Application of Hybrid Learning Neural Fuzzy Systems in Reliability Prediction

This study presents a hybrid learning neural fuzzy system for accurately predicting system reliability. Neural fuzzy system learning with and without supervision has been successfully applied in control systems and pattern recognition problems. This investigation modifies the hybrid learning fuzzy systems to accept time series data and therefore examines the feasibility of reliability prediction. Two neural network systems are developed for solving different reliability prediction problems. Additionally, a scaled conjugate gradient learning method is applied to accelerate the training in the supervised learning phase. Several existing approaches, including feed‐forward multilayer perceptron (MLP) networks, radial basis function (RBF) neural networks and Box–Jenkins autoregressive integrated moving average (ARIMA) models, are used to compare the performance of the reliability prediction. The numerical results demonstrate that the neural fuzzy systems have higher prediction accuracy than the other methods. Copyright © 2005 John Wiley & Sons, Ltd.     

A Neural Network Approach to Find The Cumulative Failure Distribution: Modeling and Experimental Evidence

The failure prediction of components plays an increasingly important role in manufacturing. In this context, new models are proposed to better face this problem, and, among them, artificial neural networks are emerging as effective. A first approach to these networks can be complex, but in this paper, we will show that even simple networks can approximate the cumulative failure distribution well. The neural network approach results are often better than those based on the most useful probability distribution in reliability, the Weibull. In this paper, the performances of multilayer feedforward basic networks with different network configurations are tested, changing different parameters (e.g., the number of nodes, the learning rate, and the momentum). We used a set of different failure data of components taken from the real world, and we analyzed the accuracy of the approximation of the different neural networks compared with the least squares method based on the Weibull distribution. The results show that the networks can satisfactorily approximate the cumulative failure distribution, very often better than the least squares method, particularly in cases with a small number of available failure times. Copyright © 2015 John Wiley & Sons, Ltd.     

基于径向基函数神经网络的滚动轴承故障模式的识别

径向基函数（RBF）神经网络是一种3层前馈性神经网络，它具有较强的函数逼近能力和分类能力。鉴于径向基函数神经网络的优点，在对滚动轴承振动信号特征分析的基础上，提出了采用时序方法对其建立AR模型，利用AR模型参数建立径向基函数神经网络，并用该网络对滚动轴承的故障模式进行了识别。理论和试验证明了该方法的有效性，且具有较高的识别精度。     

Feedforward Control Based on Neural Networks for Hard Disk Drives

We present a novel feedforward control based on neural networks to attenuate the effect of external vibrations on the positioning accuracy of hard disk drives. The neural network compensator, which is an add-on function on top of nominal feedback control, uses the accelerometer signals obtained from a sensor to detect external vibrations. Our feedforward control can be regarded as a nonlinear finite impulse response (FIR) that corresponds to linear FIR when the basis function of the neural network is linear. By neural network learning, the tracking performance of hard disk drives can be improved with no information on disturbance dynamics or sensor model. We have analyzed the stability of the proposed scheme by the Lyapunov criterion. Here, we give simulation results to demonstrate that our control scheme can eliminate the effect of external disturbances on positioning accuracy.      

Cascaded linear shift-invariant processors in optical pattern recognition

We study a cascade of linear shift-invariant processing modules (correlators), each augmented with a nonlinear threshold as a means to increase the performance of high-speed optical pattern recognition. This configuration is a special class of multilayer, feed-forward neural networks and has been proposed in the literature as a relatively fast best-guess classifier. However, it seems that, although cascaded correlation has been proposed in a number of specific pattern recognition problems, the importance of the configuration has been largely overlooked. We prove that the cascaded architecture is the exact structure that must be adopted if a multilayer feed-forward neural network is trained to produce a shift-invariant output. In contrast with more generalized multilayer networks, the approach is easily implemented in practice with optical techniques and is therefore ideally suited to the high-speed analysis of large images. We have trained a digital model of the system using a modified backpropagation algorithm with optimization using simulated annealing techniques. The resulting cascade has been applied to a defect recognition problem in the canning industry as a benchmark for comparison against a standard linear correlation filter, the minimum average correlation energy (MACE) filter. We show that the nonlinear performance of the cascade is a significant improvement over that of the linear MACE filter in this case.     

Application of chaotic noise reduction techniques to chaotic data trained by ANN

We propose a novel method of combining artificial neural networks (ANNs) with chaotic noise reduction techniques that captures the metric and dynamic invariants of a chaotic time series, e.g. a time series obtained by iterating the logistic map in chaotic regimes. Our results indicate that while the feedforward neural network is capable of capturing the dynamical and metric invariants of chaotic time series within an error of about 25%, ANNs along with chaotic noise reduction techniques, such as Hammel’s method or the local projective method, can significantly improve these results. This further suggests that the effort on the ANN to train data corresponding to complex structures can be significantly reduced. This technique can be applied in areas like signal processing, data communication, image processing etc.     

Neural-network-based models of 3-D objects for virtualized reality: a comparative study

The paper presents a comprehensive analysis and comparison of the representational capabilities of three neural architectures for three-dimensional (3-D) object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation, and potential applications in the context of virtualized reality. Starting from a pointcloud that embeds the shape of the object to be modeled, a volumetric representation is obtained using a multilayer feedforward neural network (MLFFNN) or a surface representation using either the self-organizing map (SOM) or the neural gas network. The representation provided by the neural networks (NNs) is simple, compact, and accurate. The models can be easily transformed in size, position, and shape. Some potential applications of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of object collision, and for object recognition, object motion estimation, and segmentation.     

Robust recurrent neural network modeling for software fault detection and correction prediction

Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set.     

实现CDMA最佳多用户检测的神经网络方法

提出并讨论了两种实现码分多址系统中最佳多用户检测的神经网络方法。一种基于离散Ｈｏｐｆｉｅｌｄ神经网络，另一种基于采用反向传播算法的多层感知器神经网络。理论分析和计算机模拟都证实了这两种神经网络方法的可行性，优越性和实用性。前者适用“固定”用户情况；后者既可用于“固定”用户吼适用于移动用户的情况，因而在未来的ＣＤＭＡ个人通信网中有较好的应用前景。     

Use of neural networks and expert systems to control a gas/solid sorption chilling machine: Utilisation des réseaux neuronaux et des systèmes experts pour réguler une machine frigorifique à sorption gaz/solide

This works focuses on using neural networks and expert systems to control a gas/solid sorption chilling machine. In such systems, the cold production changes cyclically with time due to the batchwise operation of the gas/solid reactors. The accurate simulation of the dynamic performance of the chilling machine has proven to be difficult for standard computers when using deterministic models. Additionally, some model parameters dynamically change with the reaction advancement. A new modelling approach is presented here to simulate the performance of such systems using neural networks. The backpropagation learning rule and the sigmoid transfer function have been applied in feedforward, full connected, single hidden layer neural networks. Overall control of this system is divided in three blocks: control of the machine stages, prediction of the machine performance and fault diagnosis.     

Computer-aided Prediction of the ZrO2 Nanoparticles’ Effects on Tensile Strength and Percentage of Water Absorption of Concrete Specimens

In the present paper,two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing ZrO2 nanoparticles have been developed at different ages of curing.For building these models,training and testing using experimental results for 144 specimens produced with 16 different mixture proportions were conducted.The data used in the multilayer feed forward neural networks models and input variables of genetic programming models were arranged in a format of eight input parameters that cover the cement content,nanoparticle content,aggregate type,water content,the amount of superplasticizer,the type of curing medium,age of curing and number of testing try.According to these input parameters,in the neural networks and genetic programming models,the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles were predicted.The training and testing results in the neural network and genetic programming models have shown that two models have strong potential for predicting the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles.It has been found that neural network(NN) and gene expression programming(GEP) models will be valid within the ranges of variables.In neural networks model,as the training and testing ended when minimum error norm of network gained,the best results were obtained and in genetic programming model,when 4 genes were selected to construct the model,the best results were acquired.Although neural network have predicted better results,genetic programming is able to predict reasonable values with a simpler method rather than neural network.     

基于注意力模型的多传感器人类活动识别

深度循环神经网络适用于处理时间序列数据, 然而循环神经网络特征提取能力差, 时间依赖关系挖掘不足。针对此问题, 提出了3种注意力机制和长短时记忆(LSTM)神经网络结合的模型用于人类活动识别问题, 并研究了3种注意力机制在不同数据集上单独及配合使用时对模型精度的影响。对于UCI_HAR数据集, 3种注意力LSTM模型准确率分别为94.13%、95.15%和94.81%,高于LSTM模型识别准确率93.2%。此外, 针对人类活动识别的传感器时间序列数据的标签特点, 提出将时间段分类任务转化为分割任务, 设计了2个基于分割任务的注意力门控循环单元(GRU)神经网络模型, Bahdanau注意力GRU模型在Skoda数据集和机会(Oppor)数据集准确率为84.61%和89.54%, 高于基准UNet模型的70.40%和88.51%。     

爆破优化的神经网络模型

文章在简要阐述了前馈多层神经网络及其反传算法一般原理的基础上,建立了露天矿爆破效果预测的人工神经网络模型,进而提出了基于神经网络的爆破参数分段优化模型。     

爆破优化的神经网络模型

文章在简要阐述了前馈多层神经网络及其反传算法一般原理的基础上，建立了露天矿爆破效果预测的人工神经网络模型，进而提出了基于神经网络的爆破参数分段优化模型。     

Novel DDoS Feature Representation Model Combining Deep Belief Network and Canonical Correlation Analysis

Distributed denial of service (DDoS) attacks launch more and more frequently and are more destructive. Feature representation as an important part of DDoS defense technology directly affects the efficiency of defense. Most DDoS feature extraction methods cannot fully utilize the information of the original data, resulting in the extracted features losing useful features. In this paper, a DDoS feature representation method based on deep belief network (DBN) is proposed. We quantify the original data by the size of the network flows, the distribution of IP addresses and ports, and the diversity of packet sizes of different protocols and train the DBN in an unsupervised manner by these quantified values. Two feedforward neural networks (FFNN) are initialized by the trained deep belief network, and one of the feedforward neural networks continues to be trained in a supervised manner. The canonical correlation analysis (CCA) method is used to fuse the features extracted by two feedforward neural networks per layer. Experiments show that compared with other methods, the proposed method can extract better features.     

基于机器学习的电喷印精度预测方法研究

目的 节省电流体喷射打印精度预测的时间和解决电流体工艺参数的选择问题,达到提高电流体打印的质量和效率的目的。方法 为了对电流体喷射打印精度进行预测,提出有限元模型与机器学习相结合的方法。基于线性回归、支持向量回归和神经网络等机器学习算法建立4种参数与射流直径的关系模型。结果 算法结果表明:支持向量回归和神经网络预测模型的决定系数R²能达到0.9以上,表示模型可信度高;支持向量回归和神经网络预测模型指标都比线性回归预测模型的小。结论 机器学习算法可对电喷印打印精度进行有效预测,预测效率提高了十几倍,节省了精度预测的时间。     

旋转机械故障诊断的神经网络方法研究

BP神经网络具有较好的非线性映射能力,可以描述频率特征和故障之间的关系,而概率神经网络学习规则简单、训练速度快、避免局部极小和反复训练的问题。根据两种神经网络的原理选择合适的参数建立两个旋转机械故障诊断模型,并利用模型对某旋转机械的故障数据进行处理,结果显示两种网络在故障诊断方面的实用价值。通过对故障数据的结果对比可以看到PNN网络比BP网络具有更好的容错能力。     

Lung cancer prediction from microarray data by gene expression programming

Lung cancer is a leading cause of cancer‐related death worldwide. The early diagnosis of cancer has demonstrated to be greatly helpful for curing the disease effectively. Microarray technology provides a promising approach of exploiting gene profiles for cancer diagnosis. In this study, the authors propose a gene expression programming (GEP)‐based model to predict lung cancer from microarray data. The authors use two gene selection methods to extract the significant lung cancer related genes, and accordingly propose different GEP‐based prediction models. Prediction performance evaluations and comparisons between the authors’ GEP models and three representative machine learning methods, support vector machine, multi‐layer perceptron and radial basis function neural network, were conducted thoroughly on real microarray lung cancer datasets. Reliability was assessed by the cross‐data set validation. The experimental results show that the GEP model using fewer feature genes outperformed other models in terms of accuracy, sensitivity, specificity and area under the receiver operating characteristic curve. It is concluded that GEP model is a better solution to lung cancer prediction problems.Inspec keywords: lung, cancer, medical diagnostic computing, patient diagnosis, genetic algorithms, feature selection, learning (artificial intelligence), support vector machines, multilayer perceptrons, radial basis function networks, reliability, sensitivity analysisOther keywords: lung cancer prediction, cancer‐related death, cancer diagnosis, gene profiles, gene expression programming‐based model, gene selection, GEP‐based prediction models, prediction performance evaluations, representative machine learning methods, support vector machine, multilayer perceptron, radial basis function neural network, real microarray lung cancer datasets, cross‐data set validation, reliability, receiver operating characteristic curve     

UFC-Net with Fully-Connected Layers and Hadamard Identity Skip Connection for Image Inpainting

Image inpainting is an interesting technique in computer vision and artificial intelligence for plausibly filling in blank areas of an image by referring to their surrounding areas. Although its performance has been improved significantly using diverse convolutional neural network (CNN)-based models, these models have difficulty filling in some erased areas due to the kernel size of the CNN. If the kernel size is too narrow for the blank area, the models cannot consider the entire surrounding area, only partial areas or none at all. This issue leads to typical problems of inpainting, such as pixel reconstruction failure and unintended filling. To alleviate this, in this paper, we propose a novel inpainting model called UFC-net that reinforces two components in U-net. The first component is the latent networks in the middle of U-net to consider the entire surrounding area. The second component is the Hadamard identity skip connection to improve the attention of the inpainting model on the blank areas and reduce computational cost. We performed extensive comparisons with other inpainting models using the Places2 dataset to evaluate the effectiveness of the proposed scheme. We report some of the results.     

基于神经网络分色算法的补偿模型

神经网络模型在分色算法中具有预测不确定和精度较低的缺点,在其基础上提出了补偿模型。该模型将神经网络预测CMYK 的各通道差值拟合成L*a*b* 多项式的函数,并对CMYK 值进行补偿。通过对该模型的实验测试表明,采用CMYK 值进行补偿后与原模型相比,提高了分色算法的精度,并且其分色精度要高于其他常用的模型。