检索结果-内蒙古大学图书馆

Eurocon

作者： Sergio Bernabé Gabriel Martín José M. P. Nascimento José M. Bioucas-Dias Antonio Plaza Guillermo Botella Manuel Prieto-Matías Department of Computer Architecture and Automation Complutense University Madrid Spain Instituto de Telecomunicações Universidade de Lisboa Lisbon Portugal Department of Technology of Computers and Communications University of Extremadura Cáceres Spain

In this paper, we develop a fast implementation of an hyperspectral coded aperture (HYCA) algorithm on different platforms using OpenCL, an open standard for parallel programming on heterogeneous systems, which includes a wide variety of devices, from dense multicore systems from major manufactures such as Intel or ARM to new accelerators such as graphics processing units (GPUs), field programmable gate arrays (FPGAs), the Intel Xeon Phi and other custom devices. Our proposed implementation of HYCA significantly reduces its computational cost. Our experiments have been conducted using simulated data and reveal considerable acceleration factors. This kind of implementations with the same descriptive language on different architectures are very important in order to really calibrate the possibility of using heterogeneous platforms for efficient hyperspectral imaging processing in real remote sensing missions.

关键词： Hyperspectral imaging Kernel Optimization Graphics processing units Apertures Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Modeling and dynamic management of 3D multicore systems with liquid cooling

Modeling and dynamic management of 3D multicore systems with...

引用

IFIP International Conference on Very Large Scale Integration (VLSI-SoC)

作者： Ayse K. Coskun José L. Ayala David Atienza Tajana Simunic Rosing Computer Science and Engineering Department (CSE) University of California San Diego USA Computer Architecture and Automation Department (DACYA) Complutense University of Madrid Spain Embedded Systems Laboratory (ESL) Ecole Polytechnique Fédérale de Lausanne (EPFL) Switzerland

Three-dimensional (3D) circuits reduce communication delay in multicore SoCs, and enable efficient integration of cores, memories, sensors, and RF devices. However, vertical integration of layers exacerbates the reliability and thermal problems, and cooling efficiency becomes a limiting factor. Liquid cooling is a solution to overcome the accelerated thermal problems imposed by multi-layer architectures. In this paper, we first provide a 3D thermal simulation model including liquid cooling, supporting both fixed and variable fluid injection rates. Our model has been integrated in HotSpot to study the impact on multicore SoCs. We design and evaluate several dynamic management policies that complement liquid cooling. Our results for 3D multicore SoCs, which are based on 3D versions of UltraSPARC T1, show that thermal management approaches that combine liquid cooling with proactive task allocation are extremely effective in preventing temperature problems. Our proactive management technique provides an additional 75% average reduction in hot spots in comparison to applying only liquid cooling. Furthermore, for systems capable of varying the coolant flow rate at runtime, our feedback controller increases the improvement to 95% on average.

关键词： Three dimensional displays Liquid cooling Thermal management Microchannel Through-silicon vias Thermal resistance

来源：评论

学校读者我要写书评

暂无评论

A Novel Real-Time DEVS Simulation architecture with Hardware-In-The-Loop Capabilities

A Novel Real-Time DEVS Simulation Architecture with Hardware...

引用

Annual Modeling and Simulation Conference (ANNSIM)

作者： Óscar Fernández-Sebastián Román Cárdenas Patricia Arroba José L. Risco-Martín Department of Computer Architecture and Automation Universidad Complutense de Madrid Spain Department of Electronic Engineering Universidad Politécnica de Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Spain

ISBN: (数字)9781713899310

ISBN: (纸本)9798350350562

Advanced Modelling and Simulation (M&S) techniques, including Digital Twins (DTs) and Hardware-In-the-Loop (HIL) simulation, are essential for the design and operation of today’s complex systems. Despite these advances, there remains a gap between the simulation methods used in design and those used in implementation. This paper introduces a Real-Time (RT) simulation framework that connects models using the Discrete-Event System Specification (DEVS) with external systems, improving implementation and operation. The Python xDEVS tool has been enhanced to introduce a new suite of real-time simulation components and a DEVS-based communication interface, facilitating adaptable communication protocols. The framework demonstrates its capability to integrate both DEVS and non-DEVS systems and establish effective communication through various experiments, ranging from RT simulation of DEVS models to complex multi-component systems. This tool has significant potential in supporting real and incremental system implementations through HIL techniques, making a valuable contribution to complex system design and operation.

关键词： Adaptation models Protocols Accuracy Hardware-in-the-loop simulation Real-time systems Digital twins Synchronization Complex systems Engines System implementation

来源：评论

学校读者我要写书评

暂无评论

Development of an interface for digital neuromorphic hardware based on an FPGA

arXiv

引用

arXiv 2023年

作者： Harmann, René Sohlbach, Lukas Perez-Peña, Fernando Schmidt, Karsten Department of Computer Science and Engineering Frankfurt University of Applied Sciences Nibelungenplatz 1 Frankfurt60318 Germany Department of Automation Electronics and Computer Architecture and Networks School of Engineering University of Cadiz Avda. de la Universidad 10 Puerto Real11519 Spain

Exploring and understanding the functioning of the human brain is one of the greatest challenges for current research. Neuromorphic engineering tries to address this challenge by abstracting biological mechanisms and translating them into technology. Via the abstraction process and experiments with the resulting technical system, an attempt is made to obtain information about the biological counterpart. One subsection of Neuromorphic Engineering (NE) are Spiking Neural Networks (SNN), which describe the structures of the human brain more and more closely than Artificial Neural Networks (ANN). Together with their dedicated hardware, SNNs provide a good platform for developing new algorithms for information processing. In the context of these neuromorphic hardware platforms, this paper aims to develop an interface for a digital hardware platform (SPINN-3 Development Board) to enable the use of industrial or conventional sensors and thus create new approaches for experimental research. The basis for this endeavor is a Field Programmable Gate Array (FPGA), which is placed as a gateway between the sensors and the neuromorphic hardware. Overall, the developed system provides a robust solution for a wide variety of investigations related to neuromorphic hardware and SNNs. Furthermore, the solution also offers suitable possibilities to monitor all processes within the system in order to obtain suitable measurements, which can be examined in search of meaningful results. © 2023, CC BY-NC-ND.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Mathematical Control Model of Secondary Coextrusion Composition Preparation

Mathematical Control Model of Secondary Coextrusion Composit...

引用

2019 International Science and Technology Conference on Earth Science, ISTCEarthScience 2019

作者： Dyadichev, V.V. Kolesnikov, A.V. Dyadichev, A.V. V.I. Vernadsky Crimean Federal University Acad. of Constr. and Architecture Engineering Center Bio-positive Construction and Resource-saving 3 Pavlenko Str. Simferopol Crimea295000 Russia Lugansk National University Named after Vladimir Dal Department of Automation and Computer-Integrated Technologies 20-A Molodezhnyi Sq. Lugansk91034 Ukraine

The control of polymer waste recycling process is an important modern problem. A partial solution to the problem can be got by using coextrusion technology. As a result of its application with respect to polymer waste, we can get a multilayer qualitative product, containing waste and safe for usage. Because of economic causes, the problem of using this technology is the correct preparation of secondary coextrusion composition based on the requirements to the quality of the obtained product. The scientific paper presents the mathematical control model of secondary polymer composition preparation. The developed model allows carrying out an operational control of composition components consumption, determining and correcting the consumption of the most expensive astringent component in order to guarantee the required quality of the product. The mathematical model is the basis for construction of intellectual automated systems for controlling polymer waste recycling process by coextrusion technology. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Towards the Munich Quantum Software Stack: Enabling Efficient Access and Tool Support for Quantum computers

Towards the Munich Quantum Software Stack: Enabling Efficien...

引用

Quantum Computing and Engineering (QCE), IEEE International Conference on

作者： Martin Schulz Laura Schulz Martin Ruefenacht Robert Wille Chair of Computer Architecture and Parallel Systems Technical University of Munich Munich Germany QCT Department Leibniz Supercomputing Centre Garching Germany Chair of Design Automation Technical University of Munich Munich Germany

As quantum computing systems mature and move from laboratories to production computing environments, corresponding software stacks are becoming key for their successful utilization. In particular, the expected use of quantum systems as HPC accelerators requires a deep integration with the existing and widely deployed HPC software stacks. Additionally, new requirements such as dynamic compilation and new challenges for tools and programming models must be considered. We tackle these challenges by developing the Munich Quantum Software Stack—a comprehensive initiative by the Munich Quantum Valley to offer a flexible, efficient, and user-oriented software environment. In this poster, we describe the core components and workflows, and how they will enable this transformation from quantum experiments to quantum accelerators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GROUP-WISE SPARSE REPRESENTATION OF RESTING-STATE FMRI DATA FOR BETTER UNDERSTANDING OF SCHIZOPHRENIA

GROUP-WISE SPARSE REPRESENTATION OF RESTING-STATE FMRI DATA ...

引用

International Symposium on Biomedical Imaging

作者： Lin Yuan Tianming Liu Dewen Hu College of Mechanotrics and Automation National University of Defense Technology Changsha Hunan 410073 China Cortical Architecture Imaging and Discovery Lab Department of Computer Science The University of Georgia Athens United States of America

ISBN: (纸本)9781509011735

Resting-state functional magnetic resonance imaging (rs-fMRI) has become a powerful technique for analyzing cognitive function and its disruption in mental diseases, including schizophrenia. It has played an important role in analyzing and diagnosing mental diseases. In this paper, we present a novel machine learning approach called group-wise sparse representation of rs-fMRI signals to find differences between schizophrenia patients and healthy controls. Firstly, we extract the fMRI signals from all subjects that are registered into the MNI atlas space in the pre-processing step to build a large input signal matrix. Secondly, we use online dictionary learning and sparse coding methods to derive the coefficient matrix. Thirdly, we use two-sample t-test to analyze the regions of increased and decreased activity in schizophrenia patients compared to healthy controls. Finally, by using the AAL atlas the distributions of the detected regions are obtained. We test our approach on the COBRE dataset and the experimental results show that the schizophrenia patients have increased activities mainly at the fronto-parietal network. All other networks excluding the fronto-parietal network show decreased phenomenon. These results provide novel insights into better understanding of schizophrenia.

关键词： resting-state fMRI group-wise sparse representation schizophrenia research

来源：评论

学校读者我要写书评

暂无评论

Towards Spiking Control for Dielectric Elastomer Actuators

Towards Spiking Control for Dielectric Elastomer Actuators

引用

International Conference on Control, Mechatronics and automation (ICCMA)

作者： Lukas Sohlbach René Harmann Fernando M. Quintana Heng Wei Zhang Fernando Perez-Peña Karsten Schmidt Department of Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt/Main Germany Department of Informatics and Technology Engineering School of Engineering University of Cá diz Cádiz Spain Department of Automation Electronics and Computer Architecture and Networks School of Engineering University of Cádiz Cádiz Spain

Dielectric Elastomer Actuators (DEAs) can be seen as flexible capacitors, where an incompressible elastomer is sandwiched between two compliant electrodes. From the elastomer non-linear and time-dependent phenomena arise during the activation of the actuator. This results in the need for appropriate control methods, especially when they are used in the field of soft robots. Therefore, this paper presents a feedforward controller which is based on Spiking Neural Networks (SNNs). To the best of our knowledge this is the first time DEAs and SNNs are combined to make a step towards true soft robots. It was demonstrated that it is necessary to include feedback into the control scheme. Also, it was found that in the context of a SpiNN-3 development board as a neuromorphic hardware platform, neuron encoding is the most promising encoding method. This also implies that a classification approach is preferable to a regression approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

POSTER: Performance evaluation of a signal extraction algorithm for the Cherenkov Telescope Array's Real Time Analysis pipeline 16

POSTER: Performance evaluation of a signal extraction algori...

引用

16th IEEE International Conference on Cluster Computing, CLUSTER 2014

作者： Rodriguez-Vazquez, Juan Jose Vazquez-Poletti, Jose Luis Delgado, Carlos Bulgarelli, Andrea Cardenas-Montes, Miguel Department of Fundamental Research CIEMAT Avda. Complutense 40 Madrid28040 Spain Dept. of Computer Architecture and Automation Complutense University of Madrid C/ Profesor José García Santesmases s/n Madrid28040 Spain Istituto di Astrofisica Spaziale e Fisica Cosmica - Bologna Istituto Nazionale di Astrofisica Via Piero Gobetti 101 Bologna40129 Italy

ISBN: (纸本)9781479955480

In this paper, several versions of a signal extraction algorithm, pertaining to the entry stage of the Cherenkov Telescope Array's Real Time Analysis pipeline, were implemented and optimised using SSE2, POSIX threads and CUDA. Results of this proof of concept let us gain an insight into the suitability of each platform, and the performance each one can deliver, to carry out this particular task. © 2014 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Reliable client-server communication in distributed programs

Reliable client-server communication in distributed programs

引用

Conference on Local computer Networks (LCN)

作者： K. Ravindran S.T. Chanson K.K. Ramakrishnan Department Of Computer Science & Automation Indian Institute of Science Bangalore India Department of Computing & Information Sciences Kansas State University Manhattan KS USA Department of Computer Science University of British Columbia Vancouver BC Canada Distributed Systems Architecture & Performance Digital Equipment Corporation Littleton MA USA

The authors' premise is that applications have the ability to tolerate certain types of failures under certain situations. This may, in turn, relax the top-level constraint on failure recovery algorithms in the interprocess communication (IPC) layer and allow exploitation of the inherent tolerance of applications to failures in a systematic way to simplify failure recovery. Using this application-driven approach, the authors present a model of a distributed program based on the well-known client-server relationship among the processes of the program. The model reflects certain generic properties of the application layer that can be exploited by the IPC layer during failure recovery. New techniques as to how the properties can be used for recovery are outlined. The authors use remote procedure call and shared variable as communication abstractions for the client and the server processes in the program to communicate with one another. The simplicity and generality of the failure recovery renders the application-driven approach particularly useful in contemporary distributed systems which are large and heterogeneous and hence have complex failure modes.< >

关键词： Local area networks automation computer networks Distributed computing Microcomputers LAN interconnection Application software Network interfaces File systems Veins

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：