检索结果-内蒙古大学图书馆

IEEE World Forum on Internet of Things (WF-IoT)

作者： Bobo Ju Kun Yang Yang Liu Jing Liu Peng Sun Wei Ni Liang Song Academy for Engineering & Technology Fudan University Shanghai China Innovation Platform for Academicians of Hainan Province Haikou China Department of Computer Science University of Toronto Toronto Ontario Canada School of Information Science and Technology Fudan University Shanghai China Division of Natural and Applied Sciences Duke Kunshan University Suzhou China Shanghai East Bund Research Institute on NSAI Shanghai China

ISBN: (数字)9798350373011

ISBN: (纸本)9798350373028

Under the architecture of Networking Systems of AI (NSAI), we propose a three-tier edge computing platform called Open Service for NSAI (OpenSAI), which can jointly configure the application execution and compute-storage-network resources, for online application-network adaption, to ensure the efficiency and reliability of the services. In this research, we investigate a specific task-device adaptation optimization problem in OpenSAI, which recommend application tasks to distributed computing devices. We evaluate the performance of various optimization and search algorithms in recommending optimal task-device combinations, which show significant differences among the algorithms in terms of recommendation runtime costs and task adaptability. Overall, the hybrid recommendation of SCORE Algorithm, Particle Swarm Optimization, and Item-Item Collaborative Filtering demonstrates the best performance in both time efficiency and fitness scores across multiple scenarios.

关键词： Performance evaluation Runtime Scheduling algorithms Heuristic algorithms Collaboration computer architecture Reliability engineering Partitioning algorithms Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

A Joint SLM and Precoding Based PAPR Reduction Scheme for 5G UFMC Cellular Networks

A Joint SLM and Precoding Based PAPR Reduction Scheme for 5G...

引用

2020 International Conference on Computing and Information Technology, ICCIT 2020

作者： Baig, Imran Farooq, Umer Hasan, Najam Ul Zghaibeh, Manaf Arshad, Muhammad Ayaz Imran, Muhammad Dhofar University College of Engineering Electrical and Computer Engineering Department Salalah211 Oman University of Tabuk SNCS Research Centre Tabuk Saudi Arabia King Saud University College of Applied Computer Science Riyadh12372 Saudi Arabia

ISBN: (纸本)9781728126807

Universal Filtered Multi Carrier (UFMC) waveform has been recommended for 5th Generation (5G) cellular networks due to its robustness against synchronization errors and short-packet burst support. However, the UFMC suffers from high Peak-to-Average Power Ratio (PAPR) problem. The high PAPR degrades the efficiency of High Power Amplifier (HPA) and makes the UFMC transmitter inefficient. This paper combines Selective-Mapping (SLM) and Generalized Chirp-Like (GCL) Precoding to minimize the high PAPR of UFMC system. Simulations in MATLAB ® have been carried out to analyze the both parameters PAPR and Symbol Error Rate (SER). computer simulation results show that the proposed SLM based GCL precoded UFMC (SLM-GCL-UFMC) scheme outperform the GCL precoded UFMC scheme, conventional UFMC scheme and conventional OFDM scheme, respectively available in the literature. © 2020 IEEE.

关键词： Peak to average power ratio

来源：评论

学校读者我要写书评

暂无评论

Branch-and-bound for the precedence constrained generalized traveling salesman problem (extended abstract) 13

Branch-and-bound for the precedence constrained generalized ...

引用

13th International Symposium on Combinatorial Search, SoCS 2020

作者： Salman, Raad Ekstedt, Fredrik Damaschke, Peter Fraunhofer-Chalmers Research Centre for Industrial Mathematics Göteborg41288 Sweden Department of Computer Science and Engineering Chalmers University of Technology Göteborg41296 Sweden

来源：评论

学校读者我要写书评

暂无评论

Predicting Solar Proton Events of Solar Cycles 22 - 24 using GOES Proton & soft X-ray flux features

arXiv

引用

arXiv 2023年

作者： Ali, Aatiya Sadykov, Viacheslav Kosovichev, Alexander Kitiashvili, Irina N. Oria, Vincent Nita, Gelu M. Illarionov, Egor O'Keefe, Patrick M. Francis, Fraila Chong, Chun-Jie Kosovich, Paul Marroquin, Russell D. Physics & Astronomy Department Georgia State University AtlantaGA30303 United States Physics Department New Jersey Institute of Technology NewarkNJ07102 United States NASA Ames Research Center Moffett FieldCA94035 United States Computer Science Department New Jersey Institute of Technology NewarkNJ07102 United States Department of Mechanics and Mathematics Moscow State University Moscow119991 Russia Moscow Center of Fundamental and Applied Mathematics Moscow119234 Russia Department of Physics University of California San Diego La Jolla CA92093 United States

Solar Energetic Particle (SEP) events and their major subclass, Solar Proton Events (SPEs), can have unfavorable consequences on numerous aspects of life and technology, making them one of the most harmful effects of solar activity. Garnering knowledge preceding such events by studying operational data flows is essential for their forecasting. Considering only Solar Cycle (SC) 24 in our previous study (Sadykov et al. 2021), we found that it may be sufficient to utilize only proton and soft X-ray (SXR) parameters for SPE forecasts. Here, we report a catalog recording ≥10 MeV ≥10 particle flux unit SPEs with their properties, spanning SCs 22-24, using NOAA's Geostationary Operational Environmental Satellite flux data. We report an additional catalog of daily proton and SXR flux statistics for this period, employing it to test the application of machine learning (ML) on the prediction of SPEs using a Support Vector Machine (SVM) and eXtreme Gradient Boosting (XGBoost). We explore the effects of training models with data from one and two SCs, evaluating how transferable a model can be across different time periods. XGBoost proved to be more accurate than SVMs for almost every test considered, while outperforming operational SWPC NOAA predictions and a persistence forecast. Interestingly, training done with SC 24 produces weaker TSS and HSS2, even when paired with SC 22 or SC 23, indicating transferability issues. This work contributes towards validating forecasts using long-spanning data- an understudied area in SEP research that should be considered to verify the cross-cycle robustness of ML-driven forecasts. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Dynamic MRI Reconstruction with Global-to-local Diffusion Model

arXiv

引用

arXiv 2024年

作者： Guan, Yu Zhang, Kunlong Qi, Qi Wang, Dong Ke, Ziwen Wang, Shaoyu Liang, Dong Liu, Qiegen School of Mathematics and Computer Sciences Nanchang University Nanchang330031 China Department of Electronic Information Engineering Nanchang University Nanchang330031 China Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL United States Paul C. Lauterbur Research Center for Biomedical Imaging SIAT Chinese Academy of Sciences Shenzhen518055 China

Diffusion models have recently demonstrated considerable advancement in the generation and reconstruction of magnetic resonance imaging (MRI) data. These models exhibit great potential in handling unsampled data and reducing noise, highlighting their promise as generative models. However, their application in dynamic MRI remains relatively underexplored. This is primarily due to the substantial amount of fully-sampled data typically required for training, which is difficult to obtain in dynamic MRI due to its spatio-temporal complexity and high acquisition costs. To address this challenge, we propose a dynamic MRI reconstruction method based on a time-interleaved acquisition scheme, termed the Global-to-local Diffusion Model. Specifically, fully encoded full-resolution reference data are constructed by merging under-sampled k-space data from adjacent time frames, generating two distinct bulk training datasets for global and local models. The global-to-local diffusion framework alternately optimizes global information and local image details, enabling zero-shot reconstruction. Extensive experiments demonstrate that the proposed method performs well in terms of noise reduction and detail preservation, achieving reconstruction quality comparable to that of supervised approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A Survey of Artificial Intelligence Solutions in Response to the COVID-19 Pandemic in Saudi Arabia

引用

Procedia computer science 2021年 194卷 190-201页

作者： Jailan Aljizawi Dina Dalloul Layal Ghryani Shaymaa AlDabbagh Tayeb Brahimi Computer Science Department College of Engineering Effat University Jeddah Saudi Arabia. Energy and Technology Research Center Natural Science Mathematics and Technology Unit College of Engineering Effat University Jeddah Saudi Arabia.

Artificial Intelligence (AI) has a significant impact on the course of the COVID-19 pandemic from various aspects. This paper aims to explore the trends of AI applications and how they help predict and prevent the progress of COVID-19 in Saudi Arabia. The method used in this study is based on a narrative review of recent literature on AI and COVID-19 and on a survey conducted on 211 participants. Results show that AI is a crucial element to overcoming COVID 19. The use of COVID-19 related Apps that helped reduce the pandemic spread was more common among the age group participants ranging from 15 - 30. The study concluded that COVID-19 made a positive impact on everyone, and by the use of technology, things got much more comfortable to help in enduring any long-term health consequences.

关键词： Artificial Intelligence COVID-19 pandemic

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Speech Representation Learning: A Review

arXiv

引用

arXiv 2022年

作者： Mohamed, Abdelrahman Lee, Hung-Yi Borgholt, Lasse Havtorn, Jakob D. Edin, Joakim Igel, Christian Kirchhoff, Katrin Li, Shang-Wen Livescu, Karen Maaløe, Lars Sainath, Tara N. Watanabe, Shinji Meta United States The Department of Electrical Engineering Taiwan University Taiwan The Department of Computer Science & Information Engineering National Taiwan University Taiwan The Department of Computer Science University of Copenhagen Denmark The Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Corti AI Denmark AWS AI Labs Amazon Seattle98121 United States The Toyota Technological Institute at Chicago ChicagoIL60615 United States The Language Technologies Institute Carnegie Mellon University PittsburghPA15213 United States

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels required for many downstream scenarios. Speech representation learning is experiencing similar progress in three main categories: generative, contrastive, and predictive methods. Other approaches rely on multi-modal data for pre-training, mixing text or visual data streams with speech. Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years. This review presents approaches for self-supervised speech representation learning and their connection to other research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we review recent efforts on benchmarking learned representations to extend the application beyond speech recognition. © 2022, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Meta-Analysis of Artificial Intelligence Applications for Tracking COVID-19: The Case of the U.A.E

引用

Procedia computer science 2021年 194卷 180-189页

作者： Hala Haneya Dhekra AlKaf Faigah Bajammal Tayeb Brahimi Computer Science Department College of Engineering Effat University Jeddah Saudi Arabia. Energy and Technology Research Center Natural Science Mathematics and Technology Unit College of Engineering Effat University Jeddah Saudi Arabia.

Coronavirus disease (COVID-19) is an infectious respiratory disease that was first found in Wuhan, China, on December 31, 2019. It is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). As of November 10, 2020, more than fifty million cases have been confirmed, and more than one million deaths have been reported globally. This situation has created a serious challenge for all countries to institute a variety of control measures to track and slow down the spread of the virus and prevent the increasing number of deaths. In recent years, there has been an ongoing interest in using Artificial Intelligence (A.I.) in healthcare to create new treatments and detecting diseases. The objective of this study is to analyze the application and the impact of A.I. on the breakout of COVID-19 and discuss the contribution of A.I. to the fight against the pandemic based on the most recent applications used in the United Arab Emirates, including Dubai Police Movement Restriction Monitoring System, Taxis Preventive Measures Compliance System, Mobile App "Wai-Eye," Smart Helmets, Virtual Doctor, and The department of Health - Abu Dhabi (DoH) Remote Healthcare App. The method used in this study is based on a meta-analysis of recent COVID-19 studies from various databases such as ScienceDirect, Sage Journals, SpringerLink, researchGate, Emerald Open research, and IEEE Xplore. The COVID-19 data was based on Johns Hopkins University Center for Systems Science and engineering (JHU CCSE). Results showed that A.I. applications provided the necessary prevention of the spread of COVID-19, assisted in monitoring restrictions and preventive measures violations, and provided remote healthcare, which directly impacted the number of hospital visits amidst the lockdown. The study concluded that A.I. has proven to be effective in supporting governments in fighting the pandemic.

关键词： Artificial Intelligence COVID-19 applications detection prevention

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Amazon Customer Reviews Using Bi-Lstm, Bi-Gru, and Distilbert for the Purpose of Opinion Miningsentiment Analysis of Amazon Customer Reviews Using Bi-Lstm, Bi-Gru, and Distilbert for the Purpose of Opinion Mining

SSRN

引用

SSRN 2023年

作者： Tebyani, Sahand Jazayeri, Kian Ahadi, Seyedeh Aridis Çelebi, Erbuğ Jahandar, Farzad Department of Management Information Systems School of Applied Sciences Cyprus International University Haspolat Turkish Republic of Northern Cyprus Cyprus Department of Engineering Artificial Intelligence Application and Research Center Cyprus International University Haspolat Turkish Republic of Northern Cyprus Cyprus Khoury College of Computer Science Northeastern University United States Cyprus International University Cyprus

Recurrent Neural Networks (RNNs) have long had a dominant position in the fields of sentiment analysis and Natural Language Processing (NLP). This research gives a thorough comparative analysis of two unique models for opinion mining: Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Gated Recurrent Units (Bi-GRU). Notably, these models have a GloVe-based tokenizer installed to improve their verbal comprehension. We use the Amazon reviews dataset, concentrating on mobile devices and accessories, a rich source of varied user opinions, to assess their effectiveness. We compare their performance to that of the powerful large language model DistilBERT in addition to bespoke models. Our study goes into the complex technique of sentiment analysis to unearth subtle insights. Performance assessments cover a wide range of measures and factors and provide a comprehensive understanding of the models' capabilities. We also contrast how well these models extract highly relevant terms, demonstrating how well they can extract insightful information from user-generated content. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

IoT device profiling: From MUD files to S×C contracts

IoT device profiling: From MUD files to S×C contracts

引用

2020 Open Identity Summit

作者： Matthíasson, Guoni Giaretta, Alberto Dragoni, Nicola Department of Applied Mathematics and Computer Science Anker Engelunds Vej 1 Kgs. Lyngby2800 Denmark Örebro University AASS Research Centre Fakultetsgatan 1 Örebro702 81 Sweden

ISBN: (纸本)9783885796992

Security is a serious, and often neglected, issue in the Internet of Things (IoT). In order to improve IoT security, researchers proposed to use Security-by-Contract (S×C), a paradigm originally designed for mobile application platforms. However, S×C assumes that manufacturers equip their devices with security contracts, which makes hard to integrate legacy devices with S×C. In this paper, we explore a method to extract S×C contracts from legacy devices' Manufacturer Usage Descriptions (MUDs). We tested our solution on 28 different MUD files, and we show that it is possible to create basic S×C contracts, paving the way to complete extraction tools. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Internet of things

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：