检索结果-内蒙古大学图书馆

SatCooper: Enhancing Cooperative Inference Analytics for Satellite Service via Multi-exit DNNs

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Qiyang Wang, Shangguang Guan, Jinglong Donta, Praveen Kumar Ma, Xiao Prasad, RangaRao Venkatesha Dustdar, Schahram Liu, Xuanzhe Peking University School of Computer Science Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Stockholm University Department of Computer and Systems Sciences Kista16455 Sweden Beiyou Shenzhen Institute Shenzhen China Netherlands TU Wien Distributed System Group Wien1040 Austria UPF Barcelona Spain

As a key technology of intelligent satellite-enabled services in B5G or 6G networks, deploying Deep Neural Networks (DNN) models on satellites has been a notable trend, catering to the daily demand for extensive computing-intensive and latency-sensitive tasks. The computing resources are strategically deployed on satellites where sensor data is generated or collected, facilitating the fine-grained computational inference of DNN-based tasks. However, no prior study has comprehensively explored the crucial inference challenges-e.g., the trade-off between the number of tasks completed and accuracy and partitioning models in multi-exit models-in the resource-constrained space environment. Effective scheduling frameworks cater to various streams of inference tasks are scarce because inference performance may deviate from the ideal situation due to changes in task system status, such as task profiles and network state. To this end, we first formulate a gain-aware in-orbit computing inference problem to strike a proper trade-off between inference latency and the number of tasks completed by dynamically selecting optimal early exit points and model partitioning points. We propose an offline dynamic programming-based algorithm that provides an effective solution when comprehensive system details are to be predicted. We have developed an online learning-based method to schedule inference tasks with uncertain and dynamic system statuses in real-world situations. Our evaluation shows that, compared to baseline methods, the online learning-based algorithm can improve task gain by an average of 87.3% across various tasks. © 2002-2012 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

TELKA: Twin-Enhanced Learning for Kubernetes Applications

TELKA: Twin-Enhanced Learning for Kubernetes Applications

引用

IEEE Symposium on computers and Communications (ISCC)

作者： Mattia Zaccarini Davide Borsatti Walter Cerroni Luca Foschini Genady Ya. Grabarnik Lorenzo Manca Filippo Poltronieri Domenico Scotece Larisa Shwartz Cesare Stefanelli Mauro Tortonesi Distributed Systems Research Group University of Ferrara Ferrara Italy University of Bologna Bologna Italy Department of Mathematics and Computer Science St. John’s University Queens NY USA Operational Innovation IBM TJ Watson Research Center NY USA

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

Chaos engineering is the discipline of injecting computing and network faults, such as increased network latency and unavailability of computing nodes, into an IT system to help developers in identifying problems that could arise in a production environment and tackle them. Several tools have emerged to ease the application of chaos engineering to complex IT systems, leveraging microservice and container-based applications deployed on Kubernetes. However, applying of such tools requires several phases to be put into practice, from defining a steady state to establishing an effective response plan if something goes wrong. To ease the application of chaos engineering in improving the resilience of Kubernetes applications, this work presents a smart scheduler for Kubernetes called TELKA: a Twin-Enhanced Learning for Kubernetes Applications, which combines chaos engineering, Digital Twin (DT), and Reinforcement Learning (RL) methodologies to mitigate the effects of computing and network faults. Instead of interacting directly with the physical Kubernetes application, TELKA learns by interacting with a digital twin, thus reducing the learning time and the operation costs related to the application of chaos engineering. Experiment results compare TELKA with other approaches to show its effectiveness in mitigating the adverse effects of injected faults.

关键词： Chaos Fault diagnosis computers Costs Microservice architectures Reinforcement learning Production Digital twins Steady-state Resilience

来源：评论

学校读者我要写书评

暂无评论

From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation systems: Survey, Taxonomy and Performance Evaluation

arXiv

引用

arXiv 2024年

作者： Shahin, Nada Ismail, Leila Intelligent Distributed Computing and Systems Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Emirates Center for Mobility Research United Arab Emirates University Abu Dhabi United Arab Emirates

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language machine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation *** Codes I.2, I.2.7, I.4, I.4.9 © 2024, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Utilization in Hyperledger Fabric: A Comprehensive SPN-Based Performance Evaluation Paradigm

Optimal Resource Utilization in Hyperledger Fabric: A Compre...

引用

IEEE Symposium on Network Operations and Management

作者： Carlos Melo Glauber Gonçalves Francisco A. Silva Leonel Feitosa Iure Fé André Soares Eunmi Choi Tuan Anh Nguyen Dugki Min Applied Research on Distributed Systems Lab (PASID) Federal University of Piauí (UFPI) Brazil School of Software College of Computer Science Kookmin University Seoul South Korea Konkuk Aerospace Design-Airworlhiness Research Inslilule (KADA) Konkuk Universily Seoul Soulh Korea Department of Computer Science and Engineering Konkuk University Seoul South Korea

ISBN: (数字)9798350327939

ISBN: (纸本)9798350327946

Hyperledger Fabric stands as a leading framework for permissioned block-chain systems, ensuring data security and audit-ability for enterprise applications. As applications on this platform grow, understanding its complex configuration concerning various block-chain parameters becomes vital. These configurations significantly affect the system’s performance and cost. In this research, we introduce a Stochastic Petri Net (SPN) model to analyze Hyper-ledger Fabric’s performance, considering variations in block-chain parameters, computational resources, and transaction rates. We provide case studies to validate the utility of our model, aiding block-chain administrators in determining optimal configurations for their applications. A key observation from our model highlights the block size’s role in system response time. We noted an increased mean response time, between 1 to 25 seconds, due to variations in transaction arrival rates.

关键词： Performance evaluation distributed ledger Computational modeling Data security Petri nets Stochastic processes Fabrics

来源：评论

学校读者我要写书评

暂无评论

Decoding the Granular Puzzle of Macromolecules: Efficient 3D Protein Structure Alignment in the Age of Big Data with Apache Spark

Decoding the Granular Puzzle of Macromolecules: Efficient 3D...

引用

IEEE International Conference on Big Data

作者： Bożena Małysiak-Mrozek Paulina Pawłowicz Vaidy Sunderam Che-Lun Hung Andrzej Kwiecień Dariusz Mrozek Department of Distributed Systems and Informatic Devices Silesian University of Technology Gliwice Poland Department of Applied Informatics Silesian University of Technology Gliwice Poland Department of Computer Science Emory University Atlanta GA USA Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei City Taiwan

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Proteins are complex biological information granules that play a crucial role in various cellular processes within living organisms. Processing 3D protein structures, which are the most informative from the biological point of view, is both intricate and time-consuming. In particular, performing 3D protein structure searches against large protein datasets involves identifying similarities and conducting structural alignments across numerous molecules (granules). This task demands advanced methods for matching identical and similar regions within protein structures and substantial computational resources to handle large collections of macromolecular data efficiently. In this paper, we present our parallel implementation of scalable 3D structural alignment on the Apache Spark big data platform. We describe a customized approach that leverages Spark data transformations within the data processing pipeline for the alignment process. Our experimental results demonstrate that this solution, tightly integrated with the Spark processing model, is both efficient and scalable, even with the increasing volume of protein structure data.

关键词： Proteins Solid modeling Three-dimensional displays Pipelines Cluster computing Big Data Biology Organisms Decoding Sparks

来源：评论

学校读者我要写书评

暂无评论

Cloud Telescope: A distributed architecture for capturing Internet Background Radiation

Cloud Telescope: A distributed architecture for capturing In...

引用

IEEE International Conference on Cloud Networking (CLOUDNET)

作者： Fabricio Bortoluzzi Barry Irwin Lucas Silvero Beiler Carla Merkle Westphall Cyber Security Programme Noroff University College Kristiansand Norway Postgraduate Programme in Computer Science University of Santa Catarina Florianópolis Brazil Department of Computer Science Rhodes University Grahamstown South Africa Laboratory of Embedded & Distributed Systems University of Vale do Itajai Itajai Brazil

Internet Background Radiation (IBR) comprises a range of unsolicited traffic directed towards Internet hosts. In general, this type of traffic is characterised by high levels of port scanning activity, malware propagation, application exploits, system misconfiguration and denial-of-service attacks. IBR capture is typically undertaken by a system termed a network telescope. This records unfiltered incoming internet traffic for a specific CIDR block in the form of a packet capture (PCAP) file for analysis. This work proposes a novel, cloud-native approach to capturing IBR by the deployment of an ephemeral and reproducible architecture, described as code, distributed across all regions of a cloud service provider. In this paper we discuss the technical and financial viability of using a fleet of small-sized compute instances, in a spot price auction model, to maximise platform collection, capillarity and duration. We also present an overview analysis of the primary characteristics of IBR as collected during a month long proof-of-concept experiment across 26 regions of a cloud service provider in May 2023. Our analysis discusses the aspects of the dataset in quantitative terms: traffic aggregation per protocol, top TCP and UDP ports, top radiation sources and radiation distribution per cloud region. We also provide an overview of the most relevant threats detected. Our results include a formalisation and validation of the cloud telescope, with the corresponding supporting architecture described in Terraform and Ansible. The aggregate dataset amounted to 2.2 GB, and 21.8 million packets. Composition by protocol was 78% TCP, 14% ICMP and 8% UDP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PupilRec: Leveraging Pupil Morphology for Recommending on Smartphones

PupilRec: Leveraging Pupil Morphology for Recommending on Sm...

引用

作者： Shen, Xiangyu Jiang, Hongbo Liu, Daibo Yang, Kehua Deng, Feiyang Lui, John C. S. Liu, Jiangchuan Dustdar, Schahram Luo, Jun Hunan University College of Computer Science and Electronic Engineering Hunan Changsha410082 China The City University of Hong Kong School of Graduate Studies Hong Kong The Chinese University of Hong Kong Computer Science and Engineering Department Hong Kong Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada Vienna University of Technology Distributed Systems Group Vienna1040 Austria Nanyang Technological University School of Computer Engineering 639798 Singapore

As mobile shopping has gradually become the mainstream shopping mode, recommendation systems are gaining an increasingly wide adoption. Existing recommendation systems are mainly based on explicit and implicit user behaviors. However, these user behaviors may not directly indicate users' inner feelings, causing erroneous user preference estimation and thus leading to inaccurate recommendations. Inspired by our key observation on the correlation between pupil size and users' inner feelings, we consider using the change of pupil size when browsing to model users' preferences, so as to achieve targeted recommendations. To this end, we propose PupilRec as a computer-vision-based recommendation framework involving a mobile terminal and a server side. On the mobile terminal, PupilRec collects users' pupil size change information through the front camera of smartphones;it then preprocesses the raw pupil size data before transmitting them to the server. On the server side, PupilRec utilizes the Tsfresh package and Random Forest algorithm to figure out the key time-series features directly implying user preferences. PupilRec then trains a neural network to fit a user preference model. Using this model, PupilRec predicts user preference to obtain a user-product matrix and further simplifies it by singular value decomposition. Finally, the real-time recommendation is achieved by a collaborative filtering module that retrieves recommended contents to users smartphones. We prototype PupilRec and conduct both experiments and field studies to comprehensively evaluate the effectiveness of PupilRec by recruiting 67 volunteers. The overall results show that PupilRec can accurately estimate users' preference and can recommend products users interested in. © 2014 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Effective Prediction of Energy Consumption in Automated Guided Vehicles with Recurrent and Convolutional Neural Networks

Effective Prediction of Energy Consumption in Automated Guid...

引用

IEEE International Conference on Big Data

作者： Pawel Benecki Daniel Kostrzewa Piotr Grzesik Bohdan Shubyn Jia-Hao Syu Jerry Chun-Wei Lin Vaidy Sunderam Dariusz Mrozek Department of Applied Informatics Silesian University of Technology Gliwice Poland Department of Telecommunications Lviv Polytechnic National University Lviv Ukraine Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Distributed Systems and Informatics Devices Silesian University of Technology Gliwice Poland Department of Computer Science Emory University Atlanta GA USA

Detection and prediction of failures in Automated Guided Vehicles (AGV) are essential for the uninterrupted operation of production plants. Anomaly detection is usually achieved by comparing expected measurement values with actual observations. Thus, it is crucial to predict telemetry signals properly. In this paper, we research the prediction of energy consumption using state-of-the-art Artificial Neural Networks architectures (SCINet) compared with other Recurrent Neural Network (RNN) approaches on the data streams acquired from CoBotAGV. We especially focus on the possibility of applying feature weighting. We show that it can improve prediction capabilities. We also investigate resource utilization in terms of time to fit the embedded AGV environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Partitioned deep learning of fluid-structure interaction

arXiv

引用

arXiv 2021年

作者： Totounferoush, Amin Schumacher, Axel Schulte, Miriam Institute for Parallel and Distributed Systems Department of Computer Science University of Stuttgart Stuttgart70569 Germany

We present a partitioned neural network-based framework for learning of fluid-structure interaction (FSI) problems. We decompose the simulation domain into two smaller sub-domains, i.e., fluid and solid domains, and incorporate an independent neural network for each. A library is used to couple the two networks which takes care of boundary data communication, data mapping and equation coupling. Simulation data are used for training of the both neural networks. We use a combination of convolutional and recurrent neural networks (CNN and RNN) to account for both spatial and temporal connectivity. A quasi-Newton method is used to accelerate the FSI coupling convergence. We observe a very good agreement between the results of the presented framework and the classical numerical methods for simulation of 1d fluid flow inside an elastic tube. This work is a preliminary step for using neural networks to speed-up the FSI coupling convergence by providing an accurate initial guess in each time step for classical numerical solvers. © 2021, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

[dai:si] - A modular dataset retrieval framework with a semantic search for biological data

[dai:si] - A modular dataset retrieval framework with a sema...

引用

Joint Ontology Workshops 2021 Episode VII: The Bolzano Summer of Knowledge, JOWO 2021

作者： Shafiei, Fateme Löffler, Felicitas Thiel, Sven Opasjumruskit, Kobkaew Grabiger, Denis Rauh, Pauline König-Ries, Birgitta Heinz Nixdorf Chair for Distributed Information Systems Department of Mathematics and Computer Science Friedrich Schiller University Jena Jena Germany Jena Germany Halle-Jena-Leipzig Germany Michael-Stifel-Center for Data-Driven and Simulation Science Jena Germany

Dataset search is receiving increasing attention in a scholar's daily research practice. In biodiversity research, dataset retrieval in particular is a challenging and time-consuming task as most search services in current data portals only offer a simple keyword-based search. In this work we introduce [Dai:Si], a modular framework for dataset retrieval with a semantic search for biological data. [Dai:Si] is based on a former semantic search service developed within the scope of the GFBio project. It allows the expansion of query keywords with related terms using GFBio's Terminology Service. This new version provides an enhanced user interface (UI) with explanations of related semantic terms upon demand. Due to its modular structure, [Dai:Si]'s semantic service can now be used independently of the user interface (UI). © 2021 CEUR-WS. All rights reserved.

关键词： Biodiversity

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：