Model Transformer Evaluation of High-Permeability Grain-Oriented Electrical Steels

The dependence of transformer performance on the material properties was investigated using two laboratory-processed 0.23 mm thick grain-oriented electrical steels domain-refined with elec-trolytically etched grooves having different magnetic properties. The iron loss at 1.7 T, 50 Hz and the flux density at 800 A/m of material A were 0.73 W/kg and 1.89 T, respectively; and those of material B, 0.83 W/kg and 1.88 T. Model stacked and wound transformer core experiments using the tested materials exhibited performance well reflecting the material characteristics. In a three-phase stacked core with step-lap joints excited to 1.7 T, 50 Hz, the core loss, the exciting current and the noise level were 0.86 W/kg, 0.74 A and 52 dB, respectively, with material A; and 0.97 W/kg, 1.0 A and 54 dB with material B. The building factors for the core losses of the two materials were almost the same in both core configurations. The effect of higher harmonics on transformer performance was also investigated.

A Model Transformation Approach for Detecting Distancing Violations in Weighted Graphs

This work presents the design of an Internet of Things(IoT)edge-based system based on model transformation and complete weighted graph to detect violations of social distancing measures in indoor public places.Awireless sensor network based on Bluetooth Low Energy is introduced as the infrastructure of the proposed design.A hybrid model transformation strategy for generating a graph database to represent groups of people is presented as a core middleware layer of the detecting system’s proposed architectural design.A Neo4j graph database is used as a target implementation generated from the proposed transformational system to store all captured real-time IoT data about the distances between individuals in an indoor area and answer user predefined queries,expressed using Neo4j Cypher,to provide insights from the stored data for decision support.As proof of concept,a discrete-time simulation model was adopted for the design of a COVID-19 physical distancing measures case study to evaluate the introduced system architecture.Twenty-one weighted graphs were generated randomly and the degrees of violation of distancing measures were inspected.The experimental results demonstrate the capability of the proposed system design to detect violations of COVID-19 physical distancing measures within an enclosed area.

Model Transformation and Optimization of the Olympics Scheduling Problem

安排问题的奥林匹克作为限制满足问题被建模，它被弄软最后的比赛的时间限制转变成一个抑制优化问题。分解方法论为抑制优化问题基于 Lagrangian 松驰被介绍。为双问题优化，有可变直径的亚坡度设计方法被学习。方法能收敛到全球性最佳的答案，效率被给。数字结果证明方法是有效的。

Model Transformation Using a Simplified Metamodel

Model Driven Engineering (MDE) is a model-centric software development approach aims at improving the quality and productivity of software development processes. While some progresses in MDE have been made, there are still many challenges in realizing the full benefits of model driven engineering. These challenges include incompleteness in existing modeling notations, inadequate in tools support, and the lack of effective model transformation mechanism. This paper provides a solution to build a template-based model transformation framework using a simplified metamode called Hierarchical Relational Metamodel (HRM). This framework supports MDE while providing the benefits of readability and rigorousness of meta-model definitions and transformation definitions.

On Utilizing Model Transformation for the Performance Analysis of Queueing Networks

In this paper, we present an approach for model transformation from Queueing Network Models (QNMs) into Queueing Petri Nets (QPNs). The performance of QPNs can be analyzed using a powerful simulation engine, SimQPN, designed to exploit the knowledge and behavior of QPNs to improve the efficiency of simulation. When QNMs are transformed into QPNs, their performance can be analyzed efficiently using SimQPN. To validate our approach, we apply it to analyze the performance of several queueing network models including a model of a database system. The evaluation results show that the performance analysis of the transformed QNMs has high accuracy and low overhead. In this context, model transformation enables the performance analysis of queueing networks using different ways that can be more efficient.

图像处理中CNN与视觉Transformer混合模型研究综述

卷积神经网络(CNN)与视觉Transformer是目前图像处理领域中两大重要的深度学习模型,两者经过多年来不断的研究与进步,已在该领域取得了非凡的成就。近些年来,CNN与视觉Transformer的混合模型正在逐步兴起,广泛的研究不断克服两种模型存在的弱项,高效地发挥出各自的亮点,在图像处理任务中表现出优异的效果。基于CNN与视觉Transformer混合模型进行深入阐述。总体概述了CNN与Vision Transformer模型的架构和优缺点,并总结混合模型的概念及优势。围绕串行结构融合方式、并行结构融合方式、层级交叉结构融合方式以及其他融合方式等四个方面全面回顾梳理了混合模型的研究现状和实际进展,并针对各种融合方式的主要代表模型进行总结与剖析,从多方面对典型混合模型进行评价对比。多角度叙述了混合模型在图像识别、图像分类、目标检测和图像分割等实际图像处理特定领域中应用研究,展现出混合模型在具体实践中的适用性和高效性。深入分析混合模型未来研究方向,并为后续该模型在图像处理中的研究与应用提出展望。

基于Point Transformer方法的鱼类三维点云模型分类

为实现对不同鱼类的精准分类,研究共采集110尾真实鱼类的三维模型,对获取的3D模型进行基于预处理、旋转增强和下采样等操作后,获取了1650尾实验样本。然后基于Point Transformer网络和2个三维分类的对比网络进行数据集的分类训练和验证。结果表明,利用本实验的目标方法Point Transformer获得了比2个对比网络更好的分类结果,整体的分类准确率能够达到91.9%。同时对所使用的三维分类网络进行有效性评估,3个模型对于5种真实鱼类模型的分类是有意义的,其中Point Transformer的模型ROC曲线准确率最高,AUC面积最大,对于三维鱼类数据集的分类最为有效。研究提供了一种可以实现对鱼类三维模型进行精准分类的方法,为以后的智能化渔业资源监测提供一种新的技术手段。

基于Transformer的动态双重处理动作识别框架

该框架采用双重处理策略:图像处理采用掩码图像建模,视频处理采用掩码视频建模。提出了一种新的自适应变压器,该变压器包含一种新的掩码方案,通过旋转掩码算法获得每帧的掩码,在掩码过程中保证一定的时空相关性,增强了模型的上下文感知能力。在主干中提出残差自适应块,有效地利用模型提取的特征信息进行动作分类。引入三维局部特征学习,提高特征表达能力,便于场景理解。在SSV2和Kinetics-400上进行了实验,结果证明了该模型的有效性。准确率分别为71.3%和81.4%。

基于双通道Transformer模型的多维信号故障诊断方法

感应电机在现代工业中有十分重要的作用。然而,电机长时间运行后会变得疲劳从而导致灾难性后果。由于电机故障诊断本质是对电机的时间信号分类,该研究提出双通道Transformer模型,该模型利用电流和振动信号进行诊断,并通过连续小波变换提取频域特征作为输入。双通道Transformer模型将数据的时域和频域信号分别通过Transformer模型,这种替代不仅可以提取时间特征,还可以提取空间特征。实验结果表明,所提出的模型可以提供高达95.36%的诊断准确率,证明其在电机故障诊断中的有效性。与传统的单信号故障诊断方法相比,该模型具有更好的鲁棒性和准确性。

基于Transformer模型与注意力机制的差分密码分析

基于差分分析的密码攻击中,通常使用贝叶斯优化方法验证部分解密的数据是否具有差分特性。目前,主要采用基于深度学习的方式训练1个差分区分器,但随着加密轮数的增加,差分特征的精确度会呈现线性降低的趋势。为此,结合注意力机制和侧信道分析,提出了一种新的差分特性判别方法。根据多轮密文间的差分关系,基于Transformer训练了1个针对SPECK32/64算法的差分区分器。在密钥恢复攻击中,借助前一轮的密文对待区分密文影响最大特性,设计了新的密钥恢复攻击方案。在SPECK32/64算法的密钥恢复攻击中,采用26个选择明密文对,并借助第20轮密文对将第22轮65536个候选密钥范围缩小至17个以内,完成对最后两轮子密钥的恢复攻击。实验结果表明,该方法的攻击成功率达90%,可以有效应对加密轮数增多造成的密文差分特征难以识别的问题。

基于CNN和Transformer的轻量化电能质量扰动识别模型

针对目前基于深度学习的电能质量扰动(power quality disturbances,PQDs)识别模型参数量多和计算复杂度较高的问题,文中提出了一种卷积神经网络(convolutional neural networks,CNN)融合Transformer(CNN and Transformer,CaT)的轻量化PQDs识别模型。首先,利用深度可分离卷积初步提取扰动信号的局部特征;其次,提出一种高效的软阈值模块,在不显著增加模型参数量与计算复杂度的同时减少特征中的噪声与冗余特征;然后,利用Transformer模型挖掘PQDs信号的全局特征;最后,通过池化层、线性层和Softmax层完成PQDs识别。仿真实验表明,文中所提CaT模型在参数量和浮点运算数较少的情况下能够有效完成PQDs识别,对PQDs信号识别准确率高,具有良好的噪声鲁棒性。同时,得益于轻量化和端到端的模型设计,CaT模型相对于其他深度学习模型的推理时间更短。

Application of Elzaki Transform Method to Market Volatility Using the Black-Scholes Model

Black-Scholes Model (B-SM) simulates the dynamics of financial market and contains instruments such as options and puts which are major indices requiring solution. B-SM is known to estimate the correct prices of European Stock options and establish the theoretical foundation for Option pricing. Therefore, this paper evaluates the Black-Schole model in simulating the European call in a cash flow in the dependent drift and focuses on obtaining analytic and then approximate solution for the model. The work also examines Fokker Planck Equation (FPE) and extracts the link between FPE and B-SM for non equilibrium systems. The B-SM is then solved via the Elzaki transform method (ETM). The computational procedures were obtained using MAPLE 18 with the solution provided in the form of convergent series.

Test-driven verification/validation of model transformations

Why is it important to verify/validate model transformations？ The motivation is to improve the quality of the trans- formations, and therefore the quality of the generated software artifacts. Verified/validated model transformations make it possible to ensure certain properties of the generated software artifacts. In this way, verification/validation methods can guarantee different requirements stated by the actual domain against the generated/modified/optimized software products. For example, a verified/ validated model transformation can ensure the preservation of certain properties during the model-to-model transformation. This paper emphasizes the necessity of methods that make model transformation verified/validated, discusses the different scenarios of model transformation verification and validation, and introduces the principles of a novel test-driven method for verifying/ validating model transformations. We provide a solution that makes it possible to automatically generate test input models for model transformations. Furthermore, we collect and discuss the actual open issues in the field of verification/validation of model transformations.

Pragmatic model transformations for refactoring in Scilab/Xcos

Model-Based Development has become an industry wide standard paradigm.As an open source alternative,Scilab/Xcos is being widely employed as a hybrid dynamic systems modeling tool.With the increasing efficiency in implementation using graphical model development and code generation,the modeling and simulation community is struggling with assuring quality as well as maintainability and extendibility.Refactoring is defined as an evolutionary modernization activity where,most of the time,the structure of the artifact is changed to alter its quality characteristics,while keeping its behavior unchanged.It has been widely established as a technique for textual programming languages to improve the code structure and quality.While refactoring is also regarded as one of the key practices of model engineering,the methodologies and approaches for model refactoring are still under development.Architecture-Driven Modernization(ADM)has been introduced by the software engineering community as a model-based approach to software modernization,in which the implicit information that lies in software artifacts is extracted to models and model transformations are applied for modernization tasks.Regarding refactoring as a low level modernization task,the practices from ADM are adaptable.Accordingly,this paper proposes a model-based approach for model refactoring in order to come up with more efficient and effective model refactoring methodology that is accessible and extendable by modelers.Like other graphical modeling tools,Scilab/Xcos also possesses a formalized model specification conforming to its implicit metamodel.Rather than proposing another metamodel for knowledge extraction,this pragmatic approach proposes to conduct in place model-to-model transformations for refactoring employing the Scilab/Xcos model specification.To construct a structured model-based approach,the implicit Scilab/Xcos metamodel is explicitly presented utilizing ECORE as a meta-metamodel.Then a practical model transformation approach is established based on Scilab scripting.A Scilab toolset is provided to the modeler for in-place model-to-model transformations.Using a sample case study,it is demonstrated that proposed model transformation functions in Scilab provide a valuable refactoring tool.

Generating native user interfaces for multiple devices by means of model transformation

In the last years, the types of devices used to access information systems have notably increased using different operating systems, screen sizes, interaction mechanisms, and software features. This device fragmentation is an important issue to tackle when developing native mobile service front-end applications. To address this issue,we propose the generation of native user interfaces(UIs) by means of model transformations, following the modelbased user interface(MBUI) paradigm. The resulting MBUI framework, called LIZARD, generates applications for multiple target platforms. LIZARD allows the definition of applications at a high level of abstraction, and applies model transformations to generate the target native UI considering the specific features of target platforms. The generated applications follow the UI design guidelines and the architectural and design patterns specified by the corresponding operating system manufacturer. The objective is not to generate generic applications following the lowest-common-denominator approach, but to follow the particular guidelines specified for each target device. We present an example application modeled in LIZARD, generating different UIs for Windows Phone and two types of Android devices(smartphones and tablets).

基于RoBERTa和图增强Transformer的序列推荐方法

自推荐系统出现以来,有限的数据信息就一直制约着推荐算法的进一步发展。为降低数据稀疏性的影响,增强非评分数据的利用率,基于神经网络的文本推荐模型相继被提出,但主流的卷积或循环神经网络在文本语义理解和长距离关系捕捉方面存在明显劣势。为了更好地挖掘用户与商品之间的深层潜在特征,进一步提高推荐质量,提出一种基于Ro BERTa和图增强Transformer的序列推荐(RGT)模型。引入评论文本数据,首先利用预训练的Ro BERTa模型捕获评论文本中的字词语义特征,初步建模用户的个性化兴趣,然后根据用户与商品的历史交互信息,构建具有时序特性的商品关联图注意力机制网络模型,通过图增强Transformer的方法将图模型学习到的各个商品的特征表示以序列的形式输入Transformer编码层,最后将得到的输出向量与之前捕获的语义表征以及计算得到的商品关联图的全图表征输入全连接层,以捕获用户全局的兴趣偏好,实现用户对商品的预测评分。在3组真实亚马逊公开数据集上的实验结果表明,与Deep FM、Conv MF等经典文本推荐模型相比,RGT模型在均方根误差(RMSE)和平均绝对误差(MAE)2种指标上有显著提升,相较于最优对比模型最高分别提升4.7%和5.3%。

基于多模态掩码Transformer网络的社会事件分类

多模态社会事件分类的关键是充分且准确地利用图像和文字2种模态的特征。然而,现有的大多数方法存在以下局限性:简单地将事件的图像特征和文本特征连接起来,不同模态之间存在不相关的上下文信息导致相互干扰。因此,仅仅考虑多模态数据模态间的关系是不够的,还要考虑模态之间不相关的上下文信息(即区域或单词)。为克服这些局限性,提出一种新颖的基于多模态掩码Transformer网络(MMTN)模型的社会事件分类方法。通过图-文编码网络来学习文本和图像的更好的表示。将获得的图像和文本表示输入多模态掩码Transformer网络来融合多模态信息,并通过计算多模态信息之间的相似性,对多模态信息的模态间的关系进行建模,掩盖模态之间的不相关上下文。在2个基准数据集上的大量实验表明:所提模型达到了最先进的性能。

考虑特征重组与改进Transformer的风电功率短期日前预测方法

短期日前风电功率预测对电力系统调度计划制定有重要意义,该文为提高风电功率预测的准确性,提出了一种基于Transformer的预测模型Powerformer。模型通过因果注意力机制挖掘序列的时序依赖;通过去平稳化模块优化因果注意力以提高数据本身的可预测性;通过设计趋势增强和周期增强模块提高模型的预测能力;通过改进解码器的多头注意力层,使模型提取周期特征和趋势特征。该文首先对风电数据进行预处理,采用完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)将风电数据序列分解为不同频率的本征模态函数并计算其样本熵,使得风电功率序列重组为周期序列和趋势序列,然后将序列输入到Powerformer模型,实现对风电功率短期日前准确预测。结果表明,虽然训练时间长于已有预测模型,但Poweformer模型预测精度得到提升;同时,消融实验结果验证了模型各模块的必要性和有效性,具有一定的应用价值。

基于遥感多参数和CNN-Transformer的冬小麦单产估测

为了提高冬小麦单产估测精度,改善估产模型存在的高产低估和低产高估等现象,以陕西省关中平原为研究区域,选取旬尺度条件植被温度指数(VTCI)、叶面积指数(LAI)和光合有效辐射吸收比率(FPAR)为遥感特征参数,结合卷积神经网络(CNN)局部特征提取能力和基于自注意力机制的Transformer网络的全局信息提取能力,构建CNN-Transformer深度学习模型,用于估测关中平原冬小麦产量。与Transformer模型(R^(2)为0.64,RMSE为465.40 kg/hm^(2),MAPE为8.04%)相比,CNN-Transformer模型具有更高的冬小麦单产估测精度(R^(2)为0.70,RMSE为420.39 kg/hm^(2),MAPE为7.65%),能够从遥感多参数中提取更多与产量相关的信息,且对于Transformer模型存在的高产低估和低产高估现象均有所改善。基于5折交叉验证法和留一法进一步验证了CNN-Transformer模型的鲁棒性和泛化能力。此外,基于CNN-Transformer模型捕获冬小麦生长过程的累积效应,分析逐步累积旬尺度输入参数对产量估测的影响,评估模型对于冬小麦不同生长阶段的累积过程的表征能力。结果表明,模型能有效捕捉冬小麦生长的关键时期,3月下旬至5月上旬是冬小麦生长的关键时期。

基于Swin Transformer和CNN的汉字书法教学系统

针对日益增长的汉字书法学习需求,将滑动窗口自注意力(Swin Transformer,ST)模型和卷积神经网络(Convolutional Neural Network,CNN)模型相结合,提出手写体汉字识别ST-CNN模型,进而开发了汉字书法教学系统。实测结果表明,ST-CNN模型识别准确率约为91.6%,较传统的ST模型提升了约0.5个百分点,较传统的CNN模型与ST模型,在收敛速度上分别提升了约10和30个百分点,开发的汉字书法教学系统性能良好。