检索结果-内蒙古大学图书馆

AIAA SciTech Forum

作者： Liu, Xin Liu, Bangde Tian, Su Yu, Wenbin Univ Texas Arlington Dept Mech & Aerosp Engn Arlington TX 76019 USA Univ Texas Arlington Dept Ind Mfg & Syst Engn Arlington TX 76019 USA AnalySwift LLC W Lafayette IN 47906 USA Purdue Univ Sch Aeronaut & Astronaut W Lafayette IN 47906 USA

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

Tow-steered composites, with their curvilinear fiber paths, have the potential to significantly enhance structural performance. Nevertheless, their development is impeded by the absence of dedicated computational tools and the considerable computational effort required to probe the vast design space of aerospace structures. To address these issues, an integrated design tool is developed as a plug-in code in commercial finite element (FE) software packages. A new machine learning (ML) module is developed in the plug-in code to provide a cost-effective surrogate model to diminish computational demands. To reduce the computational cost, a mixed-fidelity model and a transfer learning model are developed, both of which utilize varying mesh densities within FE modeling to create coarse mesh, i.e., low-fidelity datasets, and fine mesh, i.e., high-fidelity datasets. The accuracy and efficiency of these ML models are evaluated against a high-fidelity FE model. The findings reveal that the mixed-fidelity and transfer learning models achieve similar accuracy to a high-fidelity FE model and markedly enhance efficiency over the single-fidelity ML model.

关键词： Laminated Composites Neural Networks Bayesian optimization Reduced Order Modelling Aerospace Structure Nastran Design optimization Finite Element Analysis Structural Analysis optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning-Based Model for Classification of Wheat Gene Expression

引用

Computer Systems Science & Engineering 2024年第2期48卷 273-285页

作者： Amr Ismail WalidHamdy Aya MAl-Zoghby Wael AAwad Ahmed Ismail Ebada Yunyoung Nam Byeong-Gwon Kang Mohamed Abouhawwash Faculty of Science Port Said UniversityPort SaidEgypt Modern Academy for Computer Science and Management Technology Cairo11742Egypt Faculty of Computers and Artificial Intelligence Damietta UniversityNew DamiettaEgypt Department of ICT Convergence Soonchunhyang UniversityAsan31538South Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

Deep learning(DL)plays a critical role in processing and converting data into knowledge and *** technologies have been applied in a variety of applications,including image,video,and genome sequence *** deep learning the most widely utilized architecture is Convolutional Neural Networks(CNN)are taught discriminatory traits in a supervised *** comparison to other classic neural networks,CNN makes use of a limited number of artificial neurons,therefore it is ideal for the recognition and processing of wheat gene *** is an essential crop of cereals for people around the *** Genotypes identification has an impact on the possible development of many countries in the agricultural *** quantitative genetics prediction of genetic values is a central *** is an allohexaploid(AABBDD)with three distinct *** sizes of the wheat genome are quite large compared to many other kinds and the availability of a diversity of genetic knowledge and normal structure at breeding lines of wheat,Therefore,genome sequence approaches based on techniques of Artificial Intelligence(AI)are *** paper focuses on using the Wheat genome sequence will assist wheat producers in making better use of their genetic resources and managing genetic variation in their breeding program,as well as propose a novel model based on deep learning for offering a fundamental overview of genomic prediction theory and current *** this paper,the hyperparameters of the network are optimized in the CNN to decrease the requirement for manual search and enhance network performance using a new proposed model built on an optimization algorithm and Convolutional Neural Networks(CNN).

关键词： Gene expression convolutional neural network optimization algorithm genomic prediction wheat

来源：评论

学校读者我要写书评

暂无评论

Assembly Level Topology optimization Towards a Part Consolidation algorithm for Additive Manufacturing

Assembly Level Topology Optimization Towards a Part Consolid...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech)

作者： Crispo, Luke Kim, Il Yong Queens Univ Dept Mech & Mat Engn Kingston ON Canada

ISBN: (数字)9781624105951

ISBN: (纸本)9781624105951

As the adoption of additive manufacturing continues to grow in the aerospace industry, part consolidation is an emerging design technique aimed at decreasing assembly cost. Significant research is focused on design for additive manufacturing principles and their integration into design generation tools such as topology optimization, while part consolidation research has been limited to heuristic guidelines. This work presents the extension of topology optimization to assembly design for the simultaneous optimization of structural performance and connection layout. This methodology uses multiple domains occupying the same space along with a single joining domain to represent the assembly design. The proposed approach allows for future extensions with the calculation of additive manufacturing part costs on an individual domain level. The methodology is tested on a numerical example demonstrating the variation in part geometry and number of parts as the emphasis on joining cost is varied.

关键词： Topology optimization Aerospace Industry Stiffness Matrices Elastic Modulus Messerschmitt Bolkow Blohm optimization algorithm Structural optimization Manufacturing Cost Material Properties MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Genetic algorithm based Approach for the optimization of Multiple Sequence Alignment

A Genetic Algorithm based Approach for the Optimization of M...

引用

International Conference on Computational Performance Evaluation (ComPE)

作者： Mishra, Arunima Tripathi, B. K. Soam, Sudhir Singh AKTU Lucknow Uttar Pradesh India REC Bijnor India IET Lucknow Lucknow Uttar Pradesh India

ISBN: (数字)9781728166445

ISBN: (纸本)9781728166445

Multiple sequence alignment (MSA) is an elementary task of bioinformatics where the alignment of three or more biological sequences is produced in a way that helps to identify the homologous regions in the sequences. This research paper proposes a genetic algorithm-based optimization approach that can enhance the value of multiple sequence alignment (MSA) generated by the progressive technique. Mutation operators like gap insertion mutation and gap removal mutations are applied to enhance the value of the MSA obtained by the progressive technique of alignment.

关键词： Multiple sequence alignment Genetic algorithms optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimized Tuning of LOADng Routing Protocol Parameters for IoT

引用

Computer Systems Science & Engineering 2023年第8期46卷 1549-1561页

作者： Divya Sharma Sanjay Jain Vivek Maik Department of Electronics and Communication New Horizon College of EngineeringBengaluru560103India CMR Institute of Technology Bengaluru560037India Department of Electronics and Communication SRM Institute of Science and TechnologyKattankulathurChennai603203India

Interconnected devices and intelligent applications have slashed human intervention in the Internet of Things(IoT),making it possible to accomplish tasks with less human ***,it faces many problems,including lower capacity links,energy utilization,enhancement of resources and limited resources due to its openness,heterogeneity,limited resources and *** is challenging to route packets in such a constrained *** an IoT network constrained by limited resources,minimal routing control overhead is required without packet *** constrained environments can be improved through the optimal routing *** is challenging to route packets in such a constrained ***,this work is motivated to present an efficient routing protocol for enhancing the lifetime of the IoT *** On-demand Ad hoc Distance-vector Routing Protocol—Next Generation(LOADng)protocol is an extended version of the Ad Hoc On-Demand Distance Vector(AODV)*** AODV,LOADng is a lighter version that forbids the intermediate nodes on the route to send a route reply(RREP)for the route request(RREQ),which originated from the source.A resource-constrained IoT network demands minimal routing control overhead and faster packet ***,in this paper,the parameters of the LOADng routing protocol are optimized using the black widow optimization(BWO)algorithm to reduce the control overhead and ***,the performance of the proposed model is analyzed with the default LOADng in terms of delay,delivery ratio and *** results show that the LOADng-BWO protocol outperforms the conventional LOADng protocol.

关键词： Internet of things optimization algorithm routing protocol LOADng

来源：评论

学校读者我要写书评

暂无评论

An evolutionary-assisted machine learningmodel for global solar radiation prediction in Minas Gerais region, southeastern Brazilsoutheastern Brazil

引用

EARTH SCIENCE INFORMATICS 2023年第3期16卷 2049页

作者： Basilio, Samuel da Costa Alves Putti, Fernando Ferrari Cunha, Angelica Carvalho Goliatt, Leonardo Fed Ctr Technol Educ Minas Gerais Dept Comp & Mech Rua Jose Peres 558 BR-36700000 Leopoldina MG Brazil Univ Fed Juiz de Fora Computat Modeling Program Rua Jose Lourenco Kelmer BR-36036900 Juiz De Fora MG Brazil Sao Paulo State Univ Sch Sci & Engn Rua Domingos Costa Lopes 780 BR-17602496 Tupa SP Brazil

Solar radiation prediction is necessary for designing photovoltaic systems, assessment of regional climate and crop growth modeling. However, this estimate depends on expensive devices, namely pyranometer and pyranometer. Considering the difficulty of acquiring these devices, predicting such values through mathematical and computational models is a convenient approach where costs can be reduced. In particular, machine learning methods have been successfully and widely applied for this task. However, the choice of the correct machine learning model, its parameters sets, and the variables used influence obtained results. This work presents a methodology that optimizes the aforementioned points to efficiently predict solar radiation in the state of Minas Gerais, Brazil. Currently, no work presents a computational model for the entire state. For this, data from 51 cities in Minas Gerais are used, obtained by the automatic weather stations of the National Institute of Meteorology. Two machine learning models, Artificial Neural Network and Multivariate Adaptive Regression Spline, were optimized through a Simple Genetic algorithm, and the results compared to those available in the literature. The best results were found at the Guanhaes station, with R-2 of 0.867 and RMSE of 1.68 MJ m(-2) day(-1), and at the Muriae station, with R-2 of 0.864 and RMSE of 1.64 MJ m(-2) day(-1). The models had their metrics compared to each other through the methodology of performance profiles, where the Multivariate Adaptive Regression Spline model proved to be more efficient. The results demonstrate that computational models perform better than the empirical models currently used.

关键词： Solar radiation Predictive model optimization algorithm Hybrid approach

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Feature Selection for Multi-target Regression Problems

引用

SN Computer Science 2025年第5期6卷 1-15页

作者： Kanouté, Mamadou Grall-Maës, Edith Beauseroy, Pierre Computer Science and Digital Society Laboratory (LIST3N) University of Technology of Troyes Troyes France

When designing an inference model, feature selection methods can be used to select a subset of relevant variables from the original set of variables to increase the performance and reduce the complexity of the model. In this work, a new feature selection method exploiting nonlinear relationships between variables is introduced in the context of multi-target regression problems. The proposed approach is based on a neural network with one hidden layer in which a regularization term is introduced to enforce variable selection. Experiments on synthetic and real-world datasets show the effectiveness of the proposed approach. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Mathematical computation Multi-output regression Neural network optimization algorithm Supervised nonlinear feature selection

来源：评论

学校读者我要写书评

暂无评论

Multi-objectives nonlinear structure optimization for actuator in trajectory correction fuze subject to high impact loadings

引用

Defence Technology（防务技术） 2021年第4期17卷 1338-1351页

作者： Jiang-hai Hui Min Gao Ming Li Ming-rui Li Hui-hui Zou Gang Zhou Northwest Institute of Nuclear Technology Xi’an710025China Shijiazhuang Campus Army Engineering UniversityShijiazhuang050003China

This paper presents an actuator used for the trajectory correction fuze,which is subject to high impact loadings during launch.A simulation method is carried out to obtain the peak-peak stress value of each component,from which the ball bearings are possible failures according to the ***,three schemes against impact loadings,full-element deep groove ball bearing and integrated raceway,needle roller thrust bearing assembly,and gaskets are utilized for redesigning the actuator to effectively reduce the bearings’***,multi-objectives optimization still needs to be conducted for the gaskets to decrease the stress value further to the yield *** gasket’s structure parameters and three bearings’peak-peak stress are served as the four optimization variables and three objectives,*** Latin hypercube design is used for generating sample points,and Kriging model selected according to estimation result can establish the relationship between the variables and objectives,representing the simulation which is ***,two optimization algorithms work out the Pareto solutions,from which the best solutions are selected,and verified by the simulation to determine the gaskets optimized structure *** can be concluded that the simulation and optimization method based on these components is effective and efficient.

关键词： Actuator Trajectory correction fuze Impact loadings Optimized Latin hypercube design Kriging model optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Improving the Feature Section Method Based on Genetic algorithm to Increase the Efficiency of Detecting Phishing Websites

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2023年第3期57卷 213-221页

作者： Davoudi, Mohamad Reza Yari, Ali Reza Islamic Azad Univ Dept Informat Technol Engn Sci & Res Branch Tehran Iran ICT Res Inst Informat Technol Res Fac Tehran Iran

Phishing is a term for unauthorized access to users' confidential information such as password, username, and credit card information. Today, the internet has become an essential need, and most of the requirements are provided through the internet. For this reason, phishers deceive users on the internet in various ways, such as social engineering, and steal their confidential information. Therefore, designing a method to deal with phishing is essential. However, if a phishing detection system only has high accuracy and ignores the time required to detect phishing, it will cause lengthy delays. In this research, phishing, anti-phishing, and feature selection methods are introduced. In the following, a data set containing 30 features of phishing and legal websites was prepared. Then we presented an effective method for feature selection based on Genetic algorithm to deal with phishing, which can reduce the phishing detection time and maintain accuracy. Finally, the results show that the proposed method can achieve a detection time of about 0.46 s and an accuracy of 96.04%, which is better than existing research.

关键词： feature reduction optimization algorithm machine learning data mining

来源：评论

学校读者我要写书评

暂无评论

A Multimodel Transfer-Learning-Based Car Price Prediction Model with an Automatic Fuzzy Logic Parameter Optimizer

引用

Computer Systems Science & Engineering 2023年第8期46卷 1577-1596页

作者： Ping-Huan Kuo Sing-Yan Chen Her-Terng Yau Department of Mechanical Engineering National Chung Cheng UniversityChiayi62102TaiwanChina Advanced Institute of Manufacturing with High-Tech Innovations(AIM-HI) National Chung Cheng UniversityChiayi62102TaiwanChina

Cars are regarded as an indispensable means of transportation in *** studies have indicated that the automotive industry has witnessed remarkable advances and that the market of used cars has rapidly *** this study,a price prediction system for used BMW cars was *** parameters of used cars,including their model,registration year,and transmission style,were *** data obtained were then divided into three *** first subset was used to compare the results of each *** predicted values produced by the two algorithms with the most satisfactory results were used as the input of a fully connected neural *** second subset was used with an optimization algorithm to modify the number of hidden layers in a fully connected neural network and modify the low,medium,and high parameters of the membership function(MF)to achieve model ***,the third subset was used for the validation set during the prediction *** three subsets were divided using k-fold cross-validation to avoid overfitting and selection *** conclusion,in this study,a model combining two optimal algorithms(i.e.,random forest and k-nearest neighbors)with several optimization algorithms(i.e.,gray wolf optimizer,multilayer perceptron,and MF)was successfully *** prediction results obtained indicated a mean square error of 0.0978,a root-mean-square error of 0.3128,a mean absolute error of 0.1903,and a coefficient of determination of 0.9249.

关键词： Used car price prediction transfer learning fuzzy logic machine learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：