基于神经网络的异常入侵检测系统

针对神经网络检测器本身的网络结构和算法进行改造可获得好的性能,但无法从根本上解决误报率和漏报率等问题,通过对程序行为的深入研究,对程序行为进行动态建模,提出了一个应用BP神经网络检测器针对程序行为异常的入侵检测模型,从而更准确地发现程序行为的异常。通过Apache服务器为例论证其可行性。     

基于BP神经网络的红外小目标检测

针对红外小目标检测问题,提出一种基于BP(back propagation)神经网络的小目标检测算法。该算法利用BP神经网络的函数逼近特性对红外图像进行背景估计,然后根据背景对消原理消去背景噪声,从而检测到潜在的红外小目标。通过仿真实验证明该算法的有效性。     

Hopfield神经网络在磁粉制动器设计中的应用

为了优化磁粉制动器的结构,提出了Hopfield神经网络的磁粉制动器结构设计方法。方法中利用磁粉制动器的结构建立优化模型,以磁粉制动器的总体积为目标函数,推导约束条件。根据推导的目标函数和约束条件,采用外点罚函数法,构造出优化的增广目标函数,在满足约束条件下,目标函数最小,从而得到磁粉制动器结构的设计方案。实际结果表明,优化后的制动器在满足各项指标的条件下,总体积减小了23%。     

Vision-based aerial image mosaicking algorithm with object detection

Aerial image sequence mosaicking is one of the chal-lenging research fields in computer vision. To obtain large-scale orthophoto maps with object detection info...     

一种新的神经网络重新学习算法

训练样本的获取是神经网络应用中的一个"瓶颈"问题。当发现新的训练样本模式时,现有方法就要重新构造新的神经网络、重新训练,学习时间长而且影响原有记忆。为解决此问题,提出了一种新方法,其基本思想是在原有网络的基础上,增加新的局部神经网络,新网络与原有网络没有链接关系,只包含新的样本模式,而且神经网络重新学习时,只调整局部神经网络。     

视频图像中运动目标的实时检测

提出了一种运动目标检测与跟踪算法。以每点色彩信息的混合高斯模型来实现对视频图像的背景估计,从而实现对运动目标的检测。利用模板匹配的方法实现对运动目标的跟踪,并对混合高斯模型的算法进行了改进,使其能更快、更有效地适应环境的变化。实验结果表明此方法具有较强的鲁棒性,能较好地适应各种气候和光照环境的变化。     

基于多层Hopfield神经网络的配电网网络规划

分析了配电网网络结构规划模型,在此基础上提出用Hopfield神经网络进行网络结构规划.针对城市电网辐射状运行的特点,提出多层Hopfield神经网络模型、对应的能量函数以及参数选择规律.多层Hopfield神经网络的每一层对应于一个负荷点的供电线路,能量函数的建立同时考虑到各层的状态.提出一种新的基于多层Hopfield神经网络的配电网网络结构的规划算法,该算法通过使能量函数降到最低值,可以求得配电网网络规划问题的最优或近似最优解.新算法无需对线路编码、无需对数据进行归一化处理,更加易于编程实现.实例计算表明该方法可行、有效.     

用具有混沌特性的神经网络解任务分配问题

利用由一对相互藉合的混沌吸引子作为神经元构造的混沌神经网络来解决任务分配问题。通过与传统Hopfield人工神经网络解决任务分配问题相比,混沌神经网络具有更强的全局搜索能力和寻优能力。实时分布处理系统任务分配问题实例仿结果表明,该网络解任务分配问题有效地避免了Hopfield人工神经网络极易陷入局部极小的缺陷,并具有更高的搜索效率。     

Tracking maneuvering target based on neural fuzzy network with incremental neural leaning

1 .INTRODUCTIONIn mixing information battle field,it is necessaryto esti mate the targets sport characteristics for i m-proving efficiency of weapons . The military tacticsguided missile defense system and air detectionsystemneed to track andidentify thousands of tar-getsinreal ti me ,the target informationinclude notonly maneuvering target and not maneuvering tar-gets ,but also environment reverberation and falsealarm. These situations take place in accurateweapon launch system, secondary…     

Fuzzy neural network image filter based on GA

A new nonlinear image filter using fuzzy neural network based on genetic algorithm is proposed. The learning of network parameters is performed by genetic algorithm with the efficient binary encoding scheme. In the following, fuzzy reasoning embedded in the network aims at restoring noisy pixels without degrading the quality of fine details. It is shown by experiments that the filter is very effective in removing impulse noise and significantly outperforms conventional filters.     

Robust adaptive neural network control with supervisory controller

The problem of direct adaptive neural network control for a class of uncertain nonlinear systems with unknown constant control gain is studied in this paper. Based on the supervisory control strategy and the approximation capability of multilayer neural networks (MNNs), a novel design scheme of direct adaptive neural network controller is proposed.The adaptive law of the adjustable parameter vector and the matrix of weights in the neural networks and the gain of sliding mode control term to adaptively compensate for the residual and the approximation error of MNNs is determined by using a Lyapunov method. The approach does not require the optimal approximation error to be square-integrable or the supremum of the optimal approximation error to be known. By theoretical analysis, the closed-loop control system is proven to be globally stable in the sense that all signals involved are bounded, with tracking error converging to zero.Simulation results demonstrate the effectiveness of the approach.     

FORECASTING AUTOMOBILE WARRANTY PERFORMANCE IN PRESENCE OF ‘MATURING DATA＇ PHENOMENA USING MULTILAYER PERCEPTRON NEURAL NETWORK

Automobile companies that spend billions of dollars annually towards warranty cost, give high priority to warranty reduction programs. Forecasting of automobile warranty performance plays an important role towards these efforts. The forecasting process involves prediction of not only the specific months-in-service (MIS) warranty performance at certain future time, but also at future MIS values. However, ‘maturing data‘ (also called warranty growth) phenomena that causes warranty performance at specific MIS values to change with time, makes such a forecasting task challenging. Although warranty forecasting methods such as log-log plots and dynamic linear models appear in literature, there is a need for applications addressing the well recognized issue of ‘maturing data‘. In this paper we use an artificial neural network for the forecasting of warranty performance in presence of ‘maturing data‘ phenomena. The network parameters are optimized by minimizing the training and testing errors using response surface methodology. This application shows the effectiveness of neural networks in the forecasting of automobile warranty performance in the presence of the ‘maturing data‘ phenomena.     

Compressive sensing for small moving space object detection in astronomical images

It is known that detecting small moving objects in astronomical image sequences is a significant research problem in space surveillance.The new theory,compressive sensing,provides a very easy and computationally cheap coding scheme for onboard astronomical remote sensing.An algorithm for small moving space object detection and localization is proposed.The algorithm determines the measurements of objects by comparing the difference between the measurements of the current image and the measurements of the background scene.In contrast to reconstruct the whole image,only a foreground image is reconstructed,which will lead to an effective computational performance,and a high level of localization accuracy is achieved.Experiments and analysis are provided to show the performance of the proposed approach on detection and localization.     

水下目标的特征提取及识别

针对水下成像的特殊性以及成像环境的复杂性,构造了基于区域矩的仿射变换不变量,以克服水下不确定因素给目标识别带来的困难。此外针对传统的BP神经网络存在收敛速度慢以及容易陷入局部极小值的缺点,引入粒子群算法对神经网络的学习训练进行优化。为了验证所提方法的有效性,对四类水下目标进行了特征提取以及神经网络识别实验。结果表明改进后的神经网络收敛速度快,并且获得了较高的识别准确率。     

基于RBF神经网络的蜂窝无线定位算法

为了解决最小二乘法需要测量数据的先验信息来构造协方差矩阵的问题,提出了基于RBF神经网络的蜂窝无线定位算法.它融合了移动基站提供的AOA,TOA和TDOA测量值来实现移动台的定位,利用神经网络较快的学习特性和逼近任意非线性映射的能力,使其适用于复杂的多径环境.对基于RBF神经网络的定位系统性能进行了仿真,结果表明,基于REF网络的蜂窝无线定位算法消除了定位模糊和基站非理想分布对定位精度的影响,在小区半径小于2 km的情况下,系统的定位精度在125 m时准确率可达67%,在300 m时准确率可达95%.     

一种神经网络非线性噪声消除方法

针对阶数的增加,Volterra滤波器的滤波系数个数呈几何级数增长,实现困难的问题,提出采用基于Levenberg-Marquardt(LM)算法的BP神经网络逼近Volterra滤波器,实现神经网络非线性滤波,使计算简化。采用的方法是,先离线调整Volterra滤波器的系数,再用调整好的Volterra滤波器监督训练LM-BP神经网络,然后用训练好的LM-BP神经网络进行非线性自适应滤波。仿真实验结果表明,LM-BP神经网络滤波器较其学习导师———Volterra滤波器具有更好的噪声滤除效果。     

基于谱约简的变结构模糊神经网络

在先验知识不完备和不确定的情况下,针对海量数据造成的冗余和互斥,模糊神经网络结构变得复杂化且不能很快逼近和分类输出对象的情况,提出了一种基于高阶谱规则约简的变结构模糊神经网络模型。相同结论属性的模糊规则的条件属性值,可以被认为是由若干个谐波组成的平稳信号,并且此信号可以采用高阶谱分析来估计其谐波成分,规则的最小约简集与谐波对应。在完成了谐波估计后,神经网络结构和连接权值发生改变,神经网络的性能也得到优化。最后给出了此模型在航迹融合中应用的一个例子,得到了较好的结果。     

一种新的基于人工神经网络的综合集成算法

针对现有多目标综合评价中所存在的主观随机性和各种评价方法结果的差异性问题,依据层次分析法(AHP)、主成分分析法(PCA)和人工神经网络(ANN),提出了一种新的从定性到定量转换的综合集成算法,并用于多目标综合评价。该算法基于人工神经网络理论,吸收了层次分析法确定权值的技术和主成分分析法提取主因素的优点,建立了一个新的多目标综合评价模型———AHP PCA ANN模型。介绍了它的组成原理,给出了具体构成方法,描述了各个步骤的主要任务,通过全面质量管理综合评价的实例证明了有效性和可靠性。     

Wavelet neural network based fault diagnosis in nonlinear analog circuits

1 .INTRODUCTIONWith recent advancement in digital signal process-ing and wireless communication, nonlinear analogintegrated circuits , such as logarithmic amplifierand power amplifier and PLL,are being used ag-gressivelyinindustry . Nevertheless ,fault diagno-sis continues to be the bottleneckin reducing ti me-to-market of these ICs . Since the methods whichwere used to diagnose linear analog circuits oftencan’t direaly be used in nonlinear analog circuitsand building nonlinear model is…