its applications. IEEE Trans, on Neural Networks, 10(19…     

GENERALIZED INVERSE GROUP OF SIGNAL AND ITS IMPLEMENTATION WITH NEURAL NETWORKS

A new concept, the generalized inverse group (GIG) of signal, is firstly proposed and its properties, leaking coefficients and implementation with neural networks are presented. Theoretical analysis and computational simulation have shown that (1) there is a group of finite length of generalized inverse signals for any given finite signal, which forms the GIG; (2) each inverse group has different leaking coefficients, thus different abnormal states; (3) each GIG can be implemented by a grouped and improved single-layer perceptron which appears with fast convergence. When used in deconvolution, the proposed GIG can form a new parallel finite length of filtering deconvolution method. On off-line processing, the computational time is reduced to O(N) from O(N2). And the less the leaking coefficient is, the more reliable the deconvolution will be.     

神经网络指数稳定性分析及收敛率估计

该文通过李雅普诺夫直接方法,研究了一类 Hopfield神经网络平衡点的存在性、唯一性与指数稳定性。文中假设神经网络系统的激励函数为单调增Lipschitz连续函数,在自反馈项为非线性函数的条件下,研究其指数稳定性,同时给出了收敛率估计式。