基于改进BP神经网络的数字识别

针对BP(Back Propagation)神经网络易陷入局部极小、收敛速度慢的缺点,提出了一种新的BP神经网络改进算法.与标准BP算法比较,该系统通过结合附加动量法和自适应学习速率形成新的BP改进算法.附加动量法虽然可以使BP算法避免陷入局部极小,但是对初始值的选取比较敏感,而且选取合适的学习速率比较困难.而自适应学...     

启发式改进BPNN在模式分类领域内的对比研究

采用附加动量BP算法、自适应最速下降BP算法、自适应动量BP算法、弹性BP算法4种启发式改进方法分别对标准BP算法进行改进,并构建了相应的BP神经网络分类模型,将构建的4种分类模型应用于二维向量模式的分类,并进行了泛化能力测试,将4种BP网络分类模型的分类结果进行对比。仿真结果表明,对于中小规模的网络而言,弹性BP算法改进的BP网络的分类结果最为精确,收敛速度最快,分类性能最优;附加动量BP算法改进的BP网络的分类结果误差最大,收敛速度最慢,分类性能最差;自适应学习速率BP算法改进的BP网络的分类结果的误差值、收敛速度及分类性能介于上述两种算法之间。     

基于改进BP神经网络的模拟电路故障诊断

针对BP神经网络存在的固有缺陷:收敛速度慢,容易陷入局部极小,文中对所建BP网络的学习算法进行了改进,采用附加动量项和自适应调整学习率的BP算法对网络进行训练,替代标准BP算法中的梯度下降法寻找最优网络连接权值.仿真实验证明,这种学习算法提高了BP网络的学习效率及稳定性,大大提高了网络的收敛速度,更好地实现了对模拟电路...     

基于改进BP神经网络的手写字符识别

针对标准反向传播（BP,Back Propagation）神经网络算法收敛速度慢、易陷入局部极小等缺点,采用附加动量法与学习速率自适应调整相结合策略对神经网络初始参数进行设置。通过在权重计算公式中加入动量项,降低神经网络对误差曲面局部调节的敏感性,有效抑制其陷于局部极小。学习速率根据总误差的变化进行自适应调整,可以有效地缩短学习时间,加快收敛速度。将该改进算法应用于数字、英文字母以及简单汉字的手写字符识别系统中,进行了有无动量、有无噪声等实验,结果表明该方法与传统BP算法相比识别精度较高、训练时间较短且具有较强的鲁棒性。     

基于激活函数四参可调的BP神经网络改进算法

为改善BP神经网络的性能,以标准Sigmoidal函数为基础,提出了一种四参数可调的激活函数模型.在学习过程中,它能同时对激活函数的陡度、位置及映射范围进行调节,具有更强的非线性映射能力.并推导出其在BP神经网络中的学习算法.仿真结果显示,改进后的激活函数与传统的标准Sigmoidal函数相比,收敛速度能提高10倍以上,收敛精度误差可减小到传统误差的0.4%以下,而且可以有效地减少隐层的结点数,学习能力可得到较大的提高.     

改进的BP网络算法在图像识别中的应用

采用增加动量因子和自适应学习速率相结合的方法,对BP神经网络算法进行改进,利用改进的BP网络算法,可以有效地抑制网络陷入局部极小值,提高网络训练速度。实验验证表明,改进的算法对图像识别的准确率较高。     

基于改进神经网络的机床刀具故障诊断

针对机床刀具的故障诊断系统进行研究,使用智能人工神经网络算法建立诊断模型。为了提高神经网络模型的训练效率,避免网络陷入局部最优解,使用一种改进的量子神经网络,将附加动量与自适应学习速度方法融合,提高网络收敛效率。使用五轴联动铣床进行刀具故障诊断识别。对声发射信号进行特征提取,使用总振铃技术、总能量、有效电压、事件计数、重心频率、均方根频率以及频率标准方差作为网络的输入向量,判别刀具为新刀、轻微磨损或严重磨损。实验结果表明,使用的改进的量子神经网络的效率以及识别准确度均高于常规BP神经网络。     

基于神经网络的移动机器人多传感器数据融合研究

针对单超声波的测距缺陷,采用多个超声波结合红外开关共同测距,提高整体测量精度;针对BP神经网络训练收敛速度慢,容易陷入局部极小值等缺点,加入动量-自适应因子来改进BP神经网络;将改进的BP应用于移动机器人传感器旅行家II号数据融合中,实践证明,经改进后的BP神经网络收敛精度高误差小,融合后的信息比未经融合的信息更精确。     

基于BP网络的船舶发电机转速控制系统传感器故障诊断

介绍了BP网络用于船舶发电机转速控制系统传感器故障诊断的方法、其中的BP算法用变学习速率和附加动量因子方法进行了改进,用SIMULINK对传感器故障过程进行了仿真诊断．得到的结果说明改进算法对BP网络的收敛速度及陷入局部最小有较大的改善,从而说明了BP网络用于这一领域的有效性。     

基于改进PSO-BP神经网络的教学质量评价模型

教学质量评价是教学研究中的重点之一，但已有的数学评价模型不适合解决非线性问题，神经网络模型收敛速度慢、准确率不高。针对以上问题，文中提出一种基于改进PSO(Particle Swarm Optimization)-BP(Back Propagation)神经网络的教学质量评价模型。通过引入动量和自适应学习率优化BP神经网络，采用惯性权重线性递减、学习因子异步变化，并引入速度收缩因子和自适应变异策略来优化PSO算法；再使用PSO粒子群优化算法计算BP神经网络的初始连接权重和阈值，从而提升模型的全局寻优能力和收敛速度、精度。为验证模型效果，使用评价体系指标层的10个指标数据作为模型的输入，评价结果作为输出，进行模型对比实验。实验结果表明，所提模型的准确率达到96.33%，比一般BP神经网络模型提高4.68%，比自适应BP神经网络模型提高4.07%，比PSO-BP神经网络模型提高1.2%，且收敛曲线平稳，整体性能优于其他模型，说明运用该模型能够有效地对教学质量进行评价。     

两个新的特征提取轨迹网络模型

稀疏轨迹网络利用输入模式时间序列形成类的轨迹,初步实现了空时联合不变性特征提取,但不同类别的轨迹可能重叠,不利于准确分类。本文首先将不同类别轨迹之间的距离等因素引入学习算法,对轨迹调整进行自适应优化,提出一种自适应轨迹神经网络模型：进而从神经元的特性出发,以自适应Ｓｉｇｍｏｉｄ函数包作为激活函数,改善不同类别在特特征空间分布情况,提出一种量子轨迹神经网络模型。模型在任意手写体数字识别上测试了特征提     

A Nonlinear Acoustic Echo Canceller Using Sigmoid Transform in Conjunction With RLS Algorithm

Nonlinearity of amplifiers and/or loudspeakers gives rise to nonlinear echo in acoustic systems, which seriously degrades the performance of speech and audio communications. Many nonlinear acoustic echo cancellation (AEC) methods have been proposed. In this paper, a simple yet efficient nonlinear echo cancellation scheme is presented by using an adaptable sigmoid function in conjunction with a conventional transversal adaptive filter. The new scheme uses the least mean square (LMS) algorithm to update the parameters of sigmoid function and the recursive least square (RLS) algorithm to determine the coefficient vector of the transversal filter. The proposed AEC is proved to be convergent under some mild assumptions. Computer simulations show that the proposed scheme gives a superior echo cancellation performance over the well known Volterra filter approach when the echo path suffers from the saturation-type nonlinear distortion. More importantly, the new AEC has a much lower computational complexity than the Volterra-filter-based method.      

Ad Hoc网络基于TCP吞吐量的速率自适应技术

目前的IEEE 802.11标准在物理层支持多速率传输,但在媒体接入控制(MAC,Media AccessControl)层却没有相应的速率自适应方法。针对目前Ad Hoc网络自适应速率控制方法的不足和在无线通信环境下TCP性能会大幅度恶化,提出了一种改进的MAC层速率自适应协议,该协议实现简单,与传统标准兼容性好,在提高TCP吞吐量的基础上能适应快速变化的无线信道,且能实现分段数据包的速率自适应传输。仿真结果表明,该协议比RBAR协议有更好的吞吐量。     

Reliable adaptive modulation aided by observations of another fading channel

Adaptive transmission techniques, such as adaptive modulation and coding, adaptive power control, adaptive transmitter antenna diversity, etc., generally require precise channel estimation and feedback of channel state information (CSI). For fast vehicle speeds, reliable adaptive transmission also requires long-range prediction of future CSI, since the channel conditions are rapidly time variant. In this paper, we propose using past channel observations of one carrier to predict future CSI and perform adaptive modulation without feedback for another correlated carrier. We derive the minimum mean-square error (MMSE) long-range channel prediction that uses the time- and frequency-domain correlation function of the Rayleigh fading channel. An adaptive MMSE prediction method is also proposed. A statistical model of the prediction error that depends on the frequency and time correlation is developed and is used in the design of reliable adaptive modulation methods. We use a standard stationary fading channel model (Jakes model) and a novel physical channel model to test our algorithm. Significant gains relative to nonadaptive techniques are demonstrated for sufficiently correlated channels and realistic prediction range.     

Image restoration in computed tomography: restoration of experimental CT images

It is pointed out that to restore experimental computed tomography (CT) images which have been blurred by a spatially variant point spread function (PSF), a quadrant symmetry method which simultaneously optimizes storage requirements for the estimated PSFs and computational speed is used. The quadrant symmetry approach required less than 0.579 Megawords of storage for 9x9 pixel spatially variant PSFs in a 256x256 pixel image, allowing image restoration in Cartesian coordinates. A locally adaptive restoration method formulated using a noise prewhitening filter derived from the measured noise power spectrum, the conjugate gradient method was used to obtain a numerical solution. Restored images for a resolution phantom and for a cadaver femur are presented.     

Multiple Model Adaptive Control Procedure for Blood Pressure Control

Multiple model adaptive control procedures have been considered for a computer-based feedback system which regulates the infusion rate of a drug (nitroprusside) in order to maintain desired blood pressure. Because the transfer function parameters are different for each patient, and furthermore are time variant, such an algorithm is desirable for maintaining both steady-state and transient specifications. To this effect, computer simulation has shown that multiple model adaptive control procedures might be successfully applied to the control of blood pressure despite the uncertainty in the delays, time constant, and gains. Additional efforts concerned with the actual demonstration of these concepts on dogs have further supported the role of adaptive control for blood pressure regulation.     

一种基于奇异值谱加权的超声彩色多普勒成像杂波抑制算法

针对超声彩色多普勒成像中由血管或血管周围组织时变运动引起的非平稳杂波抑制问题,提出一种基于奇异值谱加权的杂波抑制算法.首先根据单个慢时方向的回波多普勒矢量构建Hankel数据矩阵并进行奇异值分解,利用分解得到的Hankel主成分构造回归滤波器的正交基函数,同时引入改进的Sigmoid函数根据能量归一化奇异值谱计算回归滤波器系数,使得杂波区域的检测具有高度的特异性,从而提高非平稳杂波的抑制能力.为验证算法的有效性,利用商业级超声仪(Sonix RP,Ultrasonix Inc.)采集50帧人体颈动脉血流基带回波数据并进行滤波处理,滤波后数据采用滞一自相关法估计法计算血流平均速度与功率并进行成像.处理结果表明,与传统静态滤波器以及现有基于特征值分解的滤波算法相比,可有效增强组织空间高强度时变运动时血流与组织的区分能力.     

An adaptive network traffic prediction approach for LDoS attacks detection

Low‐rate denial of service (LDoS) attacks reduce throughput and degrade quality of service (QoS) of network services by sending out attack packets with relatively low average rate. LDoS attack flows are difficult to detect from normal traffic since it has the property of low average rate. The research on network traffic analysis and modeling shows that network traffic measurement data are irregular nonlinear time series. To characterize and analyze network traffic between attack and non‐attack situations, the adaptive normal and abnormal ν‐support vector regression (ν‐SVR) prediction models are constructed on the basis of the reconstructed phase space. In this paper, the dimension of reconstructed phase space for ν‐SVR is optimized by Bayesian information criteria method, and the parameter in the radial basis function is adaptively adjusted by minimizing the within‐class distance and maximizing the between‐class distance in the feature space. The nonthreshold decision function is obtained through calculating the prediction error of adaptive normal and abnormal ν‐SVR prediction models, which is adopted to detect LDoS attacks. Experiments in NS‐2 environment show that the adaptive ν‐SVR prediction model can effectively predict the network traffic measurement time series, and the probability distribution of time series generated by the adaptive ν‐SVR prediction model is quite similar to that of the network traffic measurement data. Experiments also clearly demonstrate the superiority of the proposed approach in LDoS attacks detection.     

SEM algorithm and unsupervised statistical segmentation ofsatellite images

The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the noise. From this one may choose the best context contribution according to the estimated values of the above parameters. The parameter estimation is done by SEM, a densities mixture estimator which is a stochastic variant of the EM (expectation-maximization) algorithm. Another simulation study shows good robustness of the SEM algorithm with respect to different image parameters. Thus, modification of the behavior of the contextual methods, when the SEM-based unsupervised approaches are considered, is limited, and the conclusions of the supervised simulation study stay valid. An adaptive unsupervised method using more relevant contextual features is proposed. Different SEM-based unsupervised contextual segmentation methods, applied to two real SPOT images, give consistently better results than a classical histogram-based method     

基于自适应神经网络的二维线性相位FIR滤波器优化设计

提出一种基于自适应三角函数基神经网络的二维线性相位FIR滤波器优化设计方法.该方法根据二维线性相位FIR滤波器幅频响应特性,采用三角函数基神经网络优化算法计算滤波器系数,同时在神经网络训练过程引入自适应学习率算法,提高神经网络的学习效率和收敛速度.通过训练神经网络的权值,使二维线性相位FIR滤波器幅频响应与理想幅频响应...