检索结果-内蒙古大学图书馆

36th IEEE International Performance Computing and Communications Conference, IPCCC 2017

作者： Yang, Zhengyu Hoseinzadeh, Morteza Wong, Ping Artoux, John Mayers, Clay Evans, David Thomas Bolt, Rory Thomas Bhimani, Janki Mi, Ningfang Swanson, Steven Dept. Of Electrical and Computer Engineering Northeastern University BostonMA02115 United States Dept. Of Computer Science and Engineering University of California San Diego San DiegoCA92093 United States Samsung Semiconductor Inc. Memory Solution Research Lab Software Group San DiegoCA92121 United States

ISBN: (纸本)9781509064687

In the year of 2017, more and more datacenters have started to replace traditional SATA and SAS SSDs with NVMe SSDs due to NVMe's outstanding performance [1]. However, for historical reasons, current popular deployments of NVMe in VM-hypervisor-based platforms (such as VMware ESXi [2]) have numbers of intermediate queues along the I/O stack. As a result, performance is bottlenecked by synchronization locks in these queues, cross-VM interference induces I/O latency, and most importantly, up-to-64K-queue capability of NVMe SSDs cannot be fully utilized. In this paper, we developed a hybrid framework of NVMe-based storage system called 'H-NVMe', which provides two VM I/O stack deployment modes 'Parallel Queue Mode' and 'Direct Access Mode'. The first mode increases parallelism and enables lock-free operations by implementing local lightweight queues in the NVMe driver. The second mode further bypasses the entire I/O stack in the hypervisor layer and allows trusted user applications whose hosting VMDK (Virtual Machine Disk) files are attached with our customized vSphere IOFilters [3] to directly access NVMe SSDs to improve the performance isolation. This suits premium users who have higher priorities and the permission to attach IOFilter to their VMDKs. H-NVMe is implemented on VMware EXSi 6.0.0, and our evaluation results show that the proposed H-NVMe framework can significant improve throughputs and bandwidths compared to the original inbox NVMe solution. © 2017 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

AutoTiering: Automatic data placement manager in multi-tier all-flash datacenter 36

AutoTiering: Automatic data placement manager in multi-tier ...

引用

36th IEEE International Performance Computing and Communications Conference, IPCCC 2017

作者： Yang, Zhengyu Hoseinzadeh, Morteza Andrews, Allen Mayers, Clay Evans, David Bolt, Rory Thomas Bhimani, Janki Mi, Ningfang Swanson, Steven Dept. Of Electrical and Computer Engineering Northeastern University BostonMA02115 United States Dept. Of Computer Science and Engineering University of California San Diego San DiegoCA92093 United States Samsung Semiconductor Inc. Memory Solution Research Lab Software Group San DiegoCA92121 United States

ISBN: (纸本)9781509064687

In the year of 2017, the capital expenditure of Flash-based Solid State Drivers (SSDs) keeps declining and the storage capacity of SSDs keeps increasing. As a result, the 'selling point' of traditional spinning Hard Disk Drives (HDDs) as a backend storage - low cost and large capacity - is no longer unique, and eventually they will be replaced by low-end SSDs which have large capacity but perform orders of magnitude better than HDDs. Thus, it is widely believed that all-flash multi-tier storage systems will be adopted in the enterprise datacenters in the near future. However, existing caching or tiering solutions for SSD-HDD hybrid storage systems are not suitable for all-flash storage systems. This is because that all-flash storage systems do not have a large speed difference (e.g., 10x) among each tier. Instead, different specialties (such as high performance, high capacity, etc.) of each tier should be taken into consideration. Motivated by this, we develop an automatic data placement manager called 'AutoTiering' to handle virtual machine disk files (VMDK) allocation and migration in an all-flash multitier datacenter to best utilize the storage resource, optimize the performance, and reduce the migration overhead. AutoTiering is based on an optimization framework, whose core technique is to predict VM's performance change on different tiers with different specialties without conducting real migration. As far as we know, AutoTiering is the first optimization solution designed for all-flash multi-tier datacenters. We implement AutoTiering on VMware ESXi [1], and experimental results show that it can significantly improve the I/O performance compared to existing solutions. © 2017 IEEE.

关键词： Managers

来源：评论

学校读者我要写书评

暂无评论

Recommendation-based Smart Indoor Navigation: Poster Abstract 17

Recommendation-based Smart Indoor Navigation: Poster Abstrac...

引用

Proceedings of the Second International Conference on Internet-of-Things Design and Implementation

作者： Wenlu Wang Wei-Shinn Ku Dept. of Computer Science and Software Engineering Auburn University Auburn AL

ISBN: (纸本)9781450349666

Localization in indoor spaces has to rely on sensing devices (e.g., Radio Frequency Identification (RFID) readers, WiFi routers, bluetooth beacons) rather than GPS devices. On the other side, we could build a smart indoor environment that facilitates all types of spatial services with various sensing devices. In this paper, we focus on the topic of spatial *** to the complexity of indoor environments, we believe the indoor navigation strategy should not be limited to the shortest path. Taking shopping centers for example, a navigation path should be not only the shortest path, but also an attractive route to the shopper. We aim to build a smart indoor navigation system, which not only learns the user's behavior through previous sensing data, but also enjoys working with heterogeneous devices. Therefore, we propose a novel recommendation based smart navigation strategy with Recurrent Neural Network (RNN). This strategy provides optimal user experience by: 1) Memorizing the user's historical data; 2) Overlapping the navigation with the user's indoor behavior model; 3) Making recommendations based on real-time detections from sensor devices.

关键词： recurrent neural network internet of things indoor navigation

来源：评论

学校读者我要写书评

暂无评论

Poster Abstract: Recommendation-Based Smart Indoor Navigation

Poster Abstract: Recommendation-Based Smart Indoor Navigatio...

引用

IEEE International Conference on Internet-of-Things Design and Implementation (IoTDI)

作者： Wenlu Wang Wei-Shinn Ku Dept. of Computer Science and Software Engineering Auburn University Auburn AL

ISBN: (纸本)9781467391467

Localization in indoor spaces has to rely on sensing devices (e.g., Radio Frequency Identification (RFID) readers, WiFi routers, bluetooth beacons) rather than GPS *** the other side, we could build a smart indoor environment that facilitates alltypes of spatial services with various sensing devices. In this paper, we focus on the topic of spatial *** to the complexity of indoor environments, we believe the indoor navigation strategy should not be limited to the shortest path. Taking shopping centers for example, a navigation path should be not only the shortest path,but also an attractive route to the *** aim to build a smart indoor navigation system, which not only learns the user's behavior through previous sensing data,but also enjoys working with heterogeneous ***, we propose a novel recommendation based smart navigation strategy with Recurrent Neural Network (RNN).This strategy provides optimal user experience by:1) Memorizing the user's historical data;2) Overlapping the navigation with the user's indoor behavior model;3) Making recommendations based on real-time detections from sensor devices.

关键词： Recurrent neural networks Indoor navigation Radiofrequency identification Hidden Markov models IEEE merchandise

来源：评论

学校读者我要写书评

暂无评论

2022 Roadmap on Neuromorphic Computing and engineering

arXiv

引用

arXiv 2021年

作者： Christensen, Dennis Valbjørn Dittmann, Regina Linares-Barranco, Bernabé Sebastian, Abu Le Gallo, Manuel Redaelli, Andrea Slesazeck, Stefan Mikolajick, Thomas Spiga, Sabina Menzel, Stephan Valov, Ilia Milano, Gianluca Ricciardi, Carlo Liang, Shi-Jun Miao, Feng Lanza, Mario Quill, Tyler J. Keene, Scott T. Salleo, Alberto Grollier, Julie Marković, Danijela Mizrahi, Alice Yao, Peng Yang, J. Joshua Indiveri, Giacomo Strachan, John Paul Datta, Suman Vianello, Elisa Valentian, Alexandre Feldmann, Johannes Li, Xuan Pernice, Wolfram H.P. Bhaskaran, Harish Furber, Steve Neftci, Emre Scherr, Franz Maass, Wolfgang Ramaswamy, Srikanth Tapson, Jonathan Panda, Priyadarshini Kim, Youngeun Tanaka, Gouhei Thorpe, Simon Bartolozzi, Chiara Cleland, Thomas A. Posch, Christoph Liu, Shih-Chii Panuccio, Gabriella Mahmud, Mufti Mazumder, Arnab Neelim Hosseini, Morteza Mohsenin, Tinoosh Donati, Elisa Tolu, Silvia Galeazzi, Roberto Christensen, Martin Ejsing Holm, Sune Ielmini, Daniele Pryds, N. Department of Energy Conversion and Storage Technical University of Denmark Kgs. LyngbyDK-2800 Denmark Peter Gruenberg Institute 7 Forschungszentrum Juelich GmbH Juelich52425 Germany JARA-FIT RWTH Aachen University Aachen52056 Germany CSIC Universidad de Sevilla Seville41092 Spain IBM Research Zurich Switzerland STMicroelectronics Agrate Italy Dresden01187 Germany Institute of Semiconductors and Microsystems TU Dresden Dresden Germany CNR-IMM Unit of Agrate Brianza via C. Olivetti 2 MB Agrate Brianza Italy Juelich Germany Torino Italy Department of Applied Science and Technology Politecnico di Torino Torino Italy National Laboratory of Solid State Microstructures School of Physics Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing China Thuwal23955-6900 Saudi Arabia Department of Materials Science and Engineering Stanford University StanfordCA94305 United States Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Unité Mixte de Physique CNRS Thales Université Paris-Saclay Palaiseau91767 France Electrical and Computer Engineering Department University of Southern California Los AngelesCA United States Institute of Neuroinformatics University of Zurich ETH Zurich Switzerland Hewlett Packard Laboratories Hewlett Packard Enterprise San JoseCA United States Department of Electrical Engineering University of Notre Dame Notre DameIN United States CEA LETI Université Grenoble Alpes Grenoble France CEA LIST Université Grenoble Alpes Grenoble France Department of Materials University of Oxford Parks Road OxfordOX1 3PH United Kingdom Institute of Physics University of Münster Heisenbergstr. 11 Heisenbergstr Münster48149 Germany Center for Soft Nanoscience University of Münster Münster48149 Germany The University of Manchester United Kingdom Department of Cognitive Sciences University of California Irvine IrvineCA United States Institute of Theoretica

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In the Von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The Roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this Roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community. © 2021,

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Arnor: Modeling Social Intelligence via Norms to Engineer Privacy-Aware Personal Agents 17

Arnor: Modeling Social Intelligence via Norms to Engineer Pr...

引用

International Conference on Autonomous Agents and Multiagent Systems

作者： Nirav Ajmeri Pradeep K. Murukannaiah Hui Guo Munindar P. Singh Dept. of Computer Science North Carolina State University Dept. of Software Engineering Rochester Institute of Technology

ISBN: (纸本)9781510855076

We seek to address the challenge of engineering socially intelligent personal agents that are privacy-aware. We propose Arnor, a method, including a metamodel based on social constructs Arnor incorporates social norms and goes beyond existing agent-oriented software engineering (AOSE) methods by systematically capturing how a personal agent's actions influence the social experience it delivers We conduct two empirical studies to evaluate Arnor. First, via a multi-phase developer study, we show that Arnor simplifies application development. Second, via simulation experiments, we show that Arnor provides improved privacy-preserving social experience to end users than personal agents engineered using a traditional AOSE method.

关键词： Social context Norms Personal agents Methodology Developer study Social Environment social model Agents empirical studies Engineers Intelligence methodology

来源：评论

学校读者我要写书评

暂无评论

Parallelizing Soft-Synths with Soft Real-Time Requirements

Parallelizing Soft-Synths with Soft Real-Time Requirements

引用

Euromicro Conference on Parallel, Distributed and Network-Based Processing

作者： Ede Cameron Dhrubajyoti Goswami Dept. of Computer Science and Software Engineering Concordia University Montreal Quebec Canada

ISBN: (纸本)9781509060597

Though parallel processing of applications related to video processing and rendering are widespread, parallel processing of audio synthesis software (also known as soft-synths) is not much researched. This paper addresses our research and experiments in parallelizing digital audio synthesizers on a commodity multicore platform where these synthesizers are most commonly used. Soft real-time requirements and overheads of parallelization are two of the competing forces in this research. As a case study, the ALSA (Advanced Linux Sound Architecture) Modular audio Synthesizer (AMS) is evaluated. AMS employs a modular approach to digital music synthesis, is often part of a standard Linux installation package, has a GUI for user interactions, and like other audio synthesizers it has a soft real-time requirement. The main intentions of parallelization are for enhancing throughput and hence stability, whereby more complex and higher quality audio can be generated. The GUI based interactive approach adds an extra challenge of a dynamic call graph that can change on-the-fly. The paper compares the pros and cons of the different techniques adopt-ed, and highlights the advantages of parallelization. The lessons learnt can also be used in parallelizing other existing audio synthesizers and designing new parallel synthesizers from scratch.

关键词： Synthesizers Linux Synchronization Standards software Real-time systems Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

A decision support method for recommending degrees of exploration in exploratory testing

arXiv

引用

arXiv 2017年

作者： Ghazi, Ahmad Nauman Petersen, Kai Wohlin, Claes Bjarnason, Elizabeth Dept. of Software Engineering Blekinge Institute of Technology Karlskrona Sweden Dept. of Computer Science Lund University Lund Sweden

Exploratory testing is neither black nor white, but rather a continuum of exploration exists. In this research we propose an approach for decision support helping practitioners to distribute time between different degrees of exploratory testing on that continuum. To make the continuum manageable, five levels have been defined: Freestyle testing, high, medium and low degrees of exploration, and scripted testing. The decision support approach is based on the repertory grid technique. The approach has been used in one company. The method for data collection was focus groups. The results showed that the proposed approach aids practitioners in the reflection of what exploratory testing levels to use, and aligns their understanding for priorities of decision criteria and the performance of exploratory testing levels in their contexts. The findings also showed that the participating company, which is currently conducting mostly scripted testing, should spend more time on testing using higher degrees of exploration in comparison to scripted testing. Copyright © 2017, The Authors. All rights reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Improved Sentiment Classification by Multi-Modal Fusion

Improved Sentiment Classification by Multi-Modal Fusion

引用

IEEE International Conference on Big Data Computing Service and Applications (BigDataService)

作者： Lige Gan Rachid Benlamri Richard Khoury Department of Software Engineering Lakehead University Thunder Bay Canada Dept. of Computer Science and Software Engineering Université Laval Quebec City Canada

ISBN: (纸本)9781509063192

Sentiment Analysis (SA) is the task of detecting people's emotions from their written text. Many algorithms have been studied for that purpose, with different authors claiming one or the other as better by a given metric. In recent years, the focus of SA has shifted to online text and microblog text, messages so short that good analysis becomes difficult that the choice of algorithm becomes critical. In this paper, we propose that a choice is not necessary at all. Instead, we show that a fusion of multiple algorithms to create a multi-modal SA system is a preferable approach.

关键词： Classification algorithms Algorithm design and analysis Measurement Niobium Support vector machines Kernel Vegetation

来源：评论

学校读者我要写书评

暂无评论

Detection of muscle fatigue using wearable (MYO) surface electromyography based control device 8

Detection of muscle fatigue using wearable (MYO) surface ele...

引用

8th International Conference on Information Technology, ICIT 2017

作者： Nourhan, T.M. Piechnick, M. Falkenberg, J. Nazmy, T. Faculty of Engineering Dept. of Computer Systems Ain Shams Uni Cairo Egypt Fakultät Informatik Institut für Software Dreseden Germany Faculty of Sciences and Arts Qasim Uni. Uniza Saudi Arabia

ISBN: (纸本)9781509063321

Wearable technology had set to play a major role in solving various problems in medical or sports applications in sports training, ergonomics, and mostly physical therapy. Surface electromyography (sEMG) has been used for localised muscle fatigue research area, although the success of sEMG based techniques is currently limited to isometric contraction and is not acceptable to the human movement community. This work propose the use of sEMG based sensor to measure the muscle activity during dynamic contractions. In this study, the use of a low cost commercial available sensor called MYO armband was implemented to reveal the viability to utilise this type of sensor to quantify muscle fatigue. The acquired sEMG signals from the muscle were analysed with the use of a set of selected features, RMS and MDF have been used as indicators of fatigue, and then classifying the signal into two classes non-fatigue and fatigue using backpropagation neural networks, allowing the prediction of muscle fatigue. Results show that automating the process of localised muscle fatigue detection is showed with higher accuracy compared with other methods. © 2017 IEEE.

关键词： Neural networks

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：