检索结果-内蒙古大学图书馆

Rectangular multiple-relaxation-time lattice Boltzmann method for the Navier-Stokes and nonlinear convection-diffusion equations: General equilibrium and some important issues

引用

Physical Review E 2023年第1期108卷 015304-015304页

作者： Zhenhua Chai (柴振华) Xiaolei Yuan (袁晓垒) Baochang Shi (施保昌) School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan 430074 China Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology Wuhan 430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan 430074 China College of Mathematics and Information Science Hebei University Baoding 071002 China

In this paper, we develop a general rectangular multiple-relaxation-time lattice Boltzmann (RMRT-LB) method for the Navier-Stokes equations (NSEs) and nonlinear convection-diffusion equation (NCDE) by extending our recent unified framework of the multiple-relaxation-time lattice Boltzmann (MRT-LB) method [Chai and Shi, Phys. Rev. E 102, 023306 (2020)], where an equilibrium distribution function (EDF) [Lu et al., Philos. Trans. R. Soc. A 369, 2311 (2011)] on a rectangular lattice is utilized. The anisotropy of the lattice tensor on a rectangular lattice leads to anisotropy of the third-order moment of the EDF, which is inconsistent with the isotropy of the viscous stress tensor of the NSEs. To eliminate this inconsistency, we extend the relaxation matrix related to the dynamic and bulk viscosities. As a result, the macroscopic NSEs can be recovered from the RMRT-LB method through the direct Taylor expansion method. Whereas the rectangular lattice does not lead to the change of the zero-, first- and second-order moments of the EDF, the unified framework of the MRT-LB method can be directly applied to the NCDE. It should be noted that the RMRT-LB model for NSEs can be derived on the rDdQq (q discrete velocities in d-dimensional space, d≥1) lattice, including rD2Q9, rD3Q19, and rD3Q27 lattices, while there are no rectangular D3Q13 and D3Q15 lattices within this framework of the RMRT-LB method. Thanks to the block-lower triangular relaxation matrix introduced in the unified framework, the RMRT-LB versions (if existing) of the previous MRT-LB models can be obtained, including those based on raw (natural) moment, central moment, Hermite moment, and central Hermite moment. It is also found that when the parameter cs is an adjustable parameter in the standard or rectangular lattice, the present RMRT-LB method becomes a kind of MRT-LB method for the NSEs and NCDE, and the commonly used MRT-LB models on the DdQq lattice are only its special cases. We also perform some numeric

关键词： Lattice-Boltzmann methods

来源：评论

学校读者我要写书评

暂无评论

Using Contextual Text Mining and Ontology Methods to Establish a Novel technology Trend and Associative Analysis Framework for Sustainable Energy Development in Taiwan

Using Contextual Text Mining and Ontology Methods to Establi...

引用

IEEE International Conference on Big Data

作者： Yi-Hao Hsiao Chia-Yi Chuang Megn-Chi Huang Chia-Lee Yang Jyh-Horng Wu National Center for High-Performance Computing National Applied Research Laboratories Hsinchu Taiwan Science & Technology Policy Research and Information Center National Applied Research Laboratories Taipei Taiwan

ISBN: (纸本)9781665480468

In 2015, the United Nations proposed 17 Sustainable Development Goals, SDGs, as the guidelines for all countries in the world to promote sustainable development before 2030. Government Research Bulletin (GRB), the research projects and technical reports sponsored by government, which has long-term, numerous, complete research method, technology development and policy analysis information in Taiwan. Therefore, it is an important and effective way to explore SDG-related information from a large amount of GRB text. In this paper, a novel technologies trend and associative analysis framework which uses contextual text mining and ontology methods is proposed and applied to SDG 7, which "Affordable and Clean Energy". First, we integrate dictionary-based method and semantic textual similarity analysis algorithm to obtain a SDG 7 classifier which can exactly and quickly classify a large amount number of GRB text to SDG 7. Then, two major SDG 7 analysis procedures based on the classification results are implemented. One is using contextual text mining algorithm to obtain energy technologies trend information. The other is adopting ontology method to establish energy technologies associative analysis concept map. According to the analysis results mentioned above, we are able to efficiently incorporate the energy technology with long-term trend, energy technology associative information, and the most influential authors on the specify energy technology in order to generate a global strategy for continuous improvement in Taiwan.

关键词： Text mining Government Semantics Ontologies Big Data Writing Market research

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in the Internet of Vehicles Using Transformer Models

Intrusion Detection in the Internet of Vehicles Using Transf...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Mohammad Alauthman Ashraf Mashaleh Nauman Aslam Amjad Aldweesh Ammar Almomani Department of Information Security University of Petra Jordan Al-Balqa Applied University Al-Salt Jordan Department of Computer and Information Sciences Northumbria University U.K. College of computing and IT Shaqra University Shaqra Saudi Arabia Department of Computer Information Science Higher Colleges of Technology UAE Al-Balqa Applied University Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

The proliferation of Internet of Vehicles (IoV) systems has introduced critical cybersecurity vulnerabilities in connected vehicle infrastructures. This paper presents a novel application of Transformer architecture for intrusion detection in vehicular Controller Area Network (CAN) buses, specifically addressing Denial-of-Service and Spoofing attacks. We introduce a Transformer-based model optimized for CAN frame sequence analysis, evaluated on the CICIoV2024 dataset comprising real-world attack scenarios from a 2019 Ford vehicle. Our experimental results demonstrate superior detection capabilities compared to classical machine learning approaches and recurrent neural architectures, achieving 98.4% accuracy and 98.5% F1-score. The proposed architecture's self-attention mechanism effectively captures temporal dependencies in CAN frame sequences while maintaining computational efficiency (2.3ms inference time) suitable for automotive-grade ECUs. This research advances the state-of-the-art in IoV security through enhanced detection accuracy and practical deployment considerations for resource-constrained vehicular environments.

关键词： Analytical models Adaptation models Computational modeling Intrusion detection Computer architecture Machine learning Transformers Controller area networks Internet of Vehicles Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

An Integrated Deep Learning Framework for Fruits Diseases Classification

引用

Computers, Materials & Continua 2022年第4期71卷 1387-1402页

作者： Abdul Majid Muhammad Attique Khan Majed Alhaisoni Muhammad Asfand Eyar Usman Tariq Nazar Hussain Yunyoung Nam Seifedine Kadry Department of Computer Science HITEC University TaxilaTaxilaPakistan College of Computer Science and Engineering University of Ha’ilHa’ilSaudi Arabia Department of Computer Science Bahria UniversityIslamabad College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway

:Agriculture has been an important research area in the field of image processing for the last five *** affect the quality and quantity of fruits,thereby disrupting the economy of a *** computerized techniques have been introduced for detecting and recognizing fruit ***,some issues remain to be addressed,such as irrelevant features and the dimensionality of feature vectors,which increase the computational time of the ***,we propose an integrated deep learning framework for classifying fruit *** consider seven types of fruits,i.e.,apple,cherry,blueberry,grapes,peach,citrus,and *** proposed method comprises several important ***,data increase is applied,and then two different types of features are *** the first feature type,texture and color features,i.e.,classical features,are *** the second type,deep learning characteristics are extracted using a pretrained *** pretrained model is reused through transfer ***,both types of features are merged using the maximum mean value of the serial ***,the resulting fused vector is optimized using a harmonic threshold-based genetic ***,the selected features are classified using multiple *** evaluation is performed on the PlantVillage dataset,and an accuracy of 99%is achieved.A comparison with recent techniques indicate the superiority of the proposed method.

关键词： Fruit diseases data augmentation deep learning classical features features fusion features selection

来源：评论

学校读者我要写书评

暂无评论

Collaborative Filtering Approach for Movie Recommendations 19

Collaborative Filtering Approach for Movie Recommendations

引用

19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information technology, ECTI-CON 2022

作者： Mohamad, Anis Yasmin Harun, Siti Raisah Shahidan, Nur Anis Alisa Nanthaamornphong, Aziz Mustapha, Aida Wahab, Mohd Helmy Abdul Universiti Tun Hussein Onn Malaysia Faculty of Applied Sciences and Technology Johor Malaysia Prince of Songkla University Andaman Intelligent Tourism and Service Informatics Center College of Computing Phuket Thailand Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Johor Malaysia

ISBN: (纸本)9781665485845

This paper describes the development of a movies recommendation system by considering the history of the movie watched by the users through the collaborative filtering approach. This analysis are based on two datasets: the movies dataset and the ratings dataset with a total of 10,329 movie titles. Next, the matrix of the movie genre is built, and the search matrix is produced with 18 genres identified. The other matrices such as user and movie similarities matrices were created to ease the analysis of filtering. The visualization results showed that the movie Pulp Fiction has the greatest number of viewers, which is 325 views. The item-based collaborative filtering approach is also used to predict the movie to be recommended and the result revealed that two movies;Get Shorty (1995) and Bad Boys (1995) are highly recommended by the users. The item-based collaborative filtering helps the users to filter the movies according to their preference. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Application of Electrical Network Frequency as an Entropy Generator in Distributed Systems

Application of Electrical Network Frequency as an Entropy Ge...

引用

2023 IEEE National Aerospace and Electronics Conference, NAECON 2023

作者： Nagothu, Deeraj Xu, Ronghua Chen, Yu Blasch, Erik Ardiles-Cruz, Erika Intelligent Fusion Technology Inc. GermantownMD20876 United States Michigan Technological University Dept. of Applied Computing HoughtonMI49931 United States Binghamton University Dept. of Electrical and Computer Engineering BinghamtonNY13902 United States The U.S. Air Force Research Laboratory RomeNY13441 United States

ISBN: (纸本)9798350338782

The development of public information technology (IT) infrastructures using modern edge devices has revolutionized the smart city ecosystem. As the number of devices in the ecosystem exponentially increases, the power grid infrastructure has continued to function as the backbone of smart cities and support the growing requirements for electricity, such as multimedia services. Media authentication technology leveraging the power system frequency, the Electrical Network Frequency (ENF) signal, has gained traction as an environmental fingerprint to counteract visual layer attacks targeted toward multimedia-based edge devices. Due to the unique and similar fluctuation patterns throughout the grid, the ENF signal is reliable in applications like multimedia synchronization, authentication, and source identification. ENF -based systems are inevitably targeted by perpetrators to bypass their detection schemes;however, such attacks are successful only if the ENF fingerprint can be pre-dicted. In this work, we studied the randomization nature of ENF signals and the societal impacts on its fluctuation patterns due to power grid consumption. Leveraging the ENF signal fluctuations, we integrate ENF as a source of randomness for the Random Bit Generator (RBG) system in cryptographic applications. An RBG-based encrypted communication and committee election mechanism is proposed for an enhanced distribution multimedia system. The paper further discusses the potential applications of the ENF -based randomness generator. © 2023 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Bi-Directional Transformers vs. word2vec: Discovering Vulnerabilities in Lifted Compiled Code

arXiv

引用

arXiv 2024年

作者： McCully, Gary A. Hastings, John D. Xu, Shengjie Fortier, Adam The Beacom College of Computer and Cyber Sciences Dakota State University MadisonSD United States Department of Cyber Intelligence and Information Operations College of Applied Science & Technology University of Arizona TucsonAZ United States College of Computing Georgia Institute of Technology AtlantaGA United States

Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM IR) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 48k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformers (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. Word2vec Skip-Gram models achieved 92% validation accuracy in detecting vulnerabilities, outperforming word2vec Continuous Bag of Words (CBOW), BERT, and RoBERTa. This suggests that complex contextual embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 48K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Bird Swarm Algorithm with Fuzzy Min-Max Neural Network for Financial Crisis Prediction

引用

Computers, Materials & Continua 2022年第10期73卷 1541-1555页

作者： K.Pradeep Mohan Kumar S.Dhanasekaran I.S.Hephzi Punithavathi P.Duraipandy Ashit Kumar Dutta Irina V.Pustokhina Denis A.Pustokhin Department of Computing Technologies Associate ProfessorSRM Institute of Science and TechnologyKattankulathur603203India Department of Information Technology Kalasalingam Academy of Research and Education626126India Department of Computer Science and Engineering Sphoorthy Engineering CollegeHyderabadTelangana501510India Department of Electrical and Electronics Engineering J B Institute of Engineering and TechnologyHyderabadTelangana500075India Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Kingdom of Saudi Arabia Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics117997MoscowRussia Department of Logistics State University of Management109542MoscowRussia

Financial crisis prediction(FCP)models are used for predicting or forecasting the financial status of a company or financial *** is considered a challenging issue in the financial *** and machine learning(ML)models can be employed for the design of accurate FCP *** numerous works have existed in the literature,it is needed to design effective FCP models adaptable to different *** study designs a new bird swarm algorithm(BSA)with fuzzy min-max neural network(FMM-NN)model,named BSA-FMMNN for *** major intention of the BSA-FMMNN model is to determine the financial status of a firm or *** presented BSA-FMMNN model primarily undergoes minmax normalization to transform the data into uniformity ***,k-medoid clustering approach is employed for the outlier removal ***,the classification process is carried out using the FMMNN model,and the parameters involved in it are tuned by the use of *** utilization of proficient parameter selection process using BSA demonstrate the novelty of the *** experimental result analysis of the BSA-FMMNN model is validated using benchmark dataset and the comparative outcomes highlighted the supremacy of the BSA-FMMNN model over the recent approaches.

关键词： Financial crisis predictive model machine learning outlier removal clustering metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code

arXiv

引用

arXiv 2024年

Ransomware and other forms of malware cause significant financial and operational damage to organizations by exploiting long-standing and often difficult-to-detect software vulnerabilities. To detect vulnerabilities such as buffer overflows in compiled code, this research investigates the application of unidirectional transformer-based embeddings, specifically GPT-2. Using a dataset of LLVM functions, we trained a GPT-2 model to generate embeddings, which were subsequently used to build LSTM neural networks to differentiate between vulnerable and non-vulnerable code. Our study reveals that embeddings from the GPT-2 model significantly outperform those from bidirectional models of BERT and RoBERTa, achieving an accuracy of 92.5% and an F1-score of 89.7%. LSTM neural networks were developed with both frozen and unfrozen embedding model layers. The model with the highest performance was achieved when the embedding layers were unfrozen. Further, the research finds that, in exploring the impact of different optimizers within this domain, the SGD optimizer demonstrates superior performance over Adam. Overall, these findings reveal important insights into the potential of unidirectional transformer-based approaches in enhancing cybersecurity defenses. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Utilizing Deep Learning in Smart Cities for Environmental Monitoring

Utilizing Deep Learning in Smart Cities for Environmental Mo...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Hoang, Dinh Cong Devi, Shova Koner, Jonardan Dhandayuthapani, Bala Choudhury, Susanta Kumar Sahoo, Deepali Rani Institute for South Asian West Asian and African Studies Department of Middle East & West Asia Studies India Amity Law School Lucknow Amity University Uttar Pradesh UP India Nicmar University Pune India College of Computing and Information Sciences University of Technology and Applied Sciences Department of It Shinas Campus Oman Gietu University Department of Civil Engineering Odisha Gunupur India Symbiosis Law School Noida India Pune India

ISBN: (纸本)9798331543617

The effectiveness and dependability of services provided by smart cities are significantly impacted by the significant and difficult issue of intrusion detection. Replay attacks, which weaken security via improper authentication in a smart city network, are among the most common threats to this infrastructure. For example, replay attacks have the potential to severely damage the smart city structure, leading to the loss of crucial data and substantial monetary losses. As a result, we have developed a model based on deep learning to predict where attacks in smart cities would be replayed. The proposed approach is intriguing since it uses deep learning-based models as an application to differentiate replay assaults and increase recognition accuracy. Replay attacks are simulated on a real-world smart city dataset, and the model's performance is assessed by using this dataset. Our findings demonstrate that the suggested model may reasonably accurately discriminate between normal and assault actions. Furthermore, our suggested model performs better than both deep learning and conventional classification models, per the findings. © 2024 IEEE.

关键词： Sustainable city

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：