检索结果-内蒙古大学图书馆

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Zafar, Saniya Alshehri, Mohammed S. Shah, Syed Aziz Ahmad, Jawad Zafar, Adnan Khattak, Aizaz Ahmad Institute of Space Technology Department of Electrical Engineering Islamabad Pakistan Najran University College of Computer Science and Information Systems Department of Computer Science Saudi Arabia Coventry University Research Centre for Intelligent Healthcare United Kingdom Prince Mohammad Bin Fahd University Cybersecurity Center Alkhobar Saudi Arabia Edinburgh Napier University School of Computing Engineering and the Built Environment United Kingdom

ISBN: (纸本)9798350373011

The rapid advancement in mobile broadband technology has evolved wireless infrastructure influencing internet-of-things (IoTs). This evolution has made mobile IoTs (mIoTs) as centre of attention due to its potential of providing seamless connectivity to enable intelligent transportation systems with huge data demands of vehicular users. To address the ever-escalating data demands of vehicular mobile users, vehicular edge computing (VEC) and moving small cells (mSCs) play a pivotal role. mSCs together with VEC are capable to provide improved service quality for mIoTs. However, incorporating the mSCs in vehicles for mIoTs presents challenges while assigning the resources in mIoT-mSC network. This is due to the existence of time varying interference among mSCs. This work explores the distributed resource assignment mechanism for RSU assisted mIoT-mSC network formed in vehicular environment. In the proposed work, location prediction of city buses deployed with mSCs is done using federated learning (FL) which is subsequently utilized for efficient assignment of resources in mIoT-mSC network. Numerical results are provided to validate the proposed resource assignment mechanism. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Winner Prediction Model for Basketball Matches Based on Statistical Data of Teams, Players, and Line-ups

Winner Prediction Model for Basketball Matches Based on Stat...

引用

Information Technology and Data science (CITDS), IEEE Conference on

作者： Chanin Witheesawas Suphakant Phimoltares Department of Mathematics and Computer Science Faculty of Science Advanced Virtual and Intelligent Computing (AVIC) Research Center Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798350387889

ISBN: (纸本)9798350387896

Winning the National Basketball Association (hereinafter referred to as “NBA”) championship is the ultimate goal for all NBA teams, as it represents the highest achievement in professional basketball player. This accomplishment increases the team's fan base, leading to a boost in revenue. Additionally, winning the championship can enhance team loyalty, inspire team players to improve their skills, and attract high-potential players to the team. This research aims to present an precise model for predicting the winning team of NBA games utilizing statistical data of teams, players, and line-ups. Seven models used in this research consist of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boosting (GB), Random Forest (RF), Naive Bayes (NB) classifier, Decision Tree (DT), and K-Nearest Neighbor (KNN) method. The dataset utilized in this research was obtained from https://***, covering the period from 2012 to 2023 for predicting winner's team. For the test outcomes, the Multilayer Perceptron Model exhibited the highest accuracy of 85.30% by using the combination of statistical data of teams, players, and line-ups.

关键词： Support vector machines Fans Games Predictive models Nearest neighbor methods Multilayer perceptrons Data science Data models Information technology Random forests

来源：评论

学校读者我要写书评

暂无评论

Learning to Parallelize in a Shared-Memory Environment with Transformers 23

Learning to Parallelize in a Shared-Memory Environment with ...

引用

Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming

作者： Re'em Harel Yuval Pinter Gal Oren Department of Computer Science Ben-Gurion University of the Negev Department of Physics Scientific Computing Center Nuclear Research Center - Negev Israel Department of Computer Science Ben-Gurion University of the Negev Israel Department of Computer Science Technion - Israel Institute of Technology Scientific Computing Center Nuclear Research Center - Negev Israel

ISBN: (纸本)9798400700156

In past years, the world has switched to multi and many core shared memory architectures. As a result, there is a growing need to utilize these architectures by introducing shared memory parallelization schemes, such as OpenMP, to applications. Nevertheless, introducing OpenMP work-sharing loop construct into code, especially legacy code, is challenging due to pervasive pitfalls in management of parallel shared memory. To facilitate the performance of this task, many source-to-source (S2S) compilers have been created over the years, tasked with inserting OpenMP directives into code automatically. In addition to having limited robustness to their input format, these compilers still do not achieve satisfactory coverage and precision in locating parallelizable code and generating appropriate directives. In this work, we propose leveraging recent advances in machine learning techniques, specifically in natural language processing (NLP), to suggest the need for an OpenMP work-sharing loop directive and data-sharing attributes clauses --- the building blocks of concurrent programming. We train several transformer models, named PragFormer, for these tasks and show that they outperform statistically-trained baselines and automatic source-to-source (S2S) parallelization compilers in both classifying the overall need for an parallel for directive and the introduction of private and reduction clauses. In the future, our corpus can be used for additional tasks, up to generating entire OpenMP directives. The source code and database for our project can be accessed on GitHub 1 and HuggingFace 2.

关键词： concurrent computing methodologies machine learning

来源：评论

学校读者我要写书评

暂无评论

The Odyssey Journey: Top-Tier Medical Resource Seeking for Specialized Disorder in China 25

The Odyssey Journey: Top-Tier Medical Resource Seeking for S...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Chan, Ka I Hu, Siying Wang, Yuntao Xu, Xuhai Lu, Zhicong Shi, Yuanchun Institute Tsinghua University Beijing China Department of Computer Science City University of Hong Kong Hong Kong Key Laboratory of Pervasive Computing Ministry of Education Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Technology Qinghai University Xining China Google New York CityNY United States Department of Computer Science George Mason University FairfaxVA United States Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Qinghai University Xining China

ISBN: (纸本)9798400713941

It is pivotal for patients to receive accurate health information, diagnoses, and timely treatments. However, in China, the significant imbalanced doctor-to-patient ratio intensifies the information and power asymmetries in doctor-patient relationships. Health information-seeking, which enables patients to collect information from sources beyond doctors, is a potential approach to mitigate these asymmetries. While HCI research predominantly focuses on common chronic conditions, our study focuses on specialized disorders, which are often familiar to specialists but not to general practitioners and the public. With Hemifacial Spasm (HFS) as an example, we aim to understand patients' health information and top-tier1 medical resource seeking journeys in China. Through interviews with three neurosurgeons and 12 HFS patients from rural and urban areas, and applying Actor-Network Theory, we provide empirical insights into the roles, interactions, and workflows of various actors in the health information-seeking network. We also identified five strategies patients adopted to mitigate asymmetries and access top-tier medical resources, illustrating these strategies as subnetworks within the broader health information-seeking network and outlining their advantages and challenges. © 2025 Copyright held by the owner/author(s).

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Metrocycle: Designing a Browser-Based Road Safety Education App for Motorcycle and Bicycle Riders in Metro Manila, Philippines 4th

Metrocycle: Designing a Browser-Based Road Safety Education ...

引用

4th International Conference on Novel and Intelligent Digital Systems, NiDS 2024

作者： Batrina, Jan Paul Gonzaga, Chase Rina, Brill Julian Juayong, Richelle Ann Gaspay, Sandy Mae Cabarle, Francis George Department of Computer Science University of the Philippines Diliman Quezon City Philippines Institute of Civil Engineering University of the Philippines Diliman Quezon City Philippines National Center of Transportation Studies University of the Philippines Diliman Quezon City Philippines Research Group on Natural Computing Department of Computer Science and Artificial Intelligence SCORE Lab I3US Universidad de Sevilla Seville Spain

ISBN: (纸本)9783031733437

With the recent increase in the use of bicycles and motorcycles as a main mode of transportation in the Philippines, there is also an increasing need to address the extremely high rate of fatalities and injuries from these vehicles. Previous research shows that these road crashes are usually attributed to driving behavior and human error. While other researches have already explored road safety education (RSE) apps to help drivers practice safe driving, most of these are tailored for 4-wheeled vehicle drivers and do not reflect the driving environment for motorcycle and bicycle drivers in Metro Manila. Most of the more fully-featured training apps are also only limited to either PC or mobile only. To address these limitations, this research aims to design and develop Metrocycle - a browser-based RSE driving application for motorcycle and bicycle users. Metrocycle seeks to effectively engage and accurately inform motorcycle and bicycle users of proper driving behavior and standard road safety practices specific to Metro Manila. The application will be designed through reviewing government published RSE guidelines, addressing limitations of current RSE applications and consultation with motorcycle and bicycle safety domain experts in the Philippines. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Motorcycles

来源：评论

学校读者我要写书评

暂无评论

A Platform for Automated Solar Data Analysis Using Machine Learning 9

A Platform for Automated Solar Data Analysis Using Machine L...

引用

9th International Conference on Social Networks Analysis, Management and Security, SNAMS 2022

作者： Younis, Ola Tashtoush, Yahya Alomari, Mohammad Darwish, Omar Department of Computer Science University of Liverpool Liverpool United Kingdom Computer Science Department Jordan University of Science and Technology Jordan Applied Science Research Center Applied Science Private University Jordan Information Security and Applied Computing Eastern Michigan University Ypsilanti United States

ISBN: (纸本)9798350320480

This paper presents a computer platform for the automated analysis of associations among different solar events and activities. This computer tool enables the advanced learning by implementing many associations' algorithms to analyze years of solar catalogues data and to study the associations among solar flares, eruptive filaments per prominences and Coronal Mass Ejections (CMEs). The aim is to combine all solar data catalogues in one dynamic space weather database that can be easily used in the analysis of solar activities and features. The computer tool identifies patterns of associations and provides numerical representations that can be used as inputs to the machine learning algorithms to provide computerized learning rules that can be developed in the future within the context of a real-time prediction system. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things

arXiv

引用

arXiv 2025年

作者： Zeeshan, Talha Kumar, Abhishek Lovén, Lauri Pirttikangas, Susanna Tarkoma, Sasu Center for Ubiquitous Computing University of Oulu Oulu90570 Finland Department of Computer Science University of Helsinki Helsinki00560 Finland

This paper presents the development and evaluation of a Large Language Model (LLM), also known as foundation models, based multi-agent system framework for complex event processing (CEP) with a focus on video query processing use cases. The primary goal is to create a proof-of-concept (POC) that integrates state-of-the-art LLM orchestration frameworks with publish/subscribe (pub/sub) tools to address the integration of LLMs with current CEP systems. Utilizing the Autogen framework in conjunction with Kafka message brokers, the system demonstrates an autonomous CEP pipeline capable of handling complex workflows. Extensive experiments evaluate the system's performance across varying configurations, complexities, and video resolutions, revealing the trade-offs between functionality and latency. The results show that while higher agent count and video complexities increase latency, the system maintains high consistency in narrative coherence. This research builds upon and contributes to, existing novel approaches to distributed AI systems, offering detailed insights into integrating such systems into existing infrastructures. © 2025, CC BY-NC-SA.

关键词： Pipeline processing systems

来源：评论

学校读者我要写书评

暂无评论

On the Scalability of computing Genomic Diversity Using SparkLeBLAST: A Feasibility Study

On the Scalability of Computing Genomic Diversity Using Spar...

引用

IEEE Conference on High Performance Extreme computing (HPEC)

作者： Ritvik Prabhu Bernard Moussad Karim Youssef Emil Vatai Wu-Chun Feng Department of Computer Science Virginia Tech USA Center for Applied Scientific Computing Lawrence Livermore National Laboratory USA RIKEN Center for Computational Science Japan

ISBN: (数字)9798350387131

ISBN: (纸本)9798350387148

Studying the genomic diversity of viruses can help us understand how viruses evolve and how that evolution can impact human health. Rather than use a laborious and tedious wet-lab approach to conduct a genomic diversity study, we take a computational approach, using the ubiquitous NCBI BLAST and our parallel and distributed SparkLeBLAST, across 53 patients (~40,000,000 query sequences) on Fugaku, the world's fastest homogeneous supercomputer with 158,976 nodes, where each code contains a 48-core A64FX processor and 32 GB RAM. To project how long BLAST and SparkLeBLAST would take to complete a genomic diversity study of COVID-19, we first perform a feasibility study on a subset of 50 query sequences from a single COVID-19 patient to identify bottlenecks in sequence alignment processing. We then create a model using Amdahl's law to project the run times of NCBI BLAST and SparkLeBLAST on supercomputing systems like Fugaku. Based on the data from this 50-sequence feasibility study, our model predicts that NCBI BLAST, when running on all the cores of the Fugaku supercomputer, would take approximately 26.7 years to complete the full-scale study. In contrast, SparkLeBLAST, using both our query and database segmentation, would reduce the execution time to 0.026 years (i.e., 22.9 hours) – resulting in more than a 10,000× speedup over using the ubiquitous NCBI BLAST.

关键词： COVID-19 Databases computer viruses Scientific computing Scalability Genomics Predictive models Supercomputers Bioinformatics Optimization

来源：评论

学校读者我要写书评

暂无评论

Translation-Invariant Quantum Algorithms for Ordered Search are Optimal

arXiv

引用

arXiv 2025年

作者： Carolan, Joseph Childs, Andrew M. Kovacs-Deak, Matt Schaeffer, Luke Department of Computer Science Institute for Advanced Computer Studies Joint Center for Quantum Information and Computer Science University of Maryland United States David R. Cheriton School of Computer Science Institute for Quantum Computing University of Waterloo Canada

Ordered search is the task of finding an item in an ordered list using comparison queries. The best exact classical algorithm for this fundamental problem uses [log2 n] queries for a list of length n. Quantum computers can achieve a constant-factor speedup, but the best possible coefficient of log2 n for exact quantum algorithms is only known to lie between (ln 2)/π ≈ 0.221 and 4/log2 605 ≈ 0.433. We consider a special class of translation-invariant algorithms with no workspace, introduced by Farhi, Goldstone, Gutmann, and Sipser, that has been used to find the best known upper bounds. First, we show that any exact, k-query quantum algorithm for ordered search can be implemented by a k-query algorithm in this special class. Second, we use linear programming to show that the best exact 5-query quantum algorithm can search a list of length 7265, giving an ordered search algorithm that asymptotically uses 5 log7265 n ≈ 0.390 log2 n quantum queries. © 2025, CC BY.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Embedding: Literature Assessment, Recent Advancements, Opportunities, and Challenges

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Satpathy, Anurag Sahoo, Manmath Narayan Swain, Chittaranjan Bellavista, Paolo Guizani, Mohsen Muhammad, Khan Bakshi, Sambit Missouri University of Science and Technology Department of Computer Science RollaMO United States National Institute of Technology Visual Surveillance Laboratory Department of Computer Science and Engineering Odisha Rourkela769008 India Atal Bihari Vajpayee Indian Institute of Information Technology and Management Department of Computer Science and Engineering Gwalior India Department of Computer Science and Engineering Italy Machine Learning Department Abu Dhabi United Arab Emirates Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Network virtualization (NV) allows service providers (SPs) to instantiate logically isolated entities called virtual networks (VNs) on top of a substrate network (SN). Though VNs bring about multiple benefits, particularly in terms of economic costs and elasticity, they also force various technical challenges to be addressed. The primary one is the issue of optimally allocating resources to VNs, also termed virtual network embedding (VNE). This paper presents an exhaustive survey of VNE by extensively covering the state-of-the-art research field in this very active field and focusing on the emerging research trends in industry and academia over the last decade. In addition, this survey originally contributes to the literature by proposing a novel taxonomy for existing VNE solutions and providing a thorough comparative study of their strategies. © 1998-2012 IEEE.

关键词： Virtual machine

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：