基于BP神经网络的管道中泥浆输运模拟研究

BP人工神经网络是神经网络中应用最广泛的一种同络模型,本文详细介绍了BP网络模型的建立和算法过程及一些改进算法.利用BP神经网络建立管道泥浆输运中阻力与泥浆浓度和流速之间关系的预测模型.验证表明,运用BP神经网络模型可以建立精度较高的非线性动力关系.     

Aspect sentiment analysis with heterogeneous graph neural networks

Aspect-based sentiment analysis technologies may be a very practical methodology for securities trading, commodity sales, movie rating websites, etc. Most recent studies adopt the recurrent neural network or attention-based neural network methods to infer aspect sentiment using opinion context terms and sentence dependency trees. However, due to a sentence often having multiple aspects sentiment representation, these models are hard to achieve satisfactory classification results. In this paper, we discuss these problems by encoding sentence syntax tree, words relations and opinion dictionary information in a unified framework. We called this method heterogeneous graph neural networks (Hete_GNNs). Firstly, we adopt the interactive aspect words and contexts to encode the sentence sequence information for parameter sharing. Then, we utilized a novel heterogeneous graph neural network for encoding these sentences’ syntax dependency tree, prior sentiment dictionary, and some part-of-speech tagging information for sentiment prediction. We perform the Hete_GNNs sentiment judgment and report the experiments on five domain datasets, and the results confirm that the heterogeneous context information can be better captured with heterogeneous graph neural networks. The improvement of the proposed method is demonstrated by aspect sentiment classification task comparison.     

The solutions of vibration control problems using artificial neural networks

This paper introduces an alternative method artificial neural networks (ANN) used to obtain numerical solutions of mathematical models of dynamic systems, represented by ordinary differential equations (ODEs) and partial differential equations (PDEs). The proposed trial solution of differential equations (DEs) consists of two parts: The initial and boundary conditions (BCs) should be satisfied by the first part. However, the second part is not affected from initial and BCs, but it only tries to satisfy DE. This part involves a feedforward ANN containing adjustable parameters (weight and bias). The proposed solution satisfying boundary and initial condition uses a feedforward ANN with one hidden layer varying the neuron number in the hidden layer according to complexity of the considered problem. The ANN having appropriate architecture has been trained with backpropagation algorithm using an adaptive learning rate to satisfy DE. Moreover, we have, first, developed the general formula for the numerical solutions of nth-order initial-value problems by using ANN.For numerical applications, the ODEs that are the mathematical models of linear and non-linear mass-damper-spring systems and the second- and fourth-order PDEs that are the mathematical models of the control of longitudinal vibrations of rods and lateral vibrations of beams have been considered. Finally, the responses of the controlled and non-controlled systems have been obtained. The obtained results have been graphically presented and some conclusion remarks are given.     

Automatic keyword identification by artificial neural networks compared to manual identification by users of filtering systems

Information filtering (IF) systems usually filter data items by correlating a vector of terms that represent the user profile with similar vectors of terms that represent data items. Terms that represent data items can be determined by experts or automatic indexing methods. In this study we employ an artificial neural network (ANN) as an alternative method for both IF and term selection and compare its effectiveness to that of “traditional” methods. In an earlier study we developed and examined the performance of an IF system that employed content-based and stereotypic rule-based filtering methods in the domain of e-mail messages. In this study, we train a large-scale ANN-based filter, which uses meaningful terms in the same database as input, and use it to predict the relevance of those messages. Our results reveal that the ANN relevance prediction out-performs the prediction of the IF system. Moreover, we found very low correlation between the terms in the user profile (explicitly selected by the users) and the positive causal-index (CI) terms of the ANN, which indicate the relative importance of terms in messages. This implies that the users underestimate the importance of some terms, failing to include them in their profiles. This may explain the rather low prediction accuracy of the IF system.     

Implicit dimension identification in user-generated text with LSTM networks

In the process of online storytelling, individual users create and consume highly diverse content that contains a great deal of implicit beliefs and not plainly expressed narrative. It is hard to manually detect these implicit beliefs, intentions and moral foundations of the writers.We study and investigate two different tasks, each of which reflect the difficulty of detecting an implicit user’s knowledge, intent or belief that may be based on writer’s moral foundation: (1) political perspective detection in news articles (2) identification of informational vs. conversational questions in community question answering (CQA) archives. In both tasks we first describe new interesting annotated datasets and make the datasets publicly available. Second, we compare various classification algorithms, and show the differences in their performance on both tasks. Third, in political perspective detection task we utilize a narrative representation language of local press to identify perspective differences between presumably neutral American and British press.     

Passivity analysis of memristor-based recurrent neural networks with time-varying delays

This paper investigates the delay-dependent exponential passivity problem of the memristor-based recurrent neural networks (RNNs). Based on the knowledge of memristor and recurrent neural network, the model of the memristor-based RNNs is established. Taking into account of the information of the neuron activation functions and the involved time-varying delays, several improved results with less computational burden and conservatism have been obtained in the sense of Filippov solutions. A numerical example is presented to show the effectiveness of the obtained results.     

Dementia analysis from functional connectivity network with graph neural networks

Deep learning methods have been widely applied for disease diagnosis on resting-state fMRI (rs-fMRI) data, but they are incapable of investigating global relationships between different brain regions as well as ignoring the interpretability. To address these issues, this paper presents a new graph neural network framework for brain disease diagnosis via jointly learning global relationships and selecting the most discriminative brain regions. Specifically, we first design a self-attention structure learning to capture the global interactions between brain regions for achieving diagnosis effectiveness, and theoretically integrate a feature selection method to reduce the noise influence as well as achieve interpretability. Experiment results on three neurological diseases datasets show the effectiveness of our method, compared to the comparison methods, in terms of diagnostic performance and interpretability.     

石油专用设备投资评价的神经网络模型及实证研究

建立基于人工神经网络的石油专用设备投资评价模型,并利用大庆油田的历史数据对模型进行训练和模拟,以向石油企业提供科学合理的石油采油设备投资决策方法。     

Fixed-time synchronization of delayed impulsive inertial neural networks with discontinuous activation functions via indefinite LKF method

This article investigates the fixed time synchronization (FXTSY) problem of time-varying delayed impulsive inertial neural networks (INNs) with discontinuous activation functions. First, the addressed delayed discontinuous INNs are converted into a first-order differential equation using a generalized variable transformation with suitable tunable variables. Due to the existence of the discontinuities, the delayed discontinuous differential equations are transformed into the differential inclusions by using the differential inclusion theory and set-valued map concepts. Furthermore, by designing the suitable centralized impulsive control and discontinuous control, constructing the novel indefinite type Lyapunov functionals, new algebraic conditions are derived to realize the FXTSY for the leader-following impulsive INNs. Moreover, the settling time is explicitly calculated. Finally, the developed theoretical results are verified by two numerical simulation results.     

Improved exponential stability analysis for delayed recurrent neural networks

In this paper, we investigate the problem of global exponential stability analysis for a class of delayed recurrent neural networks. This class includes Hopfield neural networks and cellular neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are less conservative than previous published ones in the literature, which are illustrated by representative numerical examples.     

Stochastic stability analysis of piecewise homogeneous Markovian jump neural networks with mixed time-delays

In this paper, the problem of stochastic stability analysis is considered for piecewise homogeneous Markovian jump neural networks with both discrete and distributed delays by use of linear matrix inequality (LMI) method. Based on a Lyapunov functional that accounts for the mixed time-delays, a delay-dependent stability condition is given, which is formulated by LMIs and thus can be easily checked. Some special cases are also investigated. Finally, a numerical example is given to show the validness of the proposed result.     

Further analysis of global robust stability of neural networks with multiple time delays

This paper deals with the problem of the global robust asymptotic stability of the class of dynamical neural networks with multiple time delays. We propose a new alternative sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point under parameter uncertainties of the neural system. We first prove the existence and uniqueness of the equilibrium point by using the Homomorphic mapping theorem. Then, by employing a new Lyapunov functional, the Lyapunov stability theorem is used to establish the sufficient condition for the asymptotic stability of the equilibrium point. The obtained condition is independent of time delays and relies on the network parameters of the neural system only. Therefore, the equilibrium and stability properties of the delayed neural network can be easily checked. We also make a detailed comparison between our result and the previous corresponding results derived in the previous literature. This comparison proves that our result is new and improves some of the previously reported robust stability results. Some illustrative numerical examples are given to show the applicability and advantages of our result.     

Information retrieval by constrained spreading activation in semantic networks

GRANT is an expert system for finding sources of funding given research proposals. Its search method-constrained spreading activation—makes inferences about the goals of the user and thus finds information that the user did not explicitly request but that is likely to be useful. The architecture of GRANT and the implementation of constrained spreading activation are described, and grant's performance is evaluated.     

Global dissipativity of delayed neural networks with impulses

In this paper, we investigate the problem of global exponential dissipativity of neural networks with variable delays and impulses. The impulses are classified into three classes: input disturbances, stabilizing and “neutral” type—the impulses are neither helpful for stabilizing nor destabilizing the neural networks. We handle the three types of impulses in a uniform way by using the excellent ideology introduced recently. To this end, we propose new techniques which coupled with more general Lyapunov functions to realize the ideology and it is shown that they are more effective. Exponential dissipativity conditions are established in terms of linear matrix inequalities (LMIs) and these conditions can be straightforwardly reduced to exponential stability conditions. Numerical results are given to show that the obtained conditions are effective and less conservative than the existing ones.     

Quasi-synchronization of coupled neural networks with reaction-diffusion terms driven by fractional brownian motion

This paper investigates the quasi-synchronization of reaction-diffusion neural networks with hybrid coupling and parameter mismatches via sampled-data control technology. First, the models of neural networks with switching parameter and fraction Brownian motion are given. As a result of parameter mismatches, synchronization is normally not possible to realize directly, then the improved Halanay’s inequality is introduced, which is an important lemma to prove that the considered networks realize quasi-synchronization. Furthermore, based on stochastic theory, Lyapunov function method and inequality techniques, some sufficient conditions are derived to guarantee the quasi-synchronization of hybrid coupled neural networks with reaction-diffusion terms driven by fractional Brownian motion. Finally, two simulation examples are given to prove the efficiency of the developed criteria.     

Stability analysis of stochastic fuzzy Markovian jumping neural networks with leakage delay under impulsive perturbations

This paper investigates the global asymptotic stability of stochastic fuzzy Markovian jumping neural networks with mixed delays under impulsive perturbations in mean square. The mixed delays include constant delay in the leakage term (i.e., “leakage delay”), time-varying delay and continuously distributed delay. By using the Lyapunov functional method, reciprocal convex approach, linear convex combination technique, Jensen integral inequality and the free-weight matrix method, several novel sufficient conditions are derived to ensure the global asymptotic stability of the equilibrium point of the considered networks in mean square. The proposed results, which do not require the differentiability and monotonicity of the activation functions, can be easily checked via Matlab software. Finally, two numerical examples are given to demonstrate the effectiveness and less conservativeness of our theoretical results over existing literature.