检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Andrews, James Gkountouna, Olga Blaisten-Barojas, Estela Center for Simulation and Modeling George Mason University United States Department of Computational and Data Sciences George Mason University FairfaxVA22030 United States

Currently machine learning techniques including neural networks are popular tools for materials and chemical scientists with applications that may provide viable alternative methods in the analysis of structure and energetics of systems ranging from crystals to biomolecules. However, efforts are less abundant for prediction of kinetics and dynamics. Here we explore the ability of three well established recurrent neural network architectures for forecasting the energetics of a macromolecular polymer-lipid aggregate solvated in ethyl acetate at ambient conditions. The solvated 4-macromolecule aggregate is considered to be a pre-micellar formation of finite life span. Data models generated from three recurrent neural networks, ERNN, LSTM and GRU, are trained and tested on nanoseconds-long time series of the intra-macromolecules potential energy and their interaction energy with the solvent generated from Molecular Dynamics and containing half million points. Our exhaustive analyses convey that the three recurrent neural network architectures investigated generate data models with limited capability of reproducing the energetic fluctuations and yielding short or long term energetics forecasts with underlying distribution of points inconsistent with the input series distributions. We propose an in silico experimental protocol consisting on forming an ensemble of artificial network models trained on an ensemble of series with additional features from time series containing pre-clustered time patterns of the original series. The forecast process improves by predicting a band of forecasted time series with a spread of values consistent with the molecular dynamics energy fluctuations span. However, the distribution of points from the band of forecasts is not optimal. Although the three inspected recurrent neural networks were unable of generating single models that reproduce the actual fluctuations of the inspected molecular system energies in thermal equilibrium at the nano

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Knee Detection in Bayesian Multi-Objective Optimization Using Thompson Sampling

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Heidari, Arash Qing, Jixiang Gonzalez, Sebastian Rojas Branke, Juergen Dhaene, Tom Couckuyt, Ivo Computer Science at IDLab Ghent University Ghent Belgium Imperial College London United Kingdom Department of Computational Mathematics Data Science Institute Belgium Warwick Business School University of Warwick Coventry United Kingdom Computer Modeling and Simulation Research Group University of Antwerp Antwerp Belgium Cluster in IDLab Ghent University Belgium

Real-world problems often consist of multiple conflicting objectives to be optimized simultaneously, featuring a set of Pareto-optimal solutions. Estimating the entire Pareto front can be computationally expensive, and is not always necessary, as decision makers will likely be interested only in specific regions of the Pareto front. In the absence of knowledge about the decision maker preferences, the so-called knees in the Pareto front are considered to be particularly attractive. In this paper, we propose using Thompson Sampling in the Bayesian optimization framework to estimate the location of the knee regions in a data-efficient manner. Our experimental results show that the proposed methods accurately locate the knee regions after a very small number of evaluations, providing a computationally efficient approach to single-and multi-knee detection in multi-objective optimization. © 1997-2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

AKM-FCCI: Secure Authentication and Key Management Mechanism for Fog Computing-Based IoT-Driven Critical Infrastructure

AKM-FCCI: Secure Authentication and Key Management Mechanism...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Vijay Karnatak Neha Tripathi Amit Kumar Mishra Mohammad Wazid Ashok Kumar Das Mohsen Guizani Sachin Shetty Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad India Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE Department of Computational Modeling and Simulation Engineering Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Critical infrastructure refers to the key systems, assets, and facilities, whether they are physical or virtual, that are necessary for the overall functioning of a country. As our reliance on technology and networked systems continues to expand, so does the significance of taking precautions to protect critical infrastructure from being compromised by cyberattacks. We need some security schemes to secure the communication happening in the critical infrastructure devices. Therefore, in this paper, we focus on the design of an authentication and key establishment scheme, which is used in the critical infrastructure to secure its data transmissions. A secure authentication and key management mechanism for fog computing-based IoT-driven critical infrastructures (in short, AKM-FCCI) is proposed in the paper. We then provide the network model and threat model of the proposed AKM-FCCI to explain its deployment and organization of devices and servers. The threat model further explains the various threats of this communication environment. In addition, the security analysis of AKM-FCCI is presented to demonstrate that it is secure against the many different kinds of attacks that could be launched against it. The comparisons demonstrate that the performance of AKM-FCCI is superior to that of the other currently used schemes. In addition to that, it offers a high level of security and utility. Therefore, the proposed AKM-FCCI is appropriate for use in protecting critical infrastructure equipment against a wide variety of threats.

关键词： Threat modeling Wireless communication Performance evaluation Authentication Organizations Critical infrastructure Safety

来源：评论

学校读者我要写书评

暂无评论

EM-PAD: An Effective Mechanism for Phishing Attack Detection

EM-PAD: An Effective Mechanism for Phishing Attack Detection

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Aakash Saksham Mittal Mohammad Wazid Amit Kumar Mishra Ashok Kumar Das Sachin Shetty Mohsen Guizani Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad India Department of Computational Modeling and Simulation Engineering Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

In the present era, the increasing number of network devices and ubiquitous computing leads to the flow of enormous amounts of data traffic, including sensitive and confidential information, on the internet and carrying out commercial and banking transactions online. This gives cybercriminals an opportunity to launch an attack like phishing to steal confidential information from the user and gain unauthorized access. This can be mitigated by the help of an intelligent machine learning-based phishing detection system, which can detect potential phishing attacks and take appropriate action. In this paper, we have addressed this major cyber issue and proposed a machine learning-based phishing detection scheme (in short, EM-PAD), which is trained on a benchmark dataset and evaluated on standard metrics: F1-score and Accuracy. The proposed model is compared with different existing schemes based on Accuracy, indicating that it has outperformed them with remarkable results.

关键词： Wireless communication Measurement Accuracy Phishing computational modeling Banking Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Matrix Stiffness Regulates Mechanotransduction and Vascular Network Formation of Hipsc-Derived Endothelial Progenitors Encapsulated in 3d Hydrogels

SSRN

引用

SSRN 2025年

作者： Han, Jiwan Halwachs, Kathleen West, Toni Larsen, Bryce Sacks, Michael S. Rosales, Adrianne M. Zoldan, Janet Department of Biomedical Engineering The University of Texas at Austin AustinTX United States Department of Chemical Engineering The University of Texas at Austin AustinTX United States James T. Willerson Center for Cardiovascular Modeling and Simulation The Oden Institute for Computational Engineering and Sciences AustinTX United States

The mechanical properties of the extracellular matrix (ECM), particularly stiffness, regulate endothelial progenitor responses during vascular development, yet their behavior in physiologically compliant matrices (10 kPa), our results emphasize that vascularization is not solely driven by the most mechanotransductive environment but rather by a balance of compliance, contractility, and cell-induced remodeling. These findings underscore the need to design hydrogels that provide sufficient mechanotransduction for endothelial maturation while maintaining compliance to support dynamic vascular morphogenesis. This work provides a mechanically tuned framework for optimizing microenvironments to balance endothelial differentiation and vascular network formation in tissue engineering and regenerative medicine. © 2025, The Authors. All rights reserved.

关键词： Endothelial cells

来源：评论

学校读者我要写书评

暂无评论

A computational Pipeline for Patient-Specific Prediction of the Post-operative Mitral Valve Functional State 12th

A Computational Pipeline for Patient-Specific Prediction of...

引用

Functional Imaging and modeling of the Heart - 12th International Conference, FIMH 2023, Proceedings

作者： Liu, Hao Simonian, Natalie T. Pouch, Alison M. Gorman, III, Joseph H. Gorman, Robert C. Sacks, Michael S. James T. Willerson Center for Cardiovascular Modeling and Simulation The Oden Institute for Computational Engineering and Sciences and the Department of Biomedical Engineering The University of Texas at Austin AustinTX78712 United States Departments of Radiology and Bioengineering University of Pennsylvania PhiladelphiaPA19104 United States Gorman Cardiovascular Research Group Department of Surgery Smilow Center for Translational Research Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States

ISBN: (纸本)9783031353017

Mitral valve (MV) repair is safer than replacement for mitral regurgitation (MR) treatment, but long-term outcomes remain suboptimal and poorly understood. Moreover, preoperative optimization is complicated due to the heterogeneity of MR presentations and potential repair configurations. We thus developed a patient-specific MV computational pipeline to quantitatively predict the post-repair MV functional state using standard-of-care preoperative imaging data alone. First, we built a finite-element model of the full patient-specific MV apparatus by quantifying the MV chordae tendinae (MVCT) distributions from 5 CT-imaged excised human hearts and incorporating this data with patient-specific MV leaflet geometries and and MVCT origin displacements from preoperative 3D echocardiography. We then calibrated the leaflet and MVCT pre-strains by simulating preoperative MV closure in order to tune the functionally equivalent, patient-specific mechanical behavior. With this fully calibrated MV model, we simulated undersized ring annuloplasty (URA) by modifying the annular displacement to match the applied ring size. In all patient cases, the postoperative geometries were predicted to within 1 mm of the target, and the MV leaflet strain fields demonstrated very good global and local correspondence to results from a previous heavily validated pipeline. Additionally, our model predicted increased postoperative posterior leaflet tethering in a recurrent patient, which is the likely driver of long-term MV repair failure. This pipeline allows us to predict postoperative outcomes using strictly preoperative clinical data, which lays the foundation for quantitative surgical planning, personalized patient selection, and ultimately, more durable MV repairs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

Leveraging generative AI for urban digital twins: a scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement

引用

Urban Informatics 2024年第1期3卷 1-44页

作者： Xu, Haowen Omitaomu, Femi Sabri, Soheil Zlatanova, Sisi Li, Xiao Song, Yongze Computational Urban Sciences Group Oak Ridge National Laboratory Oak Ridge USA Urban Digital Twin Lab School of Modeling Simulation and Training University of Central Florida Orlando USA The School of Built Environment UNSW Sydney Australia Transport Studies Unit University of Oxford Oxford UK School of Design and the Built Environment Curtin University Bentley Australia

The digital transformation of modern cities by integrating advanced information, communication, and computing technologies has marked the epoch of data-driven smart city applications for efficient and sustainable urban management. Despite their effectiveness, these applications often rely on massive amounts of high-dimensional and multi-domain data for monitoring and characterizing different urban sub-systems, presenting challenges in application areas that are limited by data quality and availability, as well as costly efforts for generating urban scenarios and design alternatives. As an emerging research area in deep learning, Generative Artificial Intelligence (GenAI) models have demonstrated their unique values in content generation. This paper aims to explore the innovative integration of GenAI techniques and urban digital twins to address challenges in the planning and management of built environments with focuses on various urban sub-systems, such as transportation, energy, water, and building and infrastructure. The survey starts with the introduction of cutting-edge generative AI models, such as the Generative Adversarial Networks (GAN), Variational Autoencoders (VAEs), Generative Pre-trained Transformer (GPT), followed by a scoping review of the existing urban science applications that leverage the intelligent and autonomous capability of these techniques to facilitate the research, operations, and management of critical urban subsystems, as well as the holistic planning and design of the built environment. Based on the review, we discuss potential opportunities and technical strategies that integrate GenAI models into the next-generation urban digital twins for more intelligent, scalable, and automated smart city development and management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Technique Validation & Defense Selection Using Attack Graph & ATT&CK Matrix

Adversarial Technique Validation & Defense Selection Using A...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Md Ariful Haque Sachin Shetty Charles A. Kamhoua Kimberly Gold Computational Modeling and Simulation Engineering Old Dominion University Norfolk VA USA Network Security Research The U.S. Army Research Laboratory Adelphi MD USA Naval Surface Warfare Center Crane Division Crane IN USA

Today cyber adversaries utilize advanced techniques to victimize target assets. To tackle the adversaries, it is of utmost importance to understand potential techniques they may use to exploit network vulnerabilities. Attack graph has always been a crucial tool for network vulnerability analysis. However, the current state-of-the-art attack graph can not predict adversarial techniques. To overcome the gap, we utilize the MITRE ATT&CK matrix in this work and map the techniques with the attack graph node descriptions. We first formulate a comprehensive dataset from ATT&CK consisting of all the adversarial strategies, subtechniques, associated tactics, and mitigation for the enterprise network. We then capture the attack graph node descriptions and apply the term frequency-inverse document frequency (TF-IDF) algorithm to map the attack techniques with the available node descriptions. Next, we generate the cosine similarity to determine an adversary’s top methods to attack a network. We then map those techniques with the associated tactics and mitigation strategies as enumerated in the ATT&CK matrix. Finally, we illustrate the analysis using a networked system’s attack graph. This proposed method would help identify and validate adversarial techniques and guide in selecting mitigation mechanisms for security enhancement.

关键词： Bit error rate Transformers Security Computer crime

来源：评论

学校读者我要写书评

暂无评论

Towards a deep learning potential for anhydrous proton transport

Towards a deep learning potential for anhydrous proton trans...

引用

2020 AIChE Annual Meeting

作者： Achar, Siddarth Johnson, J. Karl Computational Modeling and Simulation Program University of Pittsburgh United States Department of Chemical Engineering University of Pittsburgh United States

ISBN: (纸本)9780816911141

Standard density functional theory (DFT) molecular dynamic (MD) simulations are prohibitively expensive in terms ofcompute time and memory requirements when the size of the physical system is larger than several hundred *** alternate approach is to develop a deep learning neural network potential that can accurately reproduce DFTenergies within an error of several 10s of meVs. Neural network potentials thus allow large-scale MD simulations formuch longer times than can be achieved with DFT-MD, but with comparable accuracy. We have used the recentlypublished DeePMD [1] formalism to develop potentials for systems relevant to modeling proton transport onfunctionalized graphane. We have used DFT-MD calculations for small structures of graphane and graphanol astraining data to build reliable machine-learned potentials. Apart from energies and forces, vibrational and thermalproperties such as phonon dispersion relations and thermal expansion coefficients from DFT-MD were used to validatethe accuracy of our trained DeePMD potentials. Our goal is to develop a machine learning potential that is able toaccurately predict proton conduction on graphanol in the complete absence of water. Previous DFT calculations haveshown that graphanol a promising candidate for anhydrous proton exchange membrane applications [2]. We seek toidentify large-scale and long-time proton hopping behavior for this system through the use of machine learningpotentials. © 2020 American Institute of Chemical Engineers. All rights reserved.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional TiNBr as photocatalyst for overall water splitting

引用

Physical Review Materials 2025年第2期9卷 025802-025802页

作者： Yatong Wang Geert Brocks Ceren Tayran Süleyman Er DIFFER – Dutch Institute for Fundamental Energy Research De Zaale 20 5612 AJ Eindhoven the Netherlands Materials Simulation and Modeling Department of Applied Physics Eindhoven University of Technology 5600 MB Eindhoven the Netherlands Computational Chemical Physics Faculty of Science and Technology and MESA+ Institute for Nanotechnology University of Twente 7500 AE Enschede the Netherlands Department of Physics Faculty of Science Gazi University Ankara 06500 Turkey

Two-dimensional (2D) Janus materials have gained increasing attention as water-splitting photocatalysts for hydrogen production. We use first-principles calculations to predict a stable 2D Janus T−TiNBr structure with strong near-ultraviolet sunlight absorption and band edges that align favorably with the water redox potentials for oxygen and hydrogen evolution. We show that the optical and electronic properties of T−TiNBr can be modulated to a certain extent by applying external uniaxial strain. Explicit calculations of the redox reactions reveal that solar-driven water splitting is viable at the N-side of T−TiNBr while the Br-side requires modifications such as vacancy creation, the application of an external potential, or adjustment of the pH conditions.

关键词： Redox reactions

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：