A hierarchical optimization neural network for large-scale dynamic systems

A recurrent neural network for dynamical hierarchical optimization of nonlinear discrete large-scale systems is presented. The proposed neural network consists of hierarchically structured sub-networks: one coordination sub-network at the upper level and several local optimization sub-networks at the lower level. In particular, the coordination sub-network and the local optimization sub-networks work simultaneously. This feature makes the proposed method outperform in computational efficiency the conventional iterative algorithms where there usually exists an alternately waiting time during the coordination and local optimization processes. Moreover, the state equations of the subsystems of the large-scale system are imbedded into their corresponding local optimization sub-networks. This imbedding technique not only overcomes the difficulty in treating the constraints imposed by the state equations, but also leads to significant reduction in the network size. We present stability analysis to prove that the neural network is asymptotically stable and this stable state corresponds to the optimal solution to the original optimal control problem. Finally, we illustrate the performance of the proposed method by an example.     

消费者偏好预测的深度学习神经网络模型

通过对于人类大脑活动的研究来分析消费者对广告和产品的反应的神经营销正在受到新的关注。针对基于脑电波（EEG）的神经营销，提出了一种基于深度学习神经网络的消费者对产品的偏好预测方法。首先，为了提取消费者EEG的特征，采用短时傅里叶变换（STFT）与双调和样条插值，从多通道脑电信号中得到了5个不同频带的EEG形图视频；然后，提出了一种结合5个三维卷积神经网络（3D CNN）与多层长短期记忆（LSTM）神经网络的预测模型，用于从脑电地形图视频预测到消费者的偏好。与卷积神经网络（CNN）模型和LSTM神经网络模型相比，消费者依赖模型的平均准确度分别提高了15.05个百分点和19.44个百分点，消费者独立模型的平均准确度分别提高了16.34个百分点和17.88个百分点。理论分析与实验结果表明，所提出的消费者偏好预测系统可以以低成本提供有效的营销策略开发和营销管理。     

Artificial neural network models for HFCS isomerization process

This work presents an approach to the modeling of a real industrial isomerization reactor by using artificial neural networks (ANN) pre-processed with principal component analysis (PCA). The initial model considered the output fructose concentration as the output variable, while the flow rate of substrate to the reactor as the principal input variable. Then, the ANN model was restructured and inversely trained by assuming the exit fructose concentration as the input variable and the feed flow rate as the output variable. Results indicate good performance by the application of the developed strategy to an extensive industrial data set. The results are expected to be useful in future, controlling the fructose concentration in the HFCS isomerization reactor.     

DSP-based hierarchical neural network modulation signal classification

This paper discusses a real-time digital signal processor (DSP)-based hierarchical neural network classifier capable of classifying both analog and digital modulation signals. A high-performance DSP processor, namely the TMS320C6701, is utilized to implement different kinds of classifiers including a hierarchical neural network classifier. A total of 31 statistical signal features are extracted and used to classify 11 modulation signals plus white noise. The modulation signals include CW, AM, FM, SSB, FSK2, FSK4, PSK2, PSK4, OOK, QAM16, and QAM32. A classification hierarchy is introduced and the genetic algorithm is employed to obtain the most effective set of features at each level of the hierarchy. The classification results and the number of operations on the DSP processor indicate the effectiveness of the introduced hierarchical neural network classifier in terms of both classification rate and processing time.     

分层神经网络在入侵检测系统中的应用

入侵检测技术是提高网络安全的重要手段之一,旨在利用分层神经网络解决入侵检测问题。针对入侵检测研究的通用审计数据集,首先将数据进行预处理以便运算;其次利用RBF网络实现粗检测;再次利用Elman BP网络进行细检测,从而实现分层神经网络的入侵检测;最后在MATLAB平台下进行仿真实验,仿真结果表明,分层神经网络结构在入侵检测中体现出良好的特性。     

Artificial neural network for predicting creep of concrete

The concrete is today the building material by excellence. Drying accompanies the hardening of concrete and leads to significant dimensional changes that appear as cracks. These cracks influence the durability of the concrete works. Deforming a concrete element subjected to long-term loading is the sum of said instantaneous and delayed deformation due to creep deformation. Concrete creep is the continuous process of deformation of an element, which exerts a constant or variable load. It depends in particular on the characteristics of concrete, age during loading, the thickness of the element of the environmental humidity, and time. Creep is a complex phenomenon, recognized but poorly understood. It is related to the effects of migration of water into the pores and capillaries of the matrix and to a process of reorganization of the structure of hydrated binder crystals. Applying a nonparametric approach called artificial neural network (ANN) to effectively predict the dimensional changes due to creep drying is the subject of this research. Using this approach allows to develop models for predicting creep. These models use a multilayer backpropagation. They depend on a very large database of experimental results issued from the literature (RILEM Data Bank) and on appropriate choice of architectures and learning processes. These models take into account the different parameters of concrete preservation and making, which affect drying creep of concrete as relative humidity, cure period, water-to-cement ratio (W/C), volume-to-surface area ratio (V/S), and fine aggregate-to-total aggregate ratio, or fine aggregate-to-total aggregate ratio. To validate these models, they are compared with parametric models as B3, ACI 209, CEB, and GL2000. In these comparisons, it appears that ANN approach describes correctly the evolution with time of drying creep. A parametric study is also conducted to quantify the degree of influence of some of the different parameters used in the developed neural network model.     

Artificial bee colony-based neural network for the prediction of the fundamental period of infilled frame structures

Neural Computing and Applications - The artificial bee colony (ABC) algorithm is a recently introduced swarm intelligence algorithm for optimization, which has already been successfully applied for...     

Artificial neural network methods for the prediction of framework crystal structures of zeolites from XRD data

Extracting information about the structures of zeolites and other crystalline materials from X-ray diffraction (XRD) data simply by using statistical methods may provide an impetus for the discovery and identification of unknown materials. In this study, the possibility of using artificial neural network methods for relating framework crystal structures to XRD data reported in literature was investigated. Generalized Regression Neural Networks and Radial Basis Function-Based Neural Networks were utilized in the investigations. The results obtained by neural networks, using fivefold cross validation technique, were compared to the actual values as well as to those determined by multilinear regression. The predictions made by these neural network methods were, in general, more reliable than those performed by regression. The best predictions were achieved for the estimation of the framework densities of zeolites, which provided quite small deviations from the actual values.     

基于迁移学习的分层注意力网络情感分析算法

文本情感分析的目的是判断文本的情感类型。传统的基于神经网络的研究方法主要依赖于无监督训练的词向量,但这些词向量无法准确体现上下文语境关系;常用于处理情感分析问题的循环神经网络（RNN）,模型参数众多,训练难度较大。为解决上述问题,提出了基于迁移学习的分层注意力神经网络（TLHANN）的情感分析算法。首先利用机器翻译任务训练一个用于在上下文中理解词语的编码器;然后,将这个编码器迁移到情感分析任务中,并将编码器输出的隐藏向量与无监督训练的词向量结合。在情感分析任务中,使用双层神经网络,每层均采用简化的循环神经网络结构——最小门单元（MGU）,有效减少了参数个数,并引入了注意力机制提取重要信息。实验结果证明,所提算法的分类准确率与传统循环神经网络算法、支持向量机（SVM）算法相比分别平均提升了8.7%及23.4%。     

Artificial neural network and wavelet neural network approaches for modelling of a solar air heater

This paper reports on a modelling study of new solar air heater (SAH) system by using artificial neural network (ANN) and wavelet neural network (WNN) models. In this study, a device for inserting an absorbing plate made of aluminium cans into the double-pass channel in a flat-plate SAH. A SAH system is a multi-variable system that is hard to model by conventional methods. As regards the ANN and WNN methods, it has a superior capability for generalization, and this capability is independent on the dimensionality of the input data’s. In this study, an ANN and WNN based methods were intended to adopt SAH system for efficient modelling. To evaluate prediction capabilities of different types of neural network models (ANN and WNN), their best architecture and effective training parameters should be found. The performance of the proposed methodology was evaluated by using several statistical validation parameters. Comparison between predicted and experimental results indicates that the proposed WNN model can be used for estimating the some parameters of SAHs with reasonable accuracy.     

High-order neural network structures for identification ofdynamical systems

Several continuous-time and discrete-time recurrent neural network models have been developed and applied to various engineering problems. One of the difficulties encountered in the application of recurrent networks is the derivation of efficient learning algorithms that also guarantee the stability of the overall system. This paper studies the approximation and learning properties of one class of recurrent networks, known as high-order neural networks; and applies these architectures to the identification of dynamical systems. In recurrent high-order neural networks, the dynamic components are distributed throughout the network in the form of dynamic neurons. It is shown that if enough high-order connections are allowed then this network is capable of approximating arbitrary dynamical systems. Identification schemes based on high-order network architectures are designed and analyzed.     

Artificial neural network based approach for dynamic parameter design

The Taguchi parameter design method has been recognized as an important tool for improving the quality of a product or a process. However, the statistical methods and optimization procedures proposed by Taguchi have much room for improvement. For instance, the two-step procedure proposed by Taguchi may fail to identify an optimum design condition if an adjustment parameter does not exist, the optimal setting of a design parameter is determined only among the levels included in the parameter design experiment, and, for the dynamic parameter design, the signal parameter is assumed to follow a uniform rather than a general distribution. This paper develops an artificial neural network based dynamic parameter design approach to overcome the shortcomings of the Taguchi and existing alternative approaches. First, an artificial neural network is trained to map the relationship between the characteristic, design, noise and signal parameters. Second, Latin hypercube samples of the signal and noise parameters are obtained and used to estimate the slope between the signal parameter and characteristic as well as the variance of the characteristic at each set of design parameter settings. Then, the dynamic parameter design problem is formulated as a nonlinear optimization problem and solved to find the optimal settings of the design parameters using sequential quadratic programming. The effectiveness of the proposed approach is illustrated with an example.     

Artificial neural network approach for solving fuzzy differential equations

The current research attempts to offer a novel method for solving fuzzy differential equations with initial conditions based on the use of feed-forward neural networks. First, the fuzzy differential equation is replaced by a system of ordinary differential equations. A trial solution of this system is written as a sum of two parts. The first part satisfies the initial condition and contains no adjustable parameters. The second part involves a feed-forward neural network containing adjustable parameters (the weights). Hence by construction, the initial condition is satisfied and the network is trained to satisfy the differential equations. This method, in comparison with existing numerical methods, shows that the use of neural networks provides solutions with good generalization and high accuracy. The proposed method is illustrated by several examples.     

Artificial neural network based predictive method for flood disaster

Most of flood disaster predictions belong to ill-structured problems, while artificial neural network (ANN) has several characteristics that are suitable for solving them. In this paper, a neural network based predictive method for flood disaster problem is proposed in which the neural network model and its basic designing principles are described, and an example of flood disaster area in China from 1949 to 1994 is used for demonstration.     

Artificial neural network visual model for image quality enhancement

An artificial neural network visual model is developed, which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate for the coding distortions. This provides a generic postprocessing technique that can be applied to all the main coding methods. Experimental results involving postprocessing of the JPEG and quadtree coding systems show that the proposed artificial neural network visual model significantly enhances the quality of reconstructed images, both in terms of the objective peak signal-to-noise ratio and subjective visual assessment.     

Artificial neural networks for coordination and control: The portability of experiential representations

It is time to locate connectionist representation theory in the new wave of robotics research. The utility of representations developed in artificial neural networks (ANNs) during learning has been demonstrated in cognitive science research since the 1980s. The research reported here puts learned representations to work in a decentered control task, the disembodied arm problem, in which a mobile robot operates an arm fixed to a table to pick up objects. There is no physical linkage between the arm and the robot and so the robot's point of view must be decentered. This is done by developing a modular Artificial Neural Net system in three stages: (i) a classifier net is trained with laser scan data to output transformationally invariant position classes; (ii) an arm net is trained for picking up objects; (iii) an inter net is trained to communicate and coordinate the sensing and acting. The completed system is shown to create new nonsymbolic transformationally invariant representations in order to perform the effective generalization of decentered viewpoints.     

多级卷积神经网络的沥青路面裂缝图像层次化筛选

如何快速准确地识别与评估沥青路面裂缝病害,已成为路面养护和保障道路安全的重要任务之 一。实际采集路面图像中往往存在大量的非裂缝图像,在保证裂缝图像无漏筛的前提下,尽可能提高裂缝图像 的精确率与非裂缝图像的真负例率,则对于降低人工筛选的工作强度,以及后续裂缝自动分割与病害损坏程度 评估具有重要实际意义。故此,提出了一种多级卷积神经网络的沥青路面裂缝图像筛选方法,由训练、微调与 验证三阶段构成,利用微调集获得 softmax 层输入微调增量。为避免裂缝图像召回率增加与精确率下降的问题, 在对比不同卷积神经网络筛除的非裂缝图像异同基础上,采用改进 AlexNet 作为一级筛选网络,VGG16 或 ResNet50 作为二、三级筛选网络的层次化处理模型。对于含噪声及复杂路面图像测试集的实验结果表明,三级 层次化筛选模型能在 100%召回裂缝图像时,达到高的真负例率及准确率。与其他方法的对比实验表明,所提 方法可有效解决沥青路面裂缝图像漏筛问题,且具有更好的检测效果。     

基于遗传算法的人工神经网络

为克服和改进传统的BP算法的不足,发挥神经网络和遗传算法各自的优势,提出了一种基于遗传算法的神经网络二次训练方法,将遗传算法应用于神经网络的权值训练中,并用神经网络二次训练得到最终结果,降低了计算时间,是一种比较有效的方法。     

基于人工神经网络的半脆弱零水印技术

提出了基于人工神经网络的半脆弱零水印技术。首先在宿主图像中随机选择像素点,然后利用神经网络构建所选择像素点与其3×3邻域像素之间的关系,并与二值水印图像进行异或运算得到水印检测密钥,作为所构造的零水印。由于仅从宿主图像中抽取特征构造水印,而没有向图像中嵌入信息,避免了嵌入水印所导致的图像变形。该技术可以用于图像真实性、完整性认证,并可定位篡改发生的位置,且对于JPEG图像压缩具有一定的稳健性。实验结果证明了算法的有效性。