A fully automated recurrent neural network for unknown dynamic system identification and control

This paper presents a fully automated recurrent neural network (FARNN) that is capable of self-structuring its network in a minimal representation with satisfactory performance for unknown dynamic system identification and control. A novel recurrent network, consisting of a fully-connected single-layer neural network and a feedback interconnected dynamic network, was developed to describe an unknown dynamic system as a state-space representation. Next, a fully automated construction algorithm was devised to construct a minimal state-space representation with the essential dynamics captured from the input-output measurements of the unknown system. The construction algorithm integrates the methods of minimal model determination, parameter initialization and performance optimization into a systematic framework that totally exempt trial-and-error processes on the selections of network sizes and parameters. Computer simulations on benchmark examples of unknown nonlinear dynamic system identification and control have successfully validated the effectiveness of the proposed FARNN in constructing a parsimonious network with superior performance.     

A vector neural network for emitter identification

This paper proposes a three-layer vector neural network (VNN) with a supervised learning algorithm suitable for signal classification in general, and for emitter identification (EID) in particular. The VNN can accept interval-value input data as well as scalar input data. The input features of the EID problems include the radio frequency, pulse width, and pulse repetition interval of a received emitter signal. Since the values of these features vary in interval ranges in accordance with a specific radar emitter, the VNN is proposed to process interval-value data in the EID problem. In the training phase, the interval values of the three features are presented to the input nodes of VNN. A new vector-type backpropagation learning algorithm is derived from an error function defined by the VNN's actual output and the desired output indicating the correct emitter type of the corresponding feature intervals. The algorithm can tune the weights of VNN optimally to approximate the nonlinear mapping between a given training set of feature intervals and the corresponding set of desired emitter types. After training, the VNN can be used to identify the sensed scalar-value features from a real-time received emitter signal. A number of simulations are presented to demonstrate the effectiveness and identification capability of VNN, including the two-EID problem and the multi-EID problem with/without additive noise. The simulated results show that the proposed algorithm cannot only accelerate the convergence speed, but it can help avoid getting stuck in bad local minima and achieve higher classification rate.     

A dynamic learning neural network for remote sensing applications

The neural network learning process is to adjust the network weights to adapt the selected training data. Based on the polynomial basis function (PBF) modeled neural network that is a modified multilayer perceptrons (MLP) network, a dynamic learning algorithm (DL) is proposed. The presented learning algorithm makes use of the Kalman filtering technique to update the network weights, in the sense that the stochastic characteristics of incoming data sets are implicitly incorporated into the network. The Kalman gains which represent the learning rates of the network weights updating are calculated by using the U-D factorization. By concatenating all of the network weights at each layer to form a long vector such that it can be updated without propagating back, the proposed algorithm improves the performance of convergence to which the backpropagation (BP) learning algorithm often suffers. Numerical illustrations are carried out using two categories of problems: multispectral imagery classification and surface parameters inversion. Results indicates the use of Kalman filtering algorithm not only substantially increases the convergence rate in the learning stage, but also enhances the separability for highly nonlinear boundaries problems, as compared to BP algorithm, suggesting that the proposed DL neural network provides a practical and potential tool for remote sensing applications     

基于神经网络的模数转换电路动态误差源识别系统设计

为提升信号识别电路的电量采集精度,实现理想状态下的电力误差校准,设计基于神经网络的模数转换电路动态误差源识别系统。以CNN神经网络作为模数转换电路的物理依赖环境,通过合理选取动态识别元件的方式,实现误差源识别系统的硬件运行环境搭建。在此基础上,将模拟电流转化成数字信号,再将其完整存储于系统数据库中,利用既定数学运算公式对已存储的数字信号进行识别精度提纯处理,实现误差源识别系统的软件运行环境搭建,联合相关硬件执行设备,完成基于神经网络的模数转换电路动态误差源识别系统设计。实际应用结果表明,在加压环境下,新型误差源识别系统的电量采集精度达到90%,单位时间内的信号识别量超过7.5×109TB,理想状态下信号识别电路的电力误差校准能力得到有效保障。     

A neural network approach to fluid quantity measurement in dynamic environments

Sloshing causes liquid to fluctuate, making accurate level readings difficult to obtain. In this paper, a measurement system has been described that can accurately determine fluid quantity in the presence of slosh. The measurement system uses a single-tube capacitive sensor to obtain instantaneous level of the fluid surface. A neural network based classification technique has been applied to predict the actual quantity of the fluid under sloshing conditions. Effects of temperature variations and contamination on the capacitive sensor have been discussed and it is proposed that these effects can also be eliminated with the proposed neural network based classification system. To examine the performance of the classification system, many field trials were carried out on a running vehicle at various tank volume levels that range from 5 L to 50 L. The paper also investigates the effectiveness of signal enhancement on the neural network based signal classification system. Signal enhancement is performed using selected signal smoothing functions such Moving Mean, Moving Median, and Wavelet filters. Results obtained from the investigation are compared with traditionally used statistical averaging methods, and it proved that the neural network based measurement system can produce highly accurate fluid quantity measurements in a dynamic environment. The approach demonstrated herein will enable a wide range of fluid quantity measurement applications in the fields of automotive, naval and aviation industries to produce accurate fluid level readings.     

A comparative study of neural network structures in identification of nonlinear systems

This paper investigates the identification of nonlinear systems by neural networks. As the identification methods, Feedforward Neural Networks (FNN), Radial Basis Function Neural Networks (RBFNN), Runge–Kutta Neural Networks (RKNN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) based identification mechanisms are studied and their performances are comparatively evaluated on a three degrees of freedom anthropomorphic robotic manipulator.     

A novel traffic identification approach based on multifractal analysis and combined neural network

An accurate identification of Internet traffic of different applications is highly relevant for a broad range of network management and measurement tasks, including traffic engineering, service differentiation, performance monitoring, and security. Traditional traffic identification approaches have become increasingly inaccurate due to restrictions of port numbers, protocol signatures, traffic encryption, and etc. In this paper, a new traffic identification approach based on multifractal analysis of wavelet energy spectrum and classification of combined neural network models is proposed. The proposed approach is able to achieve the identification of different Internet application traffic by performing classification over the wavelet energy spectrum coefficients that were inferred from the original traffic. Without using any payload information, the proposed approach has more advantages over traditional methods. The experiment results illustrate that the proposed approach has satisfactory identification results.     

动态泛回归神经网络预测的研究与仿真

在HUATECA3000过程控制实验系统上选取实验对象,研究了三容水箱液位非线性控制系统,提出了一种动态泛回归神经网络预测控制算法.先后通过开环与闭环控制,搭建了SIMUUNK仿真模型研究算法的有效性.仿真结果表明闭环预测控制改进了系统在干扰作用下的稳态和动态性能.     

User identification via neural network based language models

Identifying compromised accounts on online social networks that are used for phishing attacks or sending spam messages is still one of the most challenging problems of cyber security. In this research, the authors explore an artificial neural network‐based language model to differentiate the writing styles of different users on short text messages. In doing so, the aim is to be able to identify compromised user accounts. The results obtained indicate that one can learn the language model on one dataset and can generalize it to different datasets to identify users with high accuracy and low false alarm rates without any modification to the language model.     

基于模糊神经网络的目标识别

结合模糊推理和神经网络两种方法的优点,从网络的结构、工作过程、学习算法等方面,探讨了一种基于模糊神经网络(FNN)的目标识别方法。通过仿真结果证明,此方法确实可行。     

A multilayer complex neural network training algorithm and its application in adaptive equalization

In this paper, the layer-by-layer optimizing algorithm for training multilayer neural network is extended for the case of a multilayer neural network whose inputs, weights, and activation functions are all complex. The updating of the weights of each layer in the network is based on the recursive least squares method. The performance of the proposed algorithm is demonstrated with application in adaptive complex communication channel equalization.     

一种信号调制识别网络的轻量化设计

神经网络在信号调制识别领域得到了广泛关注和研究。针对现有调制识别算法为提高识别准确率,导致模型尺寸过大、计算时间过长的问题,提出了一种调制识别神经网络的轻量化设计方案。该方案由信号失真校正模块和分类模块两部分组成。其中,信号失真校正模块通过参数估计器提取相位偏移信息,再经参数转换器对相位偏移进行参数校正,保证信号识别精度;分类模块由一维卷积神经网络(One-Dimensional Convolutional Neural Network, 1D-CNN)、选通递归单元(Gated Recurrent Unit, GRU)和高斯衰减层构成,从时间和空间的角度有效提取信号特征,并减少冗余参数量以缩减模型大小。仿真结果表明,所提方案与同精度网络相比,平均识别准确率提升0.21%,计算时间缩减到1/3.4,模型尺寸缩减到1/7.77。     

基于动态BP神经网络的财务危机预警算法研究

为进一步提升模型合理性和预测结果准确度,充分考虑公司财务情况历史值的影响,通过对不同时期的财务面板数据赋以不同权重,设计提出了一种基于Logit-动态BP神经网络的财务危机预警机制。实证结果显示,基于面板数据的新模型能更好地体现财务危机的发生机理,因而具备良好预警精度;在对财务危机公司及财务正常公司预警实验中,其预测性能均优于现有Logit回归分析模型和传统神经网络模型。     

基于残差神经网络的无人机射频信号识别

针对民用小型无人机对低空领域安全造成威胁及无人机视觉上识别难的问题,提出了一种无人机射频信号识别的方法,使用深度学习技术学习无人机与控制器之间的射频信号特征来识别无人机。首先将射频信号数据集中的无人机信号进行预处理操作,接着使用残差神经网络进行模型训练,最后使用训练好的网络模型对无人机信号进行识别验证。实验结果表明,该方法识别无人机是否存在的准确率达到99.8%,识别无人机型号的准确率达到91.1%,识别无人机运行模式的准确率达到70.3%,且该方法具备较强的鲁棒性和环境抗干扰能力,性能明显优于基准方法。     

Two-stage neural network architecture for feedback control of dynamic systems

In this paper we investigate system identification and the design of a controller using neural networks. A two-stage neural network design for controllers using single-layer structures with functional enhancements is introduced. This neural network architecture allows the design of a controller with less a priori knowledge about the plant as well as allowing for nonlinear plants. The paper also addresses the special characteristics and problems concerning the use of neural networks in control and demonstrates their performance by showing the successful implementation of a nonlinear control example via simulation.Christop Müller-Dott was a Fulbright Scholar with the Department of Electrical Engineering.     

忆阻自突触Hopfield神经网络的动力学分析与电路仿真

通过理论分析和仿真的方法,研究了一种4维忆阻自突触Hopfiled神经网络(以下简称MAHNN)的动力学行为及其仿真电路的实现.首先,分析了MAHNN能够产生复杂动力学行为的基本条件.其次,利用常规的动力学分析方法如分岔图、李氏指数、相轨迹图和时域图,分析了它的动力学行为.MATLAB数值仿真结果揭示了MAHNN存在与...     

基于星座图和卷积神经网络的射频指纹识别

基于无线设备物理层的射频指纹识别是保障通信安全的有效途径。传统射频特征提取方法容易受到信道的信噪比变化的干扰,难以适应动态信噪比下的通信场景。因此,本文提出了一种基于卷积神经网络的射频指纹识别方法,实现了动态信噪比下的射频指纹识别,显著改善了低信噪比下的识别准确率。本文通过搭建实验系统对4台不同功放设备进行识别,实验结果表明,在信噪比为0.5～14.5 dB范围内,该方法的综合识别率达89.4%。     

Research and application of a neural network classifier based on dynamic threshold

In this study, a Multi-Layer BP neural network (MLBP) with dynamic thresholds is em-ployed to build a classifier model. As to the design of the neural network structure, theoretical guidance and plentiful experiments are combined to optimize the hidden layers’ parameters which include the number of hidden layers and their node numbers. The classifier with dynamic thresholds is used to standardize the output for the first time, and it improves the robustness of the model to a high level. Finally, the classifier is applied to forecast box office revenue of a movie before its theatrical release. The comparison results with the MLP method show that the MLBP classifier model achieves more satis-factory results, and it is more reliable and effective to solve the problem.     

复数Hopfield神经网络盲均衡QAM信号

为了解决复数多值信号的盲均衡问题,本文提出了基于复数Hopfield神经网络盲均衡多值信号的方法:将基于Hopfield神经网络的盲均衡算法从实数域推广到复数域.在复数域成功构造了复数Hopfield神经网络,重点针对16QAM信号进行盲均衡.并验证了此系统可以处理非统计量字符,即处理16QAM信号的Hopfield神...     

GRAIL: a multi-agent neural network system for gene identification

Identifying genes within large regions of uncharacterized DNA is a difficult undertaking and is currently the focus of many research efforts. We describe a gene localization and modeling system, called GRAIL. GRAIL is a multiple sensor-neural network-based system. It localizes genes in anonymous DNA sequence by recognizing features related to protein-coding regions and the boundaries of coding regions, and then combines the recognized features using a neural network system. Localized coding regions are then “optimally” parsed into a gene model. Through years of extensive testing GRAIL consistently achieves about 90% of coding portions of test genes with a false positive rate of about 10% A number of genes for major genetic diseases have been located through the use of GRAIL, and over 1000 research laboratories worldwide use GRAIL on regular bases for localization of genes on their newly sequenced DNA