检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Suganya, N. Gouthami, P. Sathiya, R. Sivaranjani, S. Murugesan, M. Department of Computer Science and Business Systems Dr. N.G.P. Institute of Technology Coimbatore India Department of Information Technology Thangavelu Engineering College Chennai India Departement of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Coimbatore India Departement of Electrical and Electronics Engineering Karpagam Institute of Technology Coimbatore India

ISBN: (纸本)9798331527549

A computing system that is based on the internet and offers users all resources as on-demand services. Servers, storage, databases, software, and networking are among these on-demand services. Usually, the user must pay for the use of the resources;they are not their property. The number of people using this technology is increasing dramatically as a result of these features. Although it has benefits, cloud computing poses certain security and privacy risks. The authorized user’s data can be stolen easily. This current research thoroughly investigates modern strategies to these problems, highlighting identity management protocols, effective encryption and blockchain-based solutions. The article identifies research gaps, focuses attention to the inadequacies of current approaches, and recommends the possible ways to improve the efficiency, scalability and trustworthiness. © 2025 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

An Efficient Federated Transfer Learning Approach for Multi-UAV systems

An Efficient Federated Transfer Learning Approach for Multi-...

引用

National Conference on Communications (NCC)

作者： Vedang Bhupesh Shenvi Nadkarni Sandeep Joshi L. Rajya Lakshmi Department of Computer Science and Information Systems Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Pilani Rajasthan India

ISBN: (数字)9798331536015

ISBN: (纸本)9798331536022

Recent advances in multi-unmanned aerial vehicle (UAV) based federated learning do not take into consideration the massive computational requirements of modern deep learning models on mobile UAV s. Additionally, there has been significant progress that shows that the information transmitted between the federated agent and the central hub can be attacked to undermine the privacy of the data. We propose a novel multi-UAV-based federated transfer learning system that drastically reduces the computational burden overall, shifts it from UAV s to the ground fusion center, and reduces the bandwidth requirements while enhancing its secure nature. The proposed system makes multi-UAV learning significantly fast, reliable, power efficient, and practically feasible. Furthermore, we provide simulation and experimental results to demonstrate the effectiveness of the proposed system.

关键词： Deep learning Image segmentation Data privacy Federated learning Power supplies Transfer learning Object detection Autonomous aerial vehicles Data models Reliability

来源：评论

学校读者我要写书评

暂无评论

Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents

arXiv

引用

arXiv 2025年

作者： Kon, Patrick Tser Jern Liu, Jiachen Ding, Qiuyi Qiu, Yiming Yang, Zhenning Huang, Yibo Srinivasa, Jayanth Lee, Myungjin Chowdhury, Mosharaf Chen, Ang Department of Computer Science and Engineering University of Michigan United States Cisco Systems United States

Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain methodical control, and an experiment knowledge module to enhance interpretability. To evaluate Curie, we design a novel experimental benchmark composed of 46 questions across four computer science domains, derived from influential research papers, and widely adopted open-source projects. Compared to the strongest baseline tested, we achieve a 3.4× improvement in correctly answering experimental questions. Curie is open-sourced at https://***/Just-Curieous/Curie. © 2025, CC0.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

LLMs as Repositories of Factual Knowledge: Limitations and Solutions

arXiv

引用

arXiv 2025年

作者： Mousavi, Seyed Mahed Alghisi, Simone Riccardi, Giuseppe Signals and Interactive Systems Lab Department of Information Engineering and Computer Science University of Trento Italy

LLMs’ sources of knowledge are data snapshots containing factual information about entities collected at different timestamps and from different media types (e.g. wikis, social media, etc.). Such unstructured knowledge is subject to change due to updates through time from past to present. Equally important are the inconsistencies and inaccuracies occurring in different information sources. Consequently, the model’s knowledge about an entity may be perturbed while training over the sequence of snapshots or at inference time, resulting in inconsistent and inaccurate model performance. In this work, we study the appropriateness of Large Language Models (LLMs) as repositories of factual knowledge. We consider twenty-four state-of-the-art LLMs that are either closed-, partially (weights), or fully (weight and training data) open-source. We evaluate their reliability in responding to time-sensitive factual questions in terms of accuracy and consistency when prompts are perturbed. We further evaluate the effectiveness of state-of-the-art methods to improve LLMs’ accuracy and consistency. We then propose "ENtity-Aware Fine-tuning" (ENAF), a soft neurosymbolic approach aimed at providing structured representation of entities during fine-tuning to improve the model’s performance. © 2025, CC BY-NC-SA.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Ionized Gas in an Annular Region

引用

Communications in Mathematical Physics 2025年第6期406卷 1-42页

作者： Strauss, Walter A. Suzuki, Masahiro Department of Mathematics and Lefschetz Center for Dynamical Systems Brown University Providence USA Department of Computer Science and Engineering Nagoya Institute of Technology Nagoya Japan

We consider a plasma that is created by a high voltage difference $$\lambda $$ , which is known as a Townsend discharge. We consider it to be confined to the region $$\Omega $$ between two concentric spheres, two concentric cylinders, or more generally between two star-shaped surfaces. We first prove that if the plasma is initially relatively dilute, then either it may remain dilute for all time or it may not, depending on a certain parameter $$\kappa (\lambda , \Omega )$$ . Secondly, we prove that there is a connected one-parameter family of steady states. This family connects the non-ionized gas to a plasma, either with a sparking voltage $$\lambda ^*$$ or with very high ionization, at least in the cylindrical or spherical cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADVANCING RETRIEVAL-AUGMENTED GENERATION FOR PERSIAN: DEVELOPMENT OF LANGUAGE MODELS, COMPREHENSIVE BENCHMARKS, AND BEST PRACTICES FOR OPTIMIZATION

arXiv

引用

arXiv 2025年

作者： Hosseinbeigi, Sara Bourbour Asghari, Sina Kashani, Mohammad Ali Seif Shalchian, Mohammad Hossein Abbasi, Mohammad Amin Department of Industrial and Systems Engineering Tarbiat Modares University Tehran Iran Department of Computer Science Iran University of Science and Technology Tehran Iran Department of Computer Engineering Sharif University of Technology Tehran Iran Department of Computer Engineering Iran University of Science and Technology Tehran Iran

This paper examines the specific obstacles of constructing Retrieval-Augmented Generation (RAG) systems in low-resource languages, with a focus on Persian’s complicated morphology and versatile syntax. The research aims to improve retrieval and generation accuracy by introducing Persian-specific models, namely MatinaRoberta (a masked language model) and MatinaSRoberta (a fine-tuned Sentence-BERT), along with a comprehensive benchmarking framework. Three datasets—general knowledge (PQuad), scientifically specialized texts, and organizational reports—were used to assess these models after they were trained on a varied corpus of 73.11 billion Persian tokens. The methodology involved extensive pretraining, fine-tuning with tailored loss functions, and systematic evaluations using both traditional metrics and the Retrieval-Augmented Generation Assessment (RAGAS) framework. The results show that MatinaSRoberta outperformed previous embeddings, achieving superior contextual relevance and retrieval accuracy across datasets. Temperature tweaking, chunk size modifications, and document summary indexing were explored to enhance RAG setups. Larger models like Llama-3.1 (70B) consistently demonstrated the highest generation accuracy, while smaller models faced challenges with domain-specific and formal contexts. The findings underscore the potential for developing RAG systems in Persian through customized embeddings and retrieval-generation settings and highlight the enhancement of NLP applications such as search engines and legal document analysis in low-resource languages. © 2025, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Educational data mining: a 10-year review

引用

Discover Computing 2025年第1期28卷 1-25页

作者： Kalita, Emi Oyelere, Solomon Sunday Gaftandzhieva, Silvia Rajesh, Kandala N. V. P. S. Jagatheesaperumal, Senthil Kumar Mohamed, Asmaa Elbarawy, Yomna M. Desuky, Abeer S. Hussain, Sadiq Cifci, Mehmet Akif Theodorou, Paraskevi Hilčenko, Slavoljub Hazarika, Jiten Ali, Tazid Centre for Computer Science and Applications Dibrugarh University Dibrugarh 786004 India Department of Computer Science Electrical and Space Engineering Luleå University of Technology Skellefteå 931 87 Sweden Department of Computer Science Faculty of Environment Science and Economy University of Exeter Exeter United Kingdom Research Group On Data Artificial Intelligence and Innovations for Digital Transformation Johannesburg Business School (JBS) University of Johannesburg Johannesburg South Africa Faculty of Mathematics and Informatics University of Plovdiv “Paisii Hilendarski” Plovdiv Bulgaria School of Electronics Engineering VIT-AP University Vijayawada India Department of Electronics & Communication Engineering Mepco Schlenk Engineering College Sivakasi 626005 India Department of Mathematics Faculty of Science Al-Azhar University (Girls Branch) Cairo 11754 Egypt Department of Computer Engineering Bandirma Onyedi Eylul University Balikesir 10200 Turkey Engineering and Informatics Department Klaipėdos Valstybinė Kolegija/Higher Education Institution Klaipeda 92294 Lithuania Department of Digital Systems University of Piraeus Piraeus Greece College for Vocational Education of Preschool Teachers and Coaches Subotica Serbia Department of Statistics Dibrugarh University Dibrugarh 786004 India

This systematic review comprehensively examines the application and impacts of Educational Data Mining (EDM) over the past decade. It explores the use of various data mining tools and techniques, statistics, and machine learning algorithms in education. The review discusses how EDM helps understand and improve the learning experience, educational strategies, and institutional efficiency. It highlights the iterative process of EDM, its applications, and the benefits it offers to different stakeholders, including students, teachers, and educational institutions. The paper also discusses the challenges related to data ethics, privacy, and security in EDM. Key sections include a methodology for conducting the systematic review, exploring different data mining techniques and learning styles, and using Artificial Intelligence in EDM. The review concludes with a discussion of findings, future research directions, and a summary of the study’s contributions and limitations. © The Author(s) 2025.

关键词： Artificial intelligence in education Education data mining Explainability in education Multimodal learning analytics

来源：评论

学校读者我要写书评

暂无评论

一种比较学者学术影响力的新方法（英文）

引用

Journal of Data and Information science 2025年第2期 40-60+187页

作者： Anand Bihari Sudhakar Tripathi Akshay Deepak P.Mohan Kumar Department of Computational Intelligence School of computer Science and Engineering Vellore Institute of Technology Department of Information Technology Rajkiya Engineering College Department of Computer Science and Engineering National Institute of Technology Patna Department of Database Systems School of computer Science and Engineering Vellore Institute of Technology

研究目的：学术影响力的比较通常依赖于学者的整体科研成果。尽管这类方法简单易行，但如何比较位于不同职业生涯阶段的学者的影响力？很明显，如果一个学者有更丰富的研究经验或开展科研的时间更长，更可能获得较高的影响力。因此，我... 详细信息

研究目的：学术影响力的比较通常依赖于学者的整体科研成果。尽管这类方法简单易行，但如何比较位于不同职业生涯阶段的学者的影响力？很明显，如果一个学者有更丰富的研究经验或开展科研的时间更长，更可能获得较高的影响力。因此，我们不能直接比较位于不同职业生涯阶段的学者的影响力。已有多种文献计量指标尝试考虑时间跨度因素，其中h指数序列和EM/EM'指数序列已经被用于评估和比较学者的科学影响力。h指数序列、EM指数序列和EM'指数序列考虑了学者的年度影响力，并通过指标值及各个年度的分量值对学者进行比较。然而当两位学者在科研年限上存在显著差距时，基于时间序列的文献计量指标难以实现对其学术影响力的有效比较。研究方法：研究提出了一种累积指数计算方法，用于评估学者在其科研生涯某一年龄节点前的科学影响力，并使用89位学者的数据进行了实证测试。研究发现：本研究提出的方法已在89位学者的发表数据上进行了测试，能够清晰地区分两类学者之间的科学影响力差异。此外，该方法还有助于根据研究影响预测未来有潜力的杰出学者。实践意义：本研究提出的方法可被各类权威机构用于比较其学者的科研影响力，资助机构亦可将其用于类似的评估目的。原创性/价值：本研究通过引入一种新的学者科研影响力比较方法，丰富了现有文献体系。研究成果对于构建更加精确且公正的科研评估框架具有重要意义，有助于实现对学术贡献更为公平的评价。

关键词： h指数 EM指数 EM’指数 h指数序列 EM指数序列 EM’指数序列科学影响力比较科研影响力

来源：评论

学校读者我要写书评

暂无评论

Optimizing forensic file classification: enhancing SFCS with βk hyperparameter tuning

引用

PeerJ computer science 2025年 11卷 e2608-e2608页

作者： Joseph, D. Paul Perumal, Viswanathan School of Computer Science Engineering and Information Systems Vellore Institute of Technology University Tamilnadu Vellore India Department of IoT School of Computer Science and Engineering Vellore Institute of Technology University Tamilnadu Vellore India

In forensic topical modelling, the a parameter controls the distribution of topics in documents. However, low, high, or incorrect values of a lead to topic sparsity, model overfitting, and suboptimal topic distribution. To control the word distribution across topics, the β parameter is introduced. However, low, high, or inappropriate β values lead to sparse distribution, disjointed topics, and abundant highly probable words. The βj parameter, in conjunction with seed-guided words based on Term Frequency and Inverse Document Frequency, is introduced to address the issues. Nevertheless, the data often suffers from skewness or noise due to frequent co-occurrences of unrelated polysemic word pairs generated using Pointwise Mutual Information. By integrating a, β, and βj into file classification systems, classification models converge to local optima with O(n log n* |V|) time complexity. To combat these challenges, this research proposes the SDOT Forensic Classification System (SFCS) with a functional parameter βk that identifies seed words by evaluating semantic and contextual similarity of word vectors. As a result, the topic distribution (Θd) is compelled to model the curated seed words within the distribution, generating pertinent topics. Incorporating βk into SFCS allowed the proposed model to remove 278 k irrelevant files from the corpus and identify 5.6 k suspicious files by extracting 700 blacklisted keywords. Furthermore, this research implemented hyperparameter optimization and hyperplane maximization, resulting in a file classification accuracy of 94.6%, 94.4% precision and 96.8% recall within O(n log n) complexity. © 2025 Joseph and Perumal

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Multilevel Discrete Cosine Transform and CNN-Based Image Steganography

Multilevel Discrete Cosine Transform and CNN-Based Image Ste...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Brindha Subburaj Aditya Sai Shantanu Shantanu Daehan Won School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Systems Science and Industrial Engineering Binghamton University USA

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

This paper investigates the growing role of steganography in cybersecurity and presents a hybrid implementation called Multi-level Discrete Cosine Convolution (MDCC) that applies a Multi-level Discrete Cosine Transform (MDCT) and a Convolutional Neural Network (CNN). Steganography provides some advantages compared to cryptography, mainly its invisibility, but there are weaknesses in information capacity and resistance to attacks in traditional techniques. The paper suggests solving these difficulties with a new steganography method using deep learning. The proposed MDCC method provides an opportunity to encrypt large amounts of data in realistic images that are beyond human visual perception. The system is trained on the ImageNet dataset by using a loss function to balance the quality of the cover image and the information it conceals within it. The MDCC model proposed yields accurate results for all metrics since PSNR, SSIM, and bits per pixel come out to be 80.13dB, 0.9918, and 12.5 bpp, respectively.

关键词： Deep learning Measurement Steganography Convolution Color Discrete cosine transforms Convolutional neural networks Intelligent systems Visual perception Immune system

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：