检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kim, Byeong-Je Jeong, Seunghoo Cho, Bong-Kyung Chung, Ji-Bum The Institute of Social Data Science Pohang University of Science and Technology Pohang Korea Republic of Division of Advanced Nuclear Engineering Pohang University of Science and Technology Pohang Korea Republic of R&D Planning Strategy Division Korea Railroad Research Institute Uiwang Korea Republic of Strategy Group INTERX Seoul Korea Republic of Department of Civil Urban Earth and Environmental Engineering Ulsan National Institute of Science and Technology Ulsan Korea Republic of

The rapid advancement of artificial intelligence (AI) has brought about significant societal changes, necessitating robust AI governance frameworks. This study analyzed the research trends in AI governance within the framework of the EU AI Act. This study conducted a bibliometric analysis to examine the publications indexed in the Web of Science database. Our findings reveal that research on AI governance, particularly concerning AI systems regulated by the EU AI Act, remains relatively limited compared to the broader AI research landscape. Nonetheless, a growing interdisciplinary interest in AI governance is evident, with notable contributions from multi-disciplinary journals and open-access publications. dominant research themes include ethical considerations, privacy concerns, and the growing impact of generative AI, such as ChatGPT. Notably, education, healthcare, and worker management are prominent application domains. Keyword network analysis highlights education, ethics, and ChatGPT as central keywords, underscoring the importance of these areas in current AI governance research. Subsequently, a comprehensive literature review was undertaken based on the bibliometric analysis findings to identify research trends, challenges, and insights within the categories of the EU AI Act. The findings provide valuable insights for researchers and policymakers, informing future research directions and contributing to developing comprehensive AI governance frameworks beyond the EU AI Act. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection based on phishing detection with machine learning

引用

Measurement: Sensors 2024年 31卷

作者： Jayaraj, r. Pushpalatha, A. Sangeetha, K. Kamaleshwar, T. Udhaya Shree, S. damodaran, deepa Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur TN Chennai India M.Tech Computer Science and Engineering Sri Krishna College of Engineering and Technology TN Coimbatore India Department of Computer Science and Engineering Panimalar Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Dr. Rangarajan Dr.Sagunthala R&D Institute of Science and Technology TN Chennai India Department of Computer Science and Engineering Alpha College of Engineering and Technology Puducherry India VITBS Vellore Institute of Technology Chennai Campus TN India

Machine learning technique which uses artificial neural networks to learn representations. Phishing is a form of fraud in which the attacker tries to learn credential information from the websites. Web phishing is to steal sensitive information such as usernames, passwords and credit card details by way of impersonating a authorized entity. The Hybrid Ensemble Feature Selection is a new feature selection method for machine learning-based phishing detection systems (HEFS). The first step of HEFS involves using a novel Cumulative distribution Function gradient (CdF-g) algorithm to generate primary feature subsets, which are then fed into a data perturbation ensemble to generate secondary feature subsets. We present the results of our approach and compare them to a few previous studies, with the paper focusing primarily on phishing urls for detecting the unauthorised one by using phishing detection method. © 2023

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Cryptographic Protocols for Securing Internet of Things (IoT)

Cryptographic Protocols for Securing Internet of Things (IoT...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： B. Manimekala T. Aravind T. Sounderrajan V. rajakumareswaran Krishnaveni Kondreddi K. Mohanambal Department of Computer Science Christ University Yeshwanthpur Bengaluru Department of CSE School of Computing Vel TecRangarajanDr.Sagunthala R&D Institute of Science and Technology Department of AI and Data Science Erode Sengunthar Engineering College Thuduppathi Tamil Nadu India Department of Computer Science and Design Erode Sengunthar Engineering College Thuduppathi Tamil Nadu India Electrical and Electronics Engineering Chaitanya Bharathi Institute of Technology Gandipet Ranga Reddy Telangana India Department of Computer Science and Engineering Bannariamman Institute of Technology Sathyamangalam

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cryptographic protocols are used to relax the ever-developing quantity of linked gadgets that make up the net of things (IoT). Those cryptographic protocols have been designed to make certain that IoT tool traffic stays cozy and personal, even while nevertheless allowing tool-to-device and cloud-to-tool communications. Examples of these protocols consist of TLS/SSL, PGP/GPG, IPsec, SSL VPN, and AES encryption. Every one of these protocols enables authentication, message integrity, and confidentiality via encryption and key trade. Moreover, a lot of these protocols are carried out in the form of diverse hardware and software answers, such as smart playing cards and gateways, to make certain that IoT traffic is secured. With the appropriate implementation of those cryptographic protocols, establishments can ensure that their IoT facts are blanketed and securely transmitted.

关键词： Prevention and mitigation Intrusion detection Logic gates Software Hardware Safety Encryption Virtual private networks Internet of Things Cryptographic protocols

来源：评论

学校读者我要写书评

暂无评论

UQSA - an r-package for uncertainty quantification and sensitivity analysis for biochemical reaction network models

arXiv

引用

arXiv 2023年

作者： Kramer, Andrei Milinanni, Federica Nyquist, Pierre Jauhiainen, Alexandra Eriksson, Olivia Science for Life Laboratory Department of Neuroscience Karolinska Institute Solna Sweden Department of Mathematics KTH Royal Institute of Technology Stockholm Sweden Early Biometrics and Statistical Innovation Data Science & AI BioPharmaceuticals R&D AstraZeneca Gothenburg Sweden Science for Life Laboratory School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

We present an r-package developed for modeling of biochemical reaction networks that especially includes tools for uncertainty quantification and sensitivity analysis. Estimating parameters and quantifying their uncertainty, especially in relationship with prediction uncertainty, is required for data-driven systems biology modeling. The methods we chose require efficient sampling from high-dimensional, correlated parameter distributions. We have developed UQSA (Uncertainty Quantification and Sensitivity Analysis) to be fast for the problem class and work well with other tools for modelling. We aim for simplicity, and part of that is our use of the SBtab format for the unified storage of model and data. Our tool-set is modular enough, that parts can be replaced. We use intermediate formats that are not hidden from the user to make this feasible. UQ is performed through Markov chain Monte Carlo (MCMC) sampling in an Approximate Bayesian Computation (ABC) setting. This can be followed by a variance-decomposition based global sensitivity analysis. If needed, complex parameter distributions can be described, evaluated, and sampled from, with the help of Vine-copulas that are available in r. This approach is especially useful when new experimental data become available, and a previously calibrated model needs to be updated. An additional feature is that complicated experimental input data can be easily fitted to corresponding model functions. This is important for e.g. neuroscience applications, where transient time dependent input (spike-trains) are common. Availability and Implementation: The main part of the code is written in r, as well as the user facing functions. r is a high-level language and allows the use of sophisticated statistical methods. The ode solver is written in C in order to be computationally efficient (from the GSL, odeiv2). We use the SBtab table format for Systems Biology projects [20] for the model description as well as the calibration data and a

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Spectrum Aware Unequal Clustering with route Selection Protocol for Energy Efficient Cognitive radio Wireless Sensor Networks

Spectrum Aware Unequal Clustering with Route Selection Proto...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： Arthi. A Chinmaya Kumar Nayak Arunmurugan Subbaiyan M. Muthalakshmi Srimathi S Venkatesh p Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai Faculty of Emerging Technologies Sri Sri University Sri Sri Vihar Odisha ECE Periyar Maniammai Institute of Science & Technology Thanjavur Tamilnadu India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India Department of ECE Ramco Institute of Technology Rajapalayam

Spectrum awareness with energy conservation is a main prerequisite in Cognitive radio Sensor Networks (CrSN) as the sensor nodes (SNs) operate in physically unattended areas and are energy constrained. Cluster based routing combined with channel allocation accomplishes energy effective path selection as a countermeasure to preserve energy. It is required to perform reliable routing with cluster based channel distribution contributing to development of network efficiency. Therefore, this study introduces a new Spectrum Aware metaheuristic Unequal Clustering with route Selection Protocol (SAMUC-rSP) technique for Energy Efficient CrSN. The focus of the SAMUC-rSP technique lies in the effective selection of CHs and routes in the CrSN. For accomplishing this, the SAMUC-rSP technique designs fruit fly optimization algorithm based unequal clustering (FFOA-UC) technique to produce unequal clusters in the CrSN. Besides, moth search optimization based routing (MSOr) approach is used to produce an optimal set of routes in the CrSN. The simulation results of the SAMUC-rSP technique are examined in terms of different measures in python environment. Extensive comparison analysis reported the superior results of the SAMUC-rSP method over other existing techniques in the CrSN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cybersecurity Using deep Learning Techniques Attack detection for Trojan Horses

Advancements in Cybersecurity Using Deep Learning Techniques...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Hosanna Princye P Ahila A A. Anna Lakshmi N. ragavendran K. E. Purushothaman G. Uma Maheswari r. Saravanakumar Department of Electronics and Communication Engineering Sri Sairam College of Engineering Bangalore Anekal India Department of Information Technology R.M.K. Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Software Analyst Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Today's computer networks are threatened by Trojan horse assaults and other cybersecurity dangers. We propose and evaluate deep learning methods using the Kaggle-hosted Trojan detection dataset to detect Trojan horse assaults. This project uses these approaches. Our malware detection technology uses CNN classification for accuracy. We clean and enhance the dataset to make the model more versatile. due to extensive testing and optimization, Trojan horse detection rates reach 98.47%. We found that the deep learning architecture accurately identifies malware. We also discuss CNN model features that illuminate Trojan horse attacks. The technique offers complete cyber security and expands our knowledge of harmful software. deep learning may boost cybersecurity defenses against emerging attacks like Trojan horses, according to our study.

关键词： deep learning Training Accuracy Feature extraction Safety Trojan horses Convolutional neural networks Computer crime Testing Python

来源：评论

学校读者我要写书评

暂无评论

Masked Motion Encoding for Self-Supervised Video representation Learning

arXiv

引用

arXiv 2022年

作者： Sun, Xinyu Chen, Peihao Chen, Liangwei Li, Changhao Li, Thomas H. Tan, Mingkui Gan, Chuang South China University of Technology China Information Technology R&d Innovation Center Peking University China UMass Amherst United States MIT-IBM Watson Ai Lab United States Key Laboratory of Big Data and Intelligent Robot Ministry of Education Peking University Shenzhen Graduate School China

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions. However, simply masking and recovering appearance contents may not be sufficient to model temporal clues as the appearance contents can be easily reconstructed from a single frame. To overcome this limitation, we present Masked Motion Encoding (MME), a new pretraining paradigm that reconstructs both appearance and motion information to explore temporal clues. In MME, we focus on addressing two critical challenges to improve the representation performance: 1) how to well represent the possible long-term motion across multiple frames;and 2) how to obtain fine-grained temporal clues from sparsely sampled videos. Motivated by the fact that human is able to recognize an action by tracking objects' position changes and shape changes, we propose to reconstruct a motion trajectory that represents these two kinds of change in the masked regions. Besides, given the sparse video input, we enforce the model to reconstruct dense motion trajectories in both spatial and temporal dimensions. Pre-trained with our MME paradigm, the model is able to anticipate longterm and fine-grained motion details. Code is available at https://***/XinyuSun/MME. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation

arXiv

引用

arXiv 2022年

作者： Chen, Peihao Ji, dongyu Lin, Kunyang Zeng, runhao Li, Thomas H. Tan, Mingkui Gan, Chuang South China University of Technology China Pazhou Laboratory China MIT-IBM Watson Ai Lab United States UMass Amherst United States Shenzhen University China Information Technology R&d Innovation Center of Peking University China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions often contain descriptions of objects in the environment. To achieve accurate and efficient navigation, it is critical to build a map that accurately represents both spatial location and the semantic information of the environment objects. However, enabling a robot to build a map that well represents the environment is extremely challenging as the environment often involves diverse objects with various attributes. In this paper, we propose a multi-granularity map, which contains both object fine-grained details (e.g., color, texture) and semantic classes, to represent objects more comprehensively. Moreover, we propose a weakly-supervised auxiliary task, which requires the agent to localize instruction-relevant objects on the map. Through this task, the agent not only learns to localize the instruction-relevant objects for navigation but also is encouraged to learn a better map representation that reveals object information. We then feed the learned map and instruction to a waypoint predictor to determine the next navigation goal. Experimental results show our method outperforms the state-of-the-art by 4.0% and 4.6% w.r.t. success rate both in seen and unseen environments, respectively on VLN-CE dataset. Code is available at https://***/PeihaoChen/WS-MGMap. Copyright © 2022, The Authors. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Sign Language recognition Using Improved Seagull Optimization Algorithm with deep Learning Model

Sign Language Recognition Using Improved Seagull Optimizatio...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： r. Sivaraman S Santiago K. Chinnathambi Swagata Sarkar Sangeethaa SN Srimathi S Department of Mathematics Dwaraka Doss Goverdhan Doss Vaishnav College Chennai Tamil Nadu India Department of Computer Science St. Joseph's College (Autonomous) Trichy Computing Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Artificial intelligence and Data Science Sri Sairam Engineering College Chennai Computer Science & Engineering Bannari Amman Institute of Technology Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Sign Language recognition (SLr) covers the ability to translate Sign Language (SL) signals into written or spoken languages. This technique is useful for hearing-impaired people by offering them an effective method to communicate with persons having trouble in recognizing SLs. It can also be employed for generating automatic captions in real-time for live actions and videos. Various models of SLr include machine and deep learning, and computer vision techniques. A commonly employed technique involves using a camera to capture the body and hand movements of the signer, processing the video data to identify the signs. One of the high tasks of SLr includes the flexibility in SL over numerous individuals and cultures, the complex of definite signs, and the need for real-time process. This manuscript presents a SL recognition Using an Improved Seagull Optimization Algorithm with deep Learning (SLr-ISOAdL) methodology. The SLr-ISOAdL approach aims to exploit a hyperparameter-tuned dL model to recognize and classify the SLs. In the SLr-ISOAdL approach, a bilateral filtering (BF) approach can be applied to get rid of the noise. For learning and deriving intrinsic patterns, the SLr-ISOAdL approach employs the AlexNet model. Besides, the ISOA can be applied for optimal hyperparameter election of the AlexNet model. Finally, the multilayer perceptron (MLP) technique can be exploited to detect and classify the SLs. The analytical experiment of the SLr-ISOAdL technique is conducted on a benchmark dataset. The investigational analysis highlighted that the SLr-ISOAdL technique gains enhanced detection outcomes in terms of distinct measures.

关键词： deep learning Sign language Voting Noise Gain measurement Benchmark testing real-time systems Classification algorithms Optimization Videos

来源：评论

学校读者我要写书评

暂无评论

Enhancing Speech recognition for Hearing-Impaired Individuals Using deep Learning Models

Enhancing Speech Recognition for Hearing-Impaired Individual...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： K. Kalaiarasi Winson Medidhi Niresh Kumar S S. Thenappan r. Sathiyaseelan Mohana Sundaram K Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of CSE(Data Science) Prasad V. Potluri Siddhartha Institute of Technology Kanuru Vijayawada Andhra Pradesh India Department of CSE St. Joseph's College of Engineering OMR Chennai Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Department of Computer Science Engineering Arunai Engineering College Thiruvannamalai Tamil Nadu India Department of Computer Science and Engineering R.M.D. Engineering College Kavaraipettai Thiruvallur India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

This study examines the constraints of current methodologies, specifically in diverse acoustic environments, to surmount the obstacles associated with speech recognition for individuals with hearing impairments. Conventional processes frequently experience reduced accuracy and utility as a result of their incapability to dynamically adjust to evolving circumstances. This study presents an innovative approach that surpasses these constraints through the utilization of a transformer-based model. Through the implementation of sophisticated data augmentation techniques, the proposed model demonstrates exceptional performance across various acoustic environments, notwithstanding obstacles such as speaker adjustments and background noise. One notable characteristic of this methodology is its transformer architecture, which aptly captures subtle speech inflections by employing self-attention processes. Additionally, through independent learning, the model improves its ability to address the unique challenges associated with hearing-impaired speech. Integrating these components, the model achieves superior accuracy and adaptability compared to current technologies.

关键词： Adaptation models Accuracy Speech recognition Auditory system Artificial neural networks Speech enhancement Transformers

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：