检索结果-内蒙古大学图书馆

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Singh, Vaishali Pandey, Pratik Aggarwal, Prateek Reena, R. Bhagwat, Suvarna R. Sunil, M.P. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Faculty of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350319125

Statistics mining has emerged as a crucial device for agencies in the past two decades that significantly impact selection-making methods. It can be used to gain insights from massive datasets and might assist with an employer's marketing approach, operational performance, customer segmentation, etc. This paper will explore the impact information mining has on decision-making approaches, especially regarding coming across new styles and relationships. It will discuss the blessings of using records mining and how it may help decorate choice-making. It will also look at various methods used to extract statistics from massive datasets and how they facilitate the selection-making method. Finally, it will discuss a number of the constraints of information mining and the ability of answers to overcome them. Standard, this paper aims to pick out the effect of information mining on the choice-making system and how it may be leveraged as a practical device. © 2023 IEEE.

关键词： discuss extract information overcome relationships

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

arXiv

引用

arXiv 2024年

作者： Li, Zhiwei Long, Guodong Zhou, Tianyi Jiang, Jing Zhang, Chengqi Australian Artificial Intelligence Institute Faculty of Engineering and IT University of Technology Sydney Australia Department of Computer Science University of Maryland College Park United States Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users’ personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance. Our code is available at https://***/mtics/FedDAE. Copyright © 2024, The Authors. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on the Results of Student Assessment data Developed by SURE Model 15

Comparative Study on the Results of Student Assessment Data ...

引用

15th International Scientific-Technical Conference on Actual Problems of Electronic Instrument Engineering, APEIE 2021

作者： Senden, Delgermaa Shambaljamts, Tsooj Tudevdagva, Uranchimeg Reva, Ivan L. Mongolian University of Science and Technology Department of Mechanical Science Ulaanbaatar Mongolia Chemnitz University of Technology Computer Sceince Faculty Chemnitz Germany Novosibirsk State Technical University Faculty of Automation and Computer Engineering Dept. of Data Security Novosibirsk Russia

ISBN: (纸本)9781665434089

The Mongolian University of science and Technology collects information (data) related to teaching methods and learning environment using a brief questionnaire from each student each semester. The data collected via questionnaires should be used for analysis of education activities, as well as development of policy level measures directed to improve education quality and teaching methods. However, as was observed by teachers, there is still an insufficiency in development of collected data and actions taken based on the results. In order to conduct comparative study within the framework of this issue, one module was taught by the same teacher (Theoretical mechanics 2) and other three different subjects (Mathematics 1, Information Technology 1, Theoretical Mechanics 1) were chosen, which are selected by most of the students, and ultimately processed the results with the use of the SURE model of structure-based evaluation. In this article, a total of 66681 evaluation data were provided by students who completed general education courses, professional foundation courses and other specialized courses at three schools (School of Industrial Technology, School of Mechanical Engineering and Transportation, School of Information and Telecommunication Technology) under the MUST, and these data were processed with the use of evaluation model mentioned above and the results were compared with the outcomes of previous study. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Investigating the Benefits of Machine Learning Algorithms for Text Classification 3

Investigating the Benefits of Machine Learning Algorithms fo...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Gowrishankar, J. Vinithra Banu, T. Parikshit, N. Singh, Vandana Kalra, Hitesh Sahoo, Girija Shankar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

This paper affords a research into using gadget studying algorithms for textual content category duties, with a focal point on understanding the importance of these algorithms and their ability to enhance the accuracy of textual content classification. it's miles located that, while conventional techniques, which include rule based models and hand-engineered features, can attain first-class outcomes, there are compelling motives to explore the capability of device getting to know algorithms to further improve the accuracy and performance of textual content class. The paper discusses the 3 maximum famous gadget gaining knowledge of algorithms for this project: the NaÏve Bayes classifier, help Vector Machines, and synthetic Neural Networks, and presents a top level view of the latest research findings that demonstrate the prevalence of these algorithms over traditional methods. The paper additionally presents an outline of the distinctive approaches for introducing era into text type, and discusses modern-day strategies for implementing and deploying those algorithms. Finally, the paper outlines ability areas for destiny research associated with information the results of system studying algorithms for this mission, and suggests viable instructions for exploration. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for Cyberbullying Detection in Arabic Tweets

Leveraging Deep Learning for Cyberbullying Detection in Arab...

引用

Women in data science at Prince Sultan University (WiDS PSU), International Conference of

作者： Fatima AlShannaq Sawsan Alhalawani Heba Al-Jarrah Mohammad Shehab Artificial Intelligence and Data Analytics Lab (AIDA) CCIS Prince Sultan University Riyadh Saudi Arabia College of Computer Science and Information Systems Prince Sultan University Riyadh Saudi Arabia Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan College of Computer Sciences and Informatics Amman Arab University Amman Jordan

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Cyberbullying is a growing concern in the digital age, particularly on social media platforms like X (formerly Twitter). This study presents a deep learning-based approach for detecting cyberbullying in Arabic tweets using the Arabic Cyberbullying Corpus (ArCybC). Leveraging the Arabic-BERT model, we conducted binary and multi-class classification tasks to identify cyberbullying content and its associated categories or domains. Our methodology incorporated advanced data-balancing techniques, including oversampling and undersam-pling, to address class imbalance challenges. The study aims to answer the research questions: (1) How effectively can deep learning models detect cyberbullying in Arabic tweets? (2) How do data balancing techniques impact classification performance? (3) Can Arabic-BERT outperform traditional classifiers in cy-berbullying detection? These questions are addressed through our methodology, where we employ Arabic-BERT, implement rebalancing techniques, and compare our model's performance with baseline classifiers. Experimental results demonstrate significant improvements in F1-scores, with 89.1% achieved in binary classification and 91.6% in category-level classification after oversampling. These findings highlight the effectiveness of fine-tuned deep learning models in tackling the linguistic complexity of Arabic and the nuanced nature of cyberbullying detection. This study provides a foundation for future research in addressing online harassment in Arabic-speaking digital communities.

关键词： Deep learning Blogs Cyberbullying Linguistics data science Information age data models Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A Secured and Optimized Broadcast Authentication Scheme for the Internet of Medical Things

A Secured and Optimized Broadcast Authentication Scheme for ...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Syed Waleed Riaz Fazlullah Khan Insaf Ullah Bandar Alshawi Ryan Alturki Mohammad Wedyan Computer Science Department Abdul Wali Khan University Mardan KPK Pakistan Faculty of Science and Engineering School of Computer Science University of Nottingham Ningbo China Ningbo Zhejiang China Institute for Analytics and Data Science University of Essex Colchester UK Department of Computer and Network Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Computer Sciences Faculty of Information Technology and Computer Sciences Yarmouk University (YU) Irbid Jordan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

This Internet of Medical Things (IoMT), facilitates the medical stop regarding real-time monitoring of patients, medical emergency management, remote surgery, patient information management, medical equipment, drug monitoring, etc. However, IoMT devices communicate with each other in an open environment that makes them vulnerable to a wide range of malicious threats from malicious entities. To protect the devices and their associated data, we designed a broadcast authentication scheme for IoMT devices using identity-based public key cryptography that exploits the lightweight features of the Hyper-Elliptic Curve (HEC). We then performed the security analysis based on the Random Oracle Model (ROM), in which we have proved that the proposed scheme is unforgeable under the hardiness of the hyperelliptic curve discrete logarithm problem. The proposed scheme is analyzed in terms of computational and communication overhead and the experimental results justify the superiority of the proposed work in comparison to the existing schemes.

关键词： Performance evaluation Computational modeling Authentication Surgery Internet of Medical Things Public key cryptography Real-time systems Information management Monitoring Read only memory

来源：评论

学校读者我要写书评

暂无评论

A C++ Library for Memory Layout and Performance Portability of Scientific Applications 28th

A C++ Library for Memory Layout and Performance Portabilit...

引用

28th International European Conference on Parallel and Distributed Computing , Euro-Par 2022

作者： Incardona, Pietro Gupta, Aryaman Yaskovets, Serhii Sbalzarini, Ivo F. Technische Universität Dresden Faculty of Computer Science Dresden Germany Max Planck Institute of Molecular Cell Biology and Genetics Dresden Germany Center for Systems Biology Dresden Dresden01307 Germany Center for Scalable Data Analytics and Artificial Intelligence ScaDS.AI Dresden/Leipzig Germany

ISBN: (纸本)9783031312083

We present a C++14 library for performance portability of scientific computing codes across CPU and GPU architectures. Our library combines generic data structures like vectors, multi-dimensional arrays, maps, graphs, and sparse grids with basic, reusable algorithms like convolutions, sorting, prefix sum, reductions, and scan. The memory layout of the data structures is adapted at compile-time using tuples with optional memory mirroring between CPU and GPU. We combine this transparent memory mapping with generic algorithms under two alternative programming interfaces: a CUDA-like kernel interface for multi-core CPUs, Nvidia GPUs, and AMD GPUs, as well as a lambda interface. We validate and benchmark the presented library using micro-benchmarks, showing that the abstractions introduce negligible performance overhead, and we compare performance against the current state of the art. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Delay Tolerant and Energy Reduced Task Allocation in Internet of Things with Cloud Systems 1

Delay Tolerant and Energy Reduced Task Allocation in Interne...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Raghunath Patil, Dipak Borkar, Bharat Markad, Ashok Kadlag, Sunil Kumbhkar, Makhan Jamal, Ahmad Amrutvahini College of Engineering Dept. of Computer Engineering Pune Sangamner India Amrutvahini College of Engineering Dept. of Information Technology Pune Sangamner India Amrutvahini College of Engineering Department of Electrical Engineering Pune Sangamner India Christian Eminent College Indore & Visiting Faculty School of Data Science and Forecasting Devi Ahilya University Department of Computer Science & Electronics Indore India Tulas Institute Department of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665456876

Through the utilization of the Internet, cloud computing supplies storage and computation resources to deliver services for many sectors. The speed of such systems suffers, though, since delay-sensitive systems, such as smart city and health applications, increasingly need for processing over massive volumes of data transmitted to centralised datacenters. When compared to cloud services, the paradigms of fog as well as edge computing provide innovative solutions by affecting the financial closer to the customer and by having low energy consumption and latency effectiveness. To optimise expense and resource efficiency, enhance QoS, and increase security and privacy, it is crucial to discover the best locations for services and assets inside the 3 IoT. The bipartite graph task scheduling method we provide in this research enhances cost effectiveness in real world applications with strict deadlines. The proposed method's performance in terms of delay, network congestion, as well as cost is deployed and tested to use the iFogSim simulator, an expanded version of CloudSim. The evaluation results demonstrate that the suggested algorithm outperforms Round-Robin and Minimum Response Time methods in terms of both cost as well as throughput. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Tiered Quadruplet Network with Patient-Specific Mining and Dynamic Margin for Improved ugly Duckling Lesion Classification

A Tiered Quadruplet Network with Patient-Specific Mining and...

引用

IEEE International Symposium on Biomedical Imaging

作者： Nathasha Naranpanawa H. Peter Soyer Adam Mothershaw Gayan K. Kulatilleke Zongyuan Ge Brigid Betz-Stablein Shekhar S. Chandra School of Electrical Engineering and Computer Science The University of Queensland Australia Dermatology Research Centre Frazer Institute The University of Queensland Australia Monash Medical AI Monash University Australia Department of Data Science and AI Faculty of IT Monash University Australia

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

The concept of the ‘ugly duckling sign’ is a criterion used in diagnosing cutaneous melanoma by identifying visually distinct skin lesions. However, variations in pigmented lesions among patients make it challenging to visually distinguish ugly ducklings. Hence, we propose DMT-Quadruplet -a deep metric learning network to learn lesion features at two tiers - patient-level and lesion-level. We introduce a patient-specific quadruplet mining approach within a tiered quadruplet network, to capture contextual information both globally and locally. We further incorporate a dynamic margin within the patient-specific mining to allow more useful quadruplets to be mined within individuals. Comprehensive experiments show that our proposed method outperforms traditional classifiers, achieving significantly higher sensitivity than baseline models, successfully classifying ugly duckling lesions both in patient-specific and patient-agnostic contexts.

关键词： Manifolds Learning systems Sensitivity Pipelines Melanoma Feature extraction Extraterrestrial measurements

来源：评论

学校读者我要写书评

暂无评论

Traveling-wave solutions and structure-preserving numerical methods for a hyperbolic approximation of the Korteweg-de Vries equation

arXiv

引用

arXiv 2024年

作者： Biswas, Abhijit Ketcheson, David I. Ranocha, Hendrik Schütz, Jochen Computer Electrical and Mathematical Sciences & Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Institute of Mathematics Johannes Gutenberg University Mainz Germany Faculty of Sciences Data Science Institute Hasselt University Belgium

We study the recently-proposed hyperbolic approximation of the Korteweg-de Vries equation (KdV). We show that this approximation, which we call KdVH, possesses a rich variety of solutions, including solitary wave solutions that approximate KdV solitons, as well as other solitary and periodic solutions that are related to higher-order water wave models, and may include singularities. We analyze a class of implicit-explicit Runge-Kutta time discretizations for KdVH that are asymptotic preserving, energy conserving, and can be applied to other hyperbolized systems. We also develop structure-preserving spatial discretizations based on summation-by-parts operators in space including finite difference, discontinuous Galerkin, and Fourier methods. We use the relaxation approach to make the fully discrete schemes energy-preserving. Numerical experiments demonstrate the effectiveness of these *** Codes 65L04, 65L20, 65M06, 65M12, 65M22 © 2024, CC BY.

关键词： Solitons

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：