检索结果-内蒙古大学图书馆

Conflict-Resilient Incremental Offloading of Deep Neural Networks to the Edge of Smart Environment

MATHEMATICAL PROBLEMS IN ENGINEERING 2021年第1期2021卷

作者： Chen, Zhongmin Xu, Zhiwei Wan, Jianxiong Tian, Jie Liu, Limin Zhang, Yujun Inner Mongolia Univ Technol Coll Data Sci & Applicat Hohhot 100080 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Inner Mongolia Autonomous Reg Engn & Technol Res Big Data Based Software Serv Hohhot 100080 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China New Jersey Inst Technol Dept Comp Sci 323 Dr Martin Luther King Jr Blvd Newark NJ 07102 USA

Novel smart environments, such as smart home, smart city, and intelligent transportation, are driving increasing interest in deploying deep neural networks (DNN) in edge devices. Unfortunately, deploying DNN at resource-constrained edge devices poses a huge challenge. These workloads are computationally intensive. Moreover, the edge server-based approach may be affected by incidental factors, such as network jitters and conflicts, when multiple tasks are offloaded to the same device. A rational workload scheduling for smart environments is highly desired. In this work, we propose a Conflict-resilient Incremental Offloading of Deep Neural Networks at Edge (CIODE) for improving the efficiency of DNN inference in the edge smart environment. CIODE divides the DNN model into several partitions by layer and incrementally uploads them to local edge nodes. We design a waiting lock-based scheduling paradigm to choose edge devices for DNN layers to be offloaded. In detail, an advanced lock mechanism is proposed to handle concurrency conflicts. Real-world testbed-based experiments demonstrate that, compared with other state-of-the-art baselines, CIODE outperforms the DNN inference performance of these popular baselines by 20% to 70% and significantly improves the robustness under the insight of neighboring collaboration.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A New Characterization of 2-Resilient Rotation Symmetric Boolean Functions

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2023年第9期E106A卷 1268-1271页

作者： Du, Jiao Chen, Ziyu Dong, Le Wang, Tianyin Pang, Shanqi Henan Normal Univ Henan Engn Lab Big Data Stat Anal & Optimal Contro Xinxiang 453007 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin 541004 Peoples R China Luoyang Normal Univ Sch Math Sci Luoyang 471934 Peoples R China

In this paper, the notion of 2-tuples distribution matrices of the rotation symmetric orbits is proposed, by using the properties of the 2-tuples distribution matrix, a new characterization of 2-resilient rotation symmetric Boolean functions is demonstrated. Based on the new characterization of 2-resilient rotation symmetric Boolean functions, constructions of 2-resilient rotation symmetric Boolean functions (RSBFs) are further studied, and new 2-resilient rotation symmetric Boolean functions with prime variables are constructed.

关键词： cryptography rotation symmetry support table orthogonal array resilient function

来源：评论

学校读者我要写书评

暂无评论

QoE-Driven data Communication Framework for Consumer Electronics in Tele-Healthcare System

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2023年第4期69卷 719-733页

作者： Zhang, Tongguang Zhou, Xiaokang Liu, Jialei Cheng, Bo Xu, Xiaolong Qi, Lianyong Tian, Qiaomei Wan, Zhiguo Xinxiang Univ Sch 3D Printing Xinxiang 453003 Henan Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Shiga Univ Fac Data Sci Hikone 5228522 Japan RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan Hubei Univ Arts & Sci Comp Sch Xiangyang 441053 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 211544 Peoples R China China Univ Petr East China Coll Comp Sci & Technol Qingdao 266580 Peoples R China Henan Normal Univ Sch Comp & Informat Engn Xinxiang 453007 Peoples R China Xinxiang Univ Sch Phys Xinxiang 453003 Peoples R China Zhejiang Lab Basic Theory Res Inst Hangzhou 311122 Peoples R China

The COVID-19 pandemic has elicited interest in the development of novel, low-cost solutions for tele-healthcare that patients can use to consult with doctors using consumer electronics (CEs). Android CEs typically have multiple network interfaces. Simultaneous access to multiple interfaces can greatly enhance users' quality of experience (QoE). To enhance data transmission throughput and robustness in tele-healthcare systems, we propose a QoE-driven data communication framework which can cater to all types of healthcare apps. The framework includes a QoE-driven congestion controller (QCC) and a QoE-driven MPTCP (multipath transmission control protocol) scheduler (QMS). Different app types correspond to specific QoE parameters that influence the QCC and QMS for meeting diverse healthcare app requirements. No server-side modifications are needed for this framework;only changes on the Android client side are necessary. We implement and experiment with the framework on an Android 13 smartphone in a real environment. Experimental results confirm the framework's effectiveness and availability, and show that the QCC and QMS reduce completion time for transferring small files by at least 4.71% and for transferring big file by at least 13.94% compared with existing solutions.

关键词： Congestion controller MPTCP packet scheduler quality of experience tele-healthcare

来源：评论

学校读者我要写书评

暂无评论

Crosslingual named entity recognition for clinical de-identification applied to a COVID-19 Italian data set

引用

APPLIED SOFT COMPUTING 2020年 97卷 106779页

作者： Catelli, Rosario Gargiulo, Francesco Casola, Valentina De Pietro, Giuseppe Fujita, Hamido Esposito, Massimo CNR Inst High Performance Comp & Networking ICAR Via Pietro Castellino 111 I-80131 Naples Italy Univ Naples Federico II Dept Elect Engn & Informat Technol DIETI Naples Italy Ho Chi Minh City Univ Technol HUTECH Fac Informat Technol Ho Chi Minh City Vietnam Univ Granada Andalusian Res Inst Data Sci & Computat Intellige Granada Spain Iwate Prefectural Univ Fac Software & Informat Sci Takizawa Iwate Japan

The COrona VIrus Disease 19 (COVID-19) pandemic required the work of all global experts to tackle it. Despite the abundance of new studies, privacy laws prevent their dissemination for medical investigations: through clinical de-identification, the Protected Health Information (PHI) contained therein can be anonymized so that medical records can be shared and published. The automation of clinical de-identification through deep learning techniques has proven to be less effective for languages other than English due to the scarcity of data sets. Hence a new Italian de-identification data set has been created from the COVID-19 clinical records made available by the Italian Society of Radiology (SIRM). Therefore, two multi-lingual deep learning systems have been developed for this low-resource language scenario: the objective is to investigate their ability to transfer knowledge between different languages while maintaining the necessary features to correctly perform the Named Entity Recognition task for de-identification. The systems were trained using four different strategies, using both the English Informatics for Integrating Biology & the Bedside (i2b2) 2014 and the new Italian SIRM COVID-19 data sets, then evaluated on the latter. These approaches have demonstrated the effectiveness of cross-lingual transfer learning to de-identify medical records written in a low resource language such as Italian, using one with high resources such as English. (C) 2020 Elsevier B.V. All rights reserved.

关键词： COVID-19 Clinical de-identification Named entity recognition Deep learning Annotated Italian data set

来源：评论

学校读者我要写书评

暂无评论

Integrating the Internet of Things and data Science

引用

IEEE CLOUD COMPUTING 2018年第3期5卷 12-26页

作者： Ranjan, Rajiv Rana, Omer Nepal, Surya Yousif, Mazin James, Philip Wen, Zhenyu Barr, Stuart Watson, Paul Jayaraman, Prem Prakash Georgakopoulos, Dimitrios Villari, Massimo Fazio, Maria Garg, Saurabh Buyya, Rajkumar Wang, Lizhe Zomaya, Albert Y. Dustdar, Schahram Newcastle Univ Comp Sci Newcastle Upon Tyne Tyne & Wear England Cardiff Univ Engn Sch Comp Sci & Informat Cardiff S Glam Wales CSIRO Data61 Canberra ACT Australia T Syst Int Architecture Royal Dutch Shell Global Account Frankfurt Germany Newcastle Univ Sch Civil Engn & Geosci Newcastle Upon Tyne Tyne & Wear England Newcastle Univ Newcastle Upon Tyne Tyne & Wear England Swinburne Univ Technol Hawthorn Vic Australia Univ Messina Comp Sci Messina Italy Univ Tasmania Dept Comp & Informat Syst Hobart Tas Australia Univ Melbourne Comp Sci & Software Engn Melbourne Vic Australia Chinese Acad Sci Inst Remote Sensing & Digital Earth Beijing Peoples R China Univ Sydney High Performance Comp & Networking Sydney NSW Australia TU Wien Comp Sci Vienna Austria TU Wien Distributed Syst Grp Vienna Austria

This article discusses research challenges related to devising a new IoT programming paradigm for orchestrating IoT applications' composition and data processing across heterogeneous computing infrastructure (Clou... 详细信息

关键词： Cloud Computing Sensors Internet Of Things Programming data Analysis Distributed databases Cloud Computing Edge Computing Internet Of Things Io T data Science

来源：评论

学校读者我要写书评

暂无评论

A new approach of analyzing time-varying dynamical equation via an optimal principle

引用

MODERN PHYSICS LETTERS B 2017年第8期31卷

作者： Zhao, Hui Li, Lixiang Peng, Haipeng Kurths, Juergen Xiao, Jinghua Yang, Yixian Li, Ang Beijing Univ Posts & Telecommun Sch Sci State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Informat Secur Ctr State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China State Key Lab Publ Big Data Guizhou 550025 Peoples R China Potsdam Inst Climate Impact Res D-14473 Potsdam Germany Beijing Univ Posts & Telecommun Sch Software Engn Beijing 100876 Peoples R China

In this paper, an innovative design approach is proposed to solve time-varying dynamical equation, including matrix inverse equation and Sylvester equation. Based on the precondition of the existing solution of time-varying dynamical equation, different from previous approach to solve unknown matrix, an optimal design principle is used to solve the unknown variables. A performance index is introduced based on the inherent properties of the time-varying dynamical equation and Euler equation. The solution of time-varying dynamical equation is converted to an optimal problem of performance index. Furthermore, convergence and sensitivity to additive noise are also analyzed, and simulation results confirm that the method is feasible and effective. Especially, in simulations we design a tunable positive parameter in the dynamic optimization model. The tunable parameter is not only helpful to accelerate its convergence but also reduce its sensitivity to additive noise. Meanwhile the comparative simulation results are shown for the convergence accuracy and robustness of this method.

关键词： Time-varying dynamical equation an optimal design principle convergence performance sensitivity to additive noise

来源：评论

学校读者我要写书评

暂无评论

Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2022年

作者： Xu, Xincao Liu, Kai Dai, Penglin Xie, Ruitao Cao, Jingjing Luo, Jiangtao The College of Computer Science Chongqing University Chongqing400040 China The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Transportation and Logistics Engineering Wuhan University of Technology Hubei430063 China The Electronic Information and Networking Research Institute Chongqing University of Posts and Telecommunications Chongqing400065 China

Cooperative sensing and heterogeneous information fusion are critical to realize vehicular cyber-physical systems (VCPSs). This paper makes the first attempt to quantitatively measure the quality of VCPS by designing a new metric called Age of View (AoV). Specifically, we first present the system architecture where heterogeneous information can be cooperatively sensed and uploaded via vehicle-to-infrastructure (V2I) communications in vehicular edge computing (VEC). Logical views are constructed by fusing the heterogeneous information at edge nodes. Further, we formulate the problem by deriving a cooperative sensing model based on the multi-class M/G/1 priority queue, and defining the AoV by modeling the timeliness, completeness and consistency of the logical views. On this basis, a multi-agent deep reinforcement learning solution is proposed. In particular, the system state includes vehicle sensed information, edge cached information and view requirements. The vehicle action space consists of the sensing frequencies and uploading priorities of information. A difference-reward-based credit assignment is designed to divide the system reward, which is defined as the VCPS quality, into the difference reward for vehicles. Edge node allocates V2I bandwidth to vehicles based on predicted vehicle trajectories and view requirements. Finally, we build the simulation model and give a comprehensive performance evaluation, which conclusively demonstrates the superiority of the proposed solution. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MOBILE BIG data FOR URBAN ANALYTICS

引用

IEEE COMMUNICATIONS MAGAZINE 2018年第11期56卷 12-12页

作者： Hui, Pan Li, Yong Ott, Joerg Uhlig, Steve Han, Bo Tan, Kun Univ Helsinki Data Sci Helsinki Finland Univ Helsinki Comp Sci Helsinki Finland Hong Kong Univ Sci & Technol Comp Sci & Engn Dept HKUST DT Syst & Media Lab SyMLab Hong Kong Hong Kong Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China Tech Univ Munich Connected Mobil Munich Germany IRTF DTN Res Grp Honolulu HI USA IEEE Comsoc TCCC Editorial Board Elsevier COMCOM Waikoloa HI USA Queen Mary Univ London Sch Elect Engn & Comp Sci Networks London England AT&T Laos Res Bedminster NJ USA Cent Software Inst Leuven Belgium Huawei Technol Cloud Networking Lab Software Innovat & Dev Luawers Cloud Leuven Belgium

The rapid progress of urbanization not only enables higher populations living in modern cities, but also engenders many “urban diseases,” such as air pollution, traffic congestion, and increased energy consumption. Mobile big data, with advanced communication and information technologies, can be collected through a variety of data sources, including cellular networks, the Internet of Things (IoT), social networks, and so on. This allows detailed analysis on the moving patterns of citizens and behaviors of devices deployed in urban areas, which helps grasp the outlines and the inner flows of cities. Based on those observations, prediction of events and their involved crowds and departments in cities can lead the city to become more intelligent and greener. The articles in this special section offer a comprehensive overview of the state-of-the-art developments in technology, application, and theory for mobile big data for urban analytics.

关键词： Special issues and sections Big data Urban areas Internet of Things Smart cities Environmental factors Social network services Green design

来源：评论

学校读者我要写书评

暂无评论

Immunogenicity of COVID-19 vaccines in patients with diverse health conditions: A comprehensive systematic review

引用

JOURNAL OF MEDICAL VIROLOGY 2022年第9期94卷 4144-4155页

作者： Cho, Kyuyeon Park, Seoyeon Kim, Eun-Young Koyanagi, Ai Jacob, Louis Yon, Dong K. Lee, Seung Won Kim, Min Seo Radua, Joaquim Elena, Dragioti Il Shin, Jae Smith, Lee Yonsei Univ Coll Med Seoul South Korea Chung Ang Univ Dept Hlth Social & Clin Pharm Coll Pharm Evidence Based & Clin Res Lab Seoul South Korea ICREA Pg Lluis Co 23 Barcelona Spain CIBERSAM Res & Dev Unit Parc Sanitari St Joan de Deu Barcelona Spain Univ Versailles St Quentin En Yvelines Fac Med Montigny Le Bretonneux France Seoul Natl Univ Seoul Natl Univ Hosp Dept Pediat Coll Med Seoul South Korea Sejong Univ Dept Data Sci Coll Software Convergence Seoul South Korea Sungkyunkwan Univ Samsung Adv Inst Hlth Sci & Technol SAIHST Samsung Med Ctr Seoul South Korea Kings Coll London Dept Psychosis Studies Inst Psychiat Psychol & Neurosci Early Psychosis Intervent & Clin Detect EPIC Lab London England Mental Hlth Networking Biomed Res Ctr CIBERSAM Barcelona Spain Karolinska Inst Ctr Psychiat Res Dept Clin Neurosci Stockholm Sweden Inst Invest Biomed August Pi & Sunyer IDIBAPS Barcelona Spain Linkoping Univ Pain & Rehabil Ctr Linkoping Sweden Linkoping Univ Dept Hlth Med & Caring Sci Linkoping Sweden Yonsei Univ Dept Pediat Coll Med 50-1 Yonsei RoCPO Box 8044 Seoul 03722 South Korea Anglia Ruskin Univ Ctr Hlth Performance & Wellbeing Cambridge England

It remains unclear how effective COVID-19 vaccinations will be in patients with weakened immunity due to diseases, transplantation, and dialysis. We conducted a systematic review comparing the efficacy of COVID-19 vaccination in patients with solid tumor, hematologic malignancy, autoimmune disease, inflammatory bowel disease, and patients who received transplantation or dialysis. A literature search was conducted twice using the Medline/PubMed database. As a result, 21 papers were included in the review, and seropositivity rate was summarized by specific type of disease, transplantation, and dialysis. When different papers studied the same type of patient group, a study with a higher number of participants was selected. Most of the solid tumor patients showed a seropositivity rate of more than 80% after the second inoculation, but a low seropositivity was found in certain tumors such as breast cancer. Research in patients with certain types of hematological malignancy and autoimmune diseases has also reported low seropositivity, and this may have been affected by the immunosuppressive treatment these patients receive. Research in patients receiving dialysis or transplantation has reported lower seropositivity rates than the general population, while all patients with inflammatory bowel disease have converted to be seropositive. Meta-analysis validating these results will be needed, and studies will also be needed on methods to protect patients with reduced immunity from COVID-19.

关键词： COVID-19 health status immunogenicity seropositivity vaccine

来源：评论

学校读者我要写书评

暂无评论

Shared gene expression signatures between visceral adipose and skeletal muscle tissues are associated with cardiometabolic traits in children with obesity

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 163卷 107085-107085页

作者： Bustos-Aibar, Mireia Aguilera, Concepcion M. Alcala-Fdez, Jesus Ruiz-Ojeda, Francisco J. Plaza-Diaz, Julio Plaza-Florido, Abel Tofe, Ines Gil-Campos, Mercedes Gacto, Maria J. Anguita-Ruiz, Augusto Univ Granada Sch Pharm Dept Biochem & Mol Biol 2 Granada 18071 Spain Carlos III Hlth Inst Biomed Res Networking Ctr Physiopathol Obes & Nut Madrid 28029 Spain Univ Granada Andalusian Res Inst Data Sci & Computat Intellige Dept Comp Sci & Artificial Intelligence Granada 18071 Spain Helmholtz Zentrum Munchen Inst Diabet & Obes RG Adipocytes & Metab Helmholtz Diabet Ctr D-85764 Munich Germany Childrens Hosp Eastern Ontario Res Inst Ottawa ON 181 Canada Univ Granada Sport & Hlth Univ Dept Phys Educ & Sports PROmoting FITness & Hlth Phys act Res GrpRes Ins Granada 18071 Spain Univ Calif Irvine Pediat Exercise & Genom Res Ctr Sch Med Dept Pediat Irvine CA 92617 USA Univ Cordoba Univ Clin Hosp Inst Maimonides Biomed Invest Cordoba Cordoba 14004 Spain Univ Granada Dept Software Engn Granada 18071 Spain ISGlobal Barcelona Inst Global Hlth Barcelona 08003 Spain

Obesity in children is related to the development of cardiometabolic complications later in life, where molecular changes of visceral adipose tissue (VAT) and skeletal muscle tissue (SMT) have been proven to be fundamental. The aim of this study is to unveil the gene expression architecture of both tissues in a cohort of Spanish boys with obesity, using a clustering method known as weighted gene co-expression network analysis. For this purpose, we have followed a multi-objective analytic pipeline consisting of three main approaches;identification of gene co-expression clusters associated with childhood obesity, individually in VAT and SMT (intra-tissue, approach I);identification of gene co-expression clusters associated with obesity metabolic alterations, individually in VAT and SMT (intra-tissue, approach II);and identification of gene co-expression clusters associated with obesity-metabolic alterations simultaneously in VAT and SMT (inter tissue, approach III). In both tissues, we identified independent and inter-tissue gene co-expression signatures associated with obesity and cardiovascular risk, some of which exceeded multiple-test correction filters. In these signatures, we could identify some central hub genes (e.g., NDUFB8, GUCY1B1, KCNMA1, NPR2, PPP3CC) participating in relevant metabolic pathways exceeding multiple-testing correction filters. We identified the central hub genes PIK3R2, PPP3C and PTPN5 associated with MAPK signaling and insulin resistance terms. This is the first time that these genes have been associated with childhood obesity in both tissues. Therefore, they could be potential novel molecular targets for drugs and health interventions, opening new lines of research on the personalized care in this pathology. This work generates interesting hypotheses about the transcriptomics alterations underlying metabolic health alterations in obesity in the pediatric population.

关键词： Childhood obesity Gene co-expression Hierarchical clustering Inter-tissue molecular signatures Skeletal muscle tissue Visceral adipose tissue

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：