基于头脑风暴优化算法的BP神经网络模糊图像复原

该文提出一种基于头脑风暴智能优化算法的BP神经网络模糊图像复原方法(OBSO-BP)。该方法在聚类和变异两方面优化了头脑风暴智能算法,利用头脑风暴优化算法易于解决多峰高维函数问题的特点,自动搜寻BP神经网络更佳的初始权值和阈值,以减少BP网络对其初始权值和阈值的敏感性,避免网络陷入局部最优解,增加网络的收敛速度,减小网络误差,提高图像还原质量。该文采用20张不同的图像,对其模糊图像分别进行维纳滤波复原(Wiener)、基于头脑风暴算法的维纳滤波复原(Wiener-BSO)、BP神经网络复原以及基于头脑风暴算法的BP神经网络(BSO-BP)图像复原实验。实验结果表明,该方法能够取得更好的图像复原效果。     

Cloud security situation prediction method based on grey wolfoptimization and BP neural network

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed.Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve theconvergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the positionupdate formula of GWO algorithm, which is used to select the features of the cloud security situation prediction dataand optimize the parameters of the BP neural network prediction model to minimize the prediction output error.Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm toincrease the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloudplatform are predicted. The simulation results show that the proposed method has lower mean square error (MSE)and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm(GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based onGWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.     

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...     

BPNN辅助KF的MEMS陀螺仪数据处理方法

针对微机电系统(MEMS)陀螺仪数据误差建模不精确或无法给出模型的情况,提出了误差反馈（BP）神经网络辅助卡尔曼滤波对陀螺仪数据进行降噪处理的方法。分析卡尔曼滤波器的系统噪声方差Q矩阵可知,当模型不精确时可通过Q补偿。基于BP神经网络优化Q值原理,首先把采集到的MEMS陀螺仪数据输入卡尔曼滤波器得到Q;再把新息、滤波增益、量测噪声方差输入神经网络,把Q作为神经网络的输出,神经网络优化系统噪声协方差矩阵得到Q*;最后将Q*作为卡尔曼滤波算法系统噪声方差矩阵。实验结果表明,在建模不精确的情况下该方法也能有效提高陀螺仪的精度。     

Fluctuation analysis of a two-layer backpropagation algorithm usedfor modeling nonlinear memoryless channels

Neural networks have been used to model the nonlinear characteristics of memoryless nonlinear channels using the backpropagation learning (BP) with experimental training data. The mean transient and convergence behavior of a simplified two-layer neural network has been studied previously in order to better understand this neural network application. The network was trained with zero mean Gaussian data. This paper extends these results to include the effects of the weight fluctuations on the mean square error (MSE). A new methodology is presented that can be extended to other nonlinear learning problems. The new mathematical model is able to predict the MSE learning behavior as a function of the algorithm step size μ. The performance analysis is based on the derivation of linear recursions for the variance and covariance of the weights that depend nonlinearly on the mean weights. These linear recursions can be used to predict the local mean-square stability of the weights. As in linear gradient search problems (LMS, etc.), it is shown that there exists an optimum p (minimizing the MSE), which is the result of the tradeoff between fast learning and small weight fluctuations. Monte Carlo simulations display excellent agreement between the actual behavior and the predictions of the theoretical model over a wide range of μ values     

用于电力数据管理分析的负荷预测与异常检测

构建了一个电力数据管理分析系统,并设计了电力负荷预测算法和异常数据检测算法问题.首先,针对BP神经网络在预测电力负荷存在的因初始权值与阈值设置影响估计精度的问题,提出利用粒子群优化BP神经网络网络参数,提高了预测算法的收敛速度与预测精度;然后,针对电力数据异常检测算法效率较低的问题,提出了基于改进谱聚类的异常数据检测算...     

Statistical analysis of a two-layer backpropagation algorithm usedfor modeling nonlinear memoryless channels: the single neuron case

Neural networks have been used for modeling the nonlinear characteristics of memoryless nonlinear channels using backpropagation (BP) learning with experimental training data. In order to better understand this neural network application, this paper studies the transient and convergence properties of a simplified two-layer neural network that uses the BP algorithm and is trained with zero mean Gaussian data. The paper studies the effects of the neural net structure, weights, initial conditions, and algorithm step size on the mean square error (MSE) of the neural net approximation. The performance analysis is based on the derivation of recursions for the mean weight update that can be used to predict the weights and the MSE over time. Monte Carlo simulations display good to excellent agreement between the actual behavior and the predictions of the theoretical model     

用神经网络实现VBR视频通信量的在线预测

VBR(Varible Bit Rate)视频信号具有时变性、非线性和突发性等特点,实现该信号通信量的高精度预测难度较大.针对以上问题,本文提出了一种用于VBR视频通信量预测的自适应神经网络模型,网络训练采用离线与在线相结合的方式,同时通过删除不重要的权重,以优化网络的拓扑结构,提高网络的推广能力,降低网络在线学习的计算复杂度;对VBR视频通信量预测的模拟结果表明该模型具有高的预测精度,并能满足通信系统对预测实时性的要求.     

基于粒子群优化的神经网络训练算法研究

本文提出了基于连接结构优化的粒子群优化算法(SPSO)用于神经网络训练,该算法在训练神经网络权值的同时优化其连接结构,删除冗余连接,使神经网络获得与模式分类问题匹配的信息处理能力.经SPSO训练的神经网络应用于Iris,Ionosphere以及Breast cancer模式分类问题,能够部分消除冗余分类参数及冗余连接结构对分类性能的影响.与BP算法及遗传算法比较,该算法在提高分类误差精度的同时可加快训练收敛的速度.仿真结果表明,SPSO是有效的神经网络训练算法.     

基于BP神经网络的飞行参数估测方法

对传统BP神经网络算法中收敛速度慢和存在局部极小点的问题进行了研究，提出了网络结构的改进方案和优化算法，提高了网络学习速度和预测精度；应用到飞行参数估测问题中，具有算法稳定、估测精确和动态自适应的特点。     

Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels

Recurrent neural networks have been successfully applied to communications channel equalization because of their modeling capability for nonlinear dynamic systems. Major problems of gradient-descent learning techniques commonly employed to train recurrent neural networks are slow convergence rates and long training sequences required for satisfactory performance. This paper presents decision-feedback equalizers using a recurrent neural network trained with Kalman-filtering algorithms. The main features of the proposed recurrent neural equalizers, using the extended Kalman filter and the unscented Kalman filter, are fast convergence and good performance using relatively short training symbols. Experimental results for various time-varying channels are presented to evaluate the performance of the proposed approaches over a conventional recurrent neural equalizer.     

A real-time learning algorithm for a multilayered neural networkbased on the extended Kalman filter

A novel real-time learning algorithm for a multilayered neural network is derived from the extended Kalman filter (EKF). Since this EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights, the convergence performance is improved in comparison with the backwards error propagation algorithm using the steepest descent techniques. Furthermore, tuning parameters which crucially govern the convergence properties are not included, which makes its application easier. Simulation results for the XOR and parity problems are provided     

基于PSO-BP算法的无线传感器网络定位优化

在研究现有定位算法的基础上,针对基于接收信号强度指示(RSSI)定位模型中的参数易受环境影响等问题,提出了一种新型的粒子群优化(PSO)算法与后向传播(BP)神经网络相结合的算法.BP网络算法权值的修正依赖于非线性梯度值,易形成局部极值,同时学习次数较多,需先通过粒子群算法进行优化.为了提高定位精度,首先采用速度常量法滤波处理,然后通过改进的混合优化算法对BP神经网络初始权值和阈值进行优化,并分析算法的性能.试验中隐层节点个数采用试错法,从12到19变化,以确定合适数目.实验结果表明,与一般加权算法和传统BP算法相比,改进的混合优化算法可大幅改善测距误差对定位误差的影响,同时可使25 m内最小定位误差小于0.27 m.     

基于遗传神经网络的AOA跟踪算法

提出了一种在非视距传播环境中基于遗传神经网络的到达角定位跟踪算法。首先使用遗传算法优化后向传播神经网络的初始权值,将优化后的GA-BP神经网络对AOA测量值进行修正,用最小二乘算法确定移动台的位置,再用卡尔曼滤波器配合相关检测距离门对移动台实施跟踪。仿真结果表明,该算法能有效地实现移动台的动态跟踪,且性能优于传统BP神经网络和LS算法。     

基于萤火虫BP神经网络的轴承故障诊断研究

针对BP神经网络训练过程易陷入局部极值导致训练误差收敛速度慢的问题,提出将具有全局寻优的萤火虫算法,结合BP算法共同训练神经网络。在本质上,萤火虫BP神经网络利用萤火虫算法对神经网络进行早期训练,避开局部极值点,得到优化后的神经网络初始权值后,利用BP算法的局部寻优特性对网络做进一步精细训练。轴承故障实验表明,萤火虫BP神经网络的训练误差收敛速度相比BP神经网络、萤火虫神经网络显著提升,故障识别率最高达到99.47%。     

基于CMAC的卡尔曼滤波技术在组合导航系统中的应用

经典卡尔曼滤波器要求假设系统的动态模型和观测模型的噪声统计特性已知,而组合导航系统的噪声具有非先验性。为了解决这一问题,提出小脑模型神经网络（CMAC）辅助卡尔曼滤波器。仿真试验结果表明,该辅助算法的精度与经典卡尔曼滤波算法相比提高了2倍,收敛时间缩短近200 s,并有效地克服了传统神经网络学习速度慢,泛化能力弱的缺点,使系统具有自适应能力,以应付动态环境的扰动。     

Parallel,self-organizing,hierarchical neural networks with forward-backward training

A forward-backward training algorithm for parallel, self-organizing hierarchical neural networks (PSHNNs) is described. Using linear algebra, it is shown that the forward-backward training of ann-stage PSHNN until convergence is equivalent to the pseudo-inverse solution for a single, total network designed in the least-squares sense with the total input vector consisting of the actual input vector and its additional nonlinear transformations. These results are also valid when a single long input vector is partitioned into smaller length vectors. A number of advantages achieved are: small modules for easy and fast learning, parallel implementation of small modules during testing, faster convergence rate, better numerical error-reduction, and suitability for learning input nonlinear transformations by other neural networks. The backpropagation (BP) algorithm is proposed for learning input nonlinearitics. Better performance in terms of deeper minimum of the error function and faster convergence rate is achieved when a single BP network is replaced by a PSHNN of equal complexity in which each stage is a BP network of smaller complexity than the single BP network.     

Direction of arrival estimation based on phase differences usingneural fuzzy network

A new high-resolution direction of arrival (DOA) estimation technique using a neural fuzzy network based on phase difference (PD) is proposed. The conventional DOA estimation method such as MUSIC and MLE, are computationally intensive and difficult to implement in real time. To attack these problems, neural networks have become popular for DOA estimation. However, the normal neural networks such as the multilayer perceptron (MLP) and radial basis function network (RBFN) usually produce the extra problems of low convergence speed and/or large network size (i.e., the number of network parameters is large). Also, the may to decide the network structure is heuristic. To overcome these defects and take use of neural learning ability, a powerful self-constructing neural fuzzy inference network (SONFIN) is used to develop a new DOA estimation algorithm. By feeding the PDs of the received radar-array signals, the trained SONFIN can give high-resolution DOA estimation. The proposed scheme is thus called PD-SONFIN. This new algorithm avoids the need of empirically determining the network size and parameters in normal neural networks due to the powerful on-line structure and parameter learning ability of SONFIN. The PD-SONFIN can always find itself an economical network size in the fast learning process. Our simulation results show that the performance of the new algorithm is superior to the RBFN in terms of convergence accuracy, estimation accuracy, sensitivity to noise, and network size     

采用进化计算的BP神经网络学习算法研究

针对ＢＰ神经网络中存在的局部极小问题,本文提出了采用进化计算方法改进ＢＰ学习算法收敛速度的新方法,理论分析和数字仿真表明算法有很好的效果。     

遗传算法优化BP神经网络的大功率LED结温预测

将遗传算法(GA)与BP神经网络相结合,对研发的120W LED双进双出的射流冲击水冷散热系统中LED阵列的结温进行预测。采用GA优化BP网络的权值和阈值,利用BP算法训练网络,改善了单独使用BP网络容易陷入局部极小值和收敛速度慢的缺点。并且在训练过程中为了使网络输出有足够长的空间,改进了GA的数据处理。结果表明,经GA优化的BP神经网络较使用Levenberg-Marquardt(LM)算法优化的BP神经网络的大功率LED结温预测精确度提高了14.14%,且预测效果较稳定。GA和BP神经网络相结合的结温预测模型较传统的结温测量方法更能掌握散热结构设计的主动性,对大功率LED寿命的延长有较高的实用价值。