End-to-end aspect category sentiment analysis based on type graph convolutional networks

For the existing aspect category sentiment analysis research,most of the aspects are given for sentiment extraction,and this pipeline method is prone to error accumulation,and the use of graph convolutional neural network for aspect category sentiment analysis does not fully utilize the dependency type information between words,so it cannot enhance feature extraction.This paper proposes an end-to-end aspect category sentiment analysis(ETESA)model based on type graph convolutional networks.The model uses the bidirectional encoder representation from transformers(BERT)pretraining model to obtain aspect categories and word vectors containing contextual dynamic semantic information,which can solve the problem of polysemy;when using graph convolutional network(GCN)for feature extraction,the fusion operation of word vectors and initialization tensor of dependency types can obtain the importance values of different dependency types and enhance the text feature representation;by transforming aspect category and sentiment pair extraction into multiple single-label classification problems,aspect category and sentiment can be extracted simultaneously in an end-to-end way and solve the problem of error accumulation.Experiments are tested on three public datasets,and the results show that the ETESA model can achieve higher Precision,Recall and F1 value,proving the effectiveness of the model.

Eddy current quantitative evaluation of high-speed railway contact wire cracks based on neural network

Purpose–The purpose of this study is to study the quantitative evaluation method of contact wire cracks by analyzing the changing law of eddy current signal characteristics under different cracks of contact wire of high-speed railway so as to provide a new way of thinking and method for the detection of contact wire injuries of high-speed railway.Design/methodology/approach–Based on the principle of eddy current detection and the specification parameters of high-speed railway contact wires in China,a finite element model for eddy current testing of contact wires was established to explore the variation patterns of crack signal characteristics in numerical simulation.A crack detection system based on eddy current detection was built,and eddy current detection voltage data was obtained for cracks of different depths and widths.By analyzing the variation law of eddy current signals,characteristic parameters were obtained and a quantitative evaluation model for crack width and depth was established based on the back propagation(BP)neural network.Findings–Numerical simulation and experimental detection of eddy current signal change rule is basically consistent,based on the law of the selected characteristics of the parameters in the BP neural network crack quantitative evaluation model also has a certain degree of effectiveness and reliability.BP neural network training results show that the classification accuracy for different widths and depths of the classification is 100 and 85.71%,respectively,and can be effectively realized on the high-speed railway contact line cracks of the quantitative evaluation classification.Originality/value–This study establishes a new type of high-speed railway contact wire crack detection and identification method,which provides a new technical means for high-speed railway contact wire injury detection.The study of eddy current characteristic law and quantitative evaluation model for different cracks in contact line has important academic value and practical significance,and it has certain guiding significance for the detection technology of contact line in high-speed railway.

Chain-type wireless sensor network node scheduling strategy

In order to reduce power consumption of sensor nodes and extend network survival time in the wireless sensor network （WSN）, sensor nodes are scheduled in an active or dormant mode. A chain-type WSN is fundamental y different from other types of WSNs, in which the sensor nodes are deployed along elongated geographic areas and form a chain-type network topo-logy structure. This paper investigates the node scheduling prob-lem in the chain-type WSN. Firstly, a node dormant scheduling mode is analyzed theoretical y from geographic coverage, and then three neighboring nodes scheduling criteria are proposed. Sec-ondly, a hybrid coverage scheduling algorithm and dead areas are presented. Final y, node scheduling in mine tunnel WSN with uniform deployment （UD）, non-uniform deployment （NUD） and op-timal distribution point spacing （ODS） is simulated. The results show that the node scheduling with UD and NUD, especial y NUD, can effectively extend the network survival time. Therefore, a strat-egy of adding a few mobile nodes which activate the network in dead areas is proposed, which can further extend the network survival time by balancing the energy consumption of nodes.

Monthly Mean Temperature Prediction Based on a Multi－level Mapping Model of Neural Network BP Type

In terms of 34-year monthly mean temperature series in 1946-1979,the multi-level maPPing model of neural netWork BP type was applied to calculate the system's fractual dimension Do=2'8,leading tO a three-level model of this type with ixj=3x2,k=l,and the 1980 monthly mean temperture predichon on a long-t6rm basis were prepared by steadily modifying the weighting coefficient,making for the correlation coefficient of 97% with the measurements.Furthermore,the weighhng parameter was modified for each month of 1980 by means of observations,therefore constrcuhng monthly mean temperature forecasts from January to December of the year,reaching the correlation of 99.9% with the measurements.Likewise,the resulting 1981 monthly predictions on a long-range basis with 1946-1980 corresponding records yielded the correlahon of 98% and the month-tO month forecasts of 99.4%.

From Single-type to Overall Networked Type： Gradual Progress Trend of the BPM Technology

Since the middle and later period of the 1990s, business process management has become the major thought and method of modem business administration. After tracking back of the management origin and probing into the relations between business process and management theory development, this paper finds after the proposition of Taylor＇s scientific management, the business process management began to sprout and was divided into four stages： technological stage of single procedure, interior networked stage, the stage of electronic network and overall networked stage. This paper also proposes the view that the evolvement of business progress management enlightens us a lot in the improvement of today＇s business administration.

BP neural network classification on passenger vehicle type based on GA of feature selection

This paper has concluded six features that belong to passenger vehicle types based on genetic algorithm(GA)of feature selection.We have obtained an optimal feature subset,including length,ratio of width and length,and ratio of height and length.And then we apply this optimal feature subset as well as another feature set,containing length,width and height,to the network input.Back-propagation(BP)neural network and support vector machine(SVM)are applied to classify the passenger vehicle type.There are four passenger vehicle types.This paper selects 400 samples of passenger vehicles,among which 320 samples are used as training set(each class has 80 samples)and the other 80 samples as testing set,taking the feature of the samples as network input and taking four passenger vehicle types as output.For the test,we have applied BP neural network to choose the optimal feature subset as network input,and the results show that the total classification accuracy rate can reach 96%,and the classification accuracy rate of first type can reach 100%.In this condition,we obtain a conclusion that this algorithm is better than the traditional ones[9].

From non-obese diabetic to Network for the Pancreatic Organ Donor with Diabetes: New heights in type 1 diabetes research

Since the discovery of therapeutic insulin in 1922 and the development of the non-obese diabetic spontaneous mouse model in 1980,the establishment of Network for Pancreatic Organ Donor with Diabetes(n POD) in 2007 is arguably the most important milestone step in advancing type 1 diabetes(T1D) research. In this perspective,we briefly describe how n POD is transforming T1 D research via procuring and coordinating analysis of disease pathogenesis directly in human organs donated by deceased diabetic and control subjects. The successful precedent set up by n POD is likely to spread far beyond the confines of research in T1 D to revolutionize biomedical research of other disease using high quality procured human cells and tissues.

Global asymptotic stability for Hopfield-type neural networks with diffusion effects

The existence, uniqueness and global asymptotic stability for the equilibrium of Hopfield-type neural networks with diffusion effects are studied. When the activation functions are monotonously nondecreasing, differentiable, and the interconnected matrix is related to the Lyapunov diagonal stable matrix, the sufficient conditions guaranteeing the existence of the equilibrium of the system are obtained by applying the topological degree theory. By means of constructing the suitable average Lyapunov functions, the global asymptotic stability of the equilibrium of the system is also investigated. It is shown that the equilibrium （if it exists） is globally asymptotically stable and this implies that the equilibrium of the system is unique.

Existence of Periodic Solutions for Neutral-Type Neural Networks with Delays on Time Scales

In this paper, we employ a fixed point theorem due to Krasnosel’skii to attain the existence of periodic solutions for neutral-type neural networks with delays on a periodic time scale. Some new sufficient conditions are established to show that there exists a unique periodic solution by the contraction mapping principle.

Four Types of Percolation Transitions in the Cluster Aggregation Network Model

We study the percolation transition in a one-species cluster aggregation network model, in which the parameter α describes the suppression on the cluster sizes. It is found that the model can exhibit four types of percolation transitions, two continuous percolation transitions and two discontinuous ones. Continuous and discontinuous percolation transitions can be distinguished from each other by the largest single jump. Two types of continuous percolation transitions show different behaviors in the time gap. Two types of discontinuous percolation transitions are different in the time evolution of the cluster size distribution. Moreover, we also find that the time gap may also be a measure to distinguish different discontinuous percolations in this model.

Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginarytype activation functions

In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.

Periodic Solution for Neutral Type Neural Networks

The principle aim of this paper is to explore the existence of periodic solution of neural networks model with neutral delay. Sufficient and realistic conditions are obtained by means of an abstract continuous theorem of k-set contractive operator and some analysis technique.

Parameter Optimization of Interval Type-2 Fuzzy Neural Networks Based on PSO and BBBC Methods

Interval type-2 fuzzy neural networks(IT2FNNs)can be seen as the hybridization of interval type-2 fuzzy systems(IT2FSs) and neural networks(NNs). Thus, they naturally inherit the merits of both IT2 FSs and NNs. Although IT2 FNNs have more advantages in processing uncertain, incomplete, or imprecise information compared to their type-1 counterparts, a large number of parameters need to be tuned in the IT2 FNNs,which increases the difficulties of their design. In this paper,big bang-big crunch(BBBC) optimization and particle swarm optimization(PSO) are applied in the parameter optimization for Takagi-Sugeno-Kang(TSK) type IT2 FNNs. The employment of the BBBC and PSO strategies can eliminate the need of backpropagation computation. The computing problem is converted to a simple feed-forward IT2 FNNs learning. The adoption of the BBBC or the PSO will not only simplify the design of the IT2 FNNs, but will also increase identification accuracy when compared with present methods. The proposed optimization based strategies are tested with three types of interval type-2 fuzzy membership functions(IT2FMFs) and deployed on three typical identification models. Simulation results certify the effectiveness of the proposed parameter optimization methods for the IT2 FNNs.

基于依赖类型剪枝的双特征自适应融合网络用于方面级情感分析

现有的模型将基于依赖树的图神经网络用于方面级情感分析,一定程度上提升了模型的分类性能。然而,由于依赖解析技术的限制,语法解析结果的不精确导致依赖树存在大量噪声,使得模型的性能提升有限。此外,一些句子本身并不符合标准的句法结构。以往的研究以同样的置信度利用句法信息和语义信息,没有充分考虑它们对于确定方面词极性的贡献的不同,导致模型在相应的数据集上性能较差。为了克服这些困难,文中提出了一种基于依赖类型剪枝的双特征自适应融合网络。具体来说,该模型使用一种新型的混合方法,命名为依赖关系类型剪枝和邻接矩阵平滑,来缓解句法解析产生的噪声。此外,该模型通过双特征自适应融合模块充分考虑句子的句法信息的可用程度,以一种更灵活的方式将句法特征和语义特征结合起来用于方面级情感分析。在5个公开可用的数据集上进行广泛的实验,结果证明了该方法明显优于基线模型。

网络安全运维工作中的攻击与防御

网络安全是指网络系统的硬件、软件及其系统中的数据受到保护,不因偶然的或者恶意的原因而遭到破坏、更改、泄露。在数据时代,信息安全逐渐成为人们关注的焦点。基于此,文章主要分析了网络安全运维工作中的攻击类型与防御策略。

通过卷积神经网络分析ECT成像和临床检验数据评估糖尿病视网膜病变和糖尿病肾病之间的相关性

目的从影像学和临床检验数据综合评估2型糖尿病患者(T2DM)中糖尿病肾病(DN)和糖尿病视网膜病变(DR)的相关性。方法选取2021年3月至2022年12月就诊于资阳市第一人民医院的T2DM患者600例,所有患者均行眼底照相和荧光素眼底血管造影检查,收集患者年龄、性别、T2DM持续时间、心血管疾病、脑血管疾病、高血压、吸烟史、饮酒史、体重指数、收缩压和舒张压等临床数据。测量空腹血糖、甘油三酯、总胆固醇、高密度脂蛋白胆固醇、低密度脂蛋白胆固醇、糖化血红蛋白、24 h尿白蛋白、尿白蛋白/肌酐、血肌酐和血尿素氮水平。采用Logistic回归分析与DR相关的危险因素。根据眼底图片进行DR分期,采用卷积神经网络(CNN)算法作为图像分析方法,通过ECT成像技术和临床检验数据评估DR和DN之间的相关性。结果采用CNN算法进行分析,无明显DR、轻度非增生型DR(NPDR)、中度NPDR、重度NPDR和增生型DR(PDR)组患者的DR和DN病变面积率均高于采用传统算法(TCM)的结果。随着DR的加重,患者血肌酐、血尿素氮、24 h尿白蛋白和尿白蛋白/肌酐均逐渐升高,无明显DR、轻度NPDR、中度NPDR、重度NPDR和PDR组患者的DN发生率分别为1.67%、8.83%、16.16%、22.16%和30.83%。Logistic回归分析结果显示,T2DM持续时间、吸烟史、糖化血红蛋白、总胆固醇、甘油三酯、高密度脂蛋白胆固醇、低密度脂蛋白胆固醇、24 h尿白蛋白、血肌酐、血尿素氮、尿白蛋白/肌酐、肾小球滤过率是DR的独立危险因素。肾动态ECT成像分析结果表明,随着DR的加重,肾血流灌注逐渐减少,从而导致肾过滤功能下降。结论在T2DM患者中,CNN算法早期应用于DR和DN图像的分析,将有助于提高DR和DN病变面积诊断准确性,随着DR病变的加重,DN的严重程度逐渐增加。

基于多节点策略的雷达智能干扰调制类型识别技术研究

采用认知雷达架构有助于实现雷达抗干扰技术的智能化程度提升。针对认知抗干扰技术领域中雷达对电磁干扰环境的感知问题,文中提出了一种基于深度学习的多节点干扰调制类型识别方法。该方法针对雷达信号处理的不同节点,如数字波束形成、自适应副瓣对消、脉冲压缩前后以及动目标检测之后,采用多个节点的时频平面和距离多普勒平面作为干扰信号的联合特征提取对象,建立了基于深度学习的多节点干扰识别策略模型,以提高多种干扰场景下的干扰识别正确率。为了提升干扰特征的提取能力和网络的训练效率,将用于干扰识别的深度学习算法在卷积神经网络的基础上引入了注意力机制和残差网络,建立了针对多节点策略下的干扰类型识别网络结构,实现了对多种不同干扰场景下的干扰类型识别。仿真结果表明:在单一干扰场景下,当干噪比为14 dB时,所提算法的干扰识别准确率可达92%;在多干扰场景下,所提算法在不同节点策略的加持下,识别准确率可达90%。

基于点云反射特性的前方道路附着系数估计方法研究

路面附着系数是影响自动驾驶系统决策控制策略的重要因素。为实现对道路附着系数前瞻性的高精度感知,本文基于车载激光雷达设计了一种新的路面附着系数估计方法。首先采集了干燥柏油路面、混凝土路面、湿滑柏油路面、结冰路面和积雪路面构建道路数据集;基于使用布料模拟滤波和RANSAC算法进行了道路点云提取、基于高斯滤波去除反射率异常噪点;根据点云反射率随距离和入射角变化的规律将路面划分为不同区域分别提取特征;基于深度神经网络构建了道路识别模型,并基于采集数据集进行了训练,最后基于路面材质和峰值附着系数的统计经验确定了前方道路的附着系数。测试结果表明,本文提出的算法道路类型辨识精度超过99.3%,算法平均运行周期55ms,可实现实时高精度的路面峰值附着系数估计。