检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qiankun Tang Jie Li Zhiping Shi Yu Hu Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing Advanced Innovation Center for Imaging Theory and Technology Capital Normal University

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module. To effectively aggregate bottom and top-down features, we introduce an efficient Feature-Preserving and Refinement Module. A lightweight prediction head is employed to further reduce the entire network complexity. Experimental results show that our LightDet achieves 75.5% mAP on PASCAL VOC 2007 at the speed of 250 FPS and 24.0% mAP on MS COCO dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-level spectral deferred corrections scheme for the shallow water equations on the rotating sphere

arXiv

引用

arXiv 2018年

作者： Hamona, François P. Schreiberb, Martin Miniond, Michael L. Center for Computational Sciences and Engineering Lawrence Berkeley National Laboratory Berkeley United States Department of Mathematics/Computer Science University of Exeter Exeter United Kingdom Computer Architecture and Parallel Systems Technical University of Munich Germany Department of Applied Mathematics Lawrence Berkeley National Laboratory Berkeley United States

Effcient time integration schemes are necessary to capture the complex processes involved in atmospheric ows over long periods of time. In this work, we propose a high-order, implicit-explicit numerical scheme that combines Multi-Level Spectral Deferred Corrections (MLSDC) and the Spherical Harmonics (SH) transform to solve the wave-propagation problems arising from the shallow-water equations on the rotating *** iterative temporal integration is based on a sequence of corrections distributed on coupled spacetime levels to perform a significant portion of the calculations on a coarse representation of the problem and hence to reduce the time-to-solution while preserving accuracy. In our scheme, referred to as MLSDCSH, the spatial discretization plays a key role in the efficiency of MLSDC, since the SH basis allows for consistent transfer functions between space-time levels that preserve important physical properties of the *** study the performance of the MLSDC-SH scheme with shallow-water test cases commonly used in numerical atmospheric modeling. We use this suite of test cases, which gradually adds more complexity to the nonlinear system of governing partial differential equations, to perform a detailed analysis of the accuracy of MLSDC-SH upon renement in time. We illustrate the stability properties of MLSDC-SH and show that the proposed scheme achieves up to eighth-order convergence in time. Finally, we study the conditions in which MLSDC-SH achieves its theoretical speedup, and we show that it can significantlyreduce the computational cost compared to single-level Spectral Deferred Corrections (SDC). Copyright © 2018, The Authors. All rights reserved.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

KFS-LIO: Key-Feature Selection for Lightweight Lidar Inertial Odometry

KFS-LIO: Key-Feature Selection for Lightweight Lidar Inertia...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wei Li Yu Hu Yinhe Han Xiaowei Li Research Center for Intelligent Computing Systems Institute of Computing Technology the Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology the Chinese Academy of Sciences Beijing China

Feature-based lidar odometry methods have attracted increasing attention due to their low computational cost. However, theoretically analysis of the effect of extracted features on pose estimation is still lacked. In this paper, we propose a method of key-feature selection for lightweight lidar inertial odometry, KFS-LIO, to further enhance the real-time performance by selecting the most effective subset of lidar feature constraints. Aiming at explaining the correlation between the feature distribution and state errors, a quantitative evaluation method of lidar constraints is introduced. In addition, to avoid recalculating the reprojection matrices in de-skewing step, we use the intermediate variables in IMU preintegration to compensate for lidar motion distortion. The experimental results demonstrate that KFS-LIO can reduce half of the LOAM features and provide comparable accuracy with the state-of-the-art odometry.

关键词： Laser radar Correlation Automation Conferences Pose estimation Feature extraction Distortion

来源：评论

学校读者我要写书评

暂无评论

A Parallel Ray Tracing architecture Suitable for Application-Specific Hardware and GPGPU Implementations

A Parallel Ray Tracing Architecture Suitable for Application...

引用

Euromicro Symposium on Digital System Design

作者： Alexandre S. Nery Nadia Nedjah Felipa M.G. Franca Lech Jozwiak LAM-Computer Architecture and Microelectronics Laboratory Systems Engineering and Computer Science Program COPPE Universidade Federal do Rio de Janeiro Brazil Department of Electrical Engineering-Electronic Systems Eindhoven University of Technology Netherlands Universidade do Estado do Rio de Janeiro Rio de Janeiro RJ BR

The Ray Tracing rendering algorithm can produce high-fidelity images of 3-D scenes, including shadow effects, as well as reflections and transparencies. This is currently done at a processing speed of at most 30 frames per second. Therefore, actual implementations of the algorithm are not yet suitable for interactive real-time rendering, which is required in games and virtual reality based applications. Fortunately, the algorithm allows for massive parallelization of its computations. In this paper, we present a parallel architecture for ray tracing based on a uniform spatial subdivision of the scene and exploiting an embedded computation of ray-triangle intersections. This approach allows for a significant acceleration of intersection computations, as well as, a reduction of the total number of the required intersections checks. Furthermore, it allows for these checks to be performed in parallel and in advance for each ray. In this paper we discuss and analyze an ASIP-based implementation using FPGAs and a GPGPU-based parallel implementation of the proposed architecture. The performance of both implementations are reported and compared.

关键词： Ray tracing Graphics processing unit Instruction sets computer architecture Registers Image color analysis Hardware

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 service-oriented priority-based resource scheduling scheme for virtualized utility computing 08

引用

Proceedings of the 15th international conference on High performance computing

作者： Ying Song Yaqiong Li Hui Wang Yufang Zhang Binquan Feng Hongyong Zang Yuzhong Sun Key Lab. of Computer System and Architecture Inst. of Computing Techn. Chinese Academy of Sciences China and National Research Center for Intelligent Computing Systems ICT China and Graduate Univ. of Chinese Academy of Sciences China Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences China and National Research Center for Intelligent Computing Systems ICT China

ISBN: (纸本)9783540898931

In order to provide high resource utilization and QoS assurance inutility computing hosting concurrently various services, this paper proposes aservice computing framework-RAINBOW for VM(Virtual Machine)-basedutility computing. In RAINBOW, we present a priority-based resourcescheduling scheme including resource flowing algorithms (RFaVM) to optimizeresource allocations amongst services. The principle of RFaVM is preferentiallyensuring performance of some critical services by degrading of others to someextent when resource competition arises. Based on our prototype, we evaluateRAINBOW and RFaVM. The experimental results show that RAINBOWwithout RFaVM provides 28%-324% improvements in service performance,and 26% higher the average CPU utilization than traditional service computingframework (TSF) in typical enterprise environment. RAINBOW with RFaVMfurther improves performance by 25%-42% for those critical services whileonly introducing up to 7% performance degradation to others, with 2%-8%more improvements in resource utilization than RAINBOW without RFaVM.

关键词： resource scheduling utility computing virtualization

来源：评论

学校读者我要写书评

暂无评论

The DEVStone Metric: Performance Analysis of DEVS Simulation Engines

arXiv

引用

arXiv 2023年

作者： Cárdenas, Román Henares, Kevin Arroba, Patricia Risco-Martín, José L. Wainer, Gabriel A. Integrated Systems Laboratory Universidad Politécnica de Madrid Madrid Spain Dept. of Systems and Computer Engineering Carleton University OttawaON Canada Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain

The DEVStone benchmark allows us to evaluate the performance of discrete-event simulators based on the DEVS formalism. It provides model sets with different characteristics, enabling the analysis of specific issues of simulation engines. However, this heterogeneity hinders the comparison of the results among studies, as the results obtained on each research work depend on the chosen subset of DEVStone models. We define the DEVStone metric based on the DEVStone synthetic benchmark and provide a mechanism for specifying objective ratings for DEVS-based simulators. This metric corresponds to the average number of times that a simulator can execute a selection of 12 DEVStone models in one minute. The variety of the chosen models ensures we measure different particularities provided by DEVStone. The proposed metric allows us to compare various simulators and to assess the impact of new features on their performance. We use the DEVStone metric to compare some popular DEVS-based simulators. © 2023, CC BY-SA.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

xDEVS no_std: A Rust Crate for Real-Time DEVS on Embedded systems

xDEVS no_std: A Rust Crate for Real-Time DEVS on Embedded Sy...

引用

Annual Modeling and Simulation Conference (ANNSIM)

作者： Román Cárdenas Pedro Malagón Patricia Arroba José L. Risco-Martín Integrated Systems Laboratory Universidad Politécnica de Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Spain Department of Computer Architecture and Automation Universidad Complutense de Madrid Spain

ISBN: (数字)9781713899310

ISBN: (纸本)9798350350562

Modeling and Simulation (M&S) plays a crucial role in the design and analysis of complex systems, with the Discrete EVent System specification (DEVS) formalism being a widely adopted mathematical framework. This paper introduces xDEVS no_std, the first version of xDEVS written in the Rust programming language’s no_std environment. Rust’s features, including a data ownership mechanism, enable the development of high-performance, memory-safe simulations. xDEVS no_std focuses on Real-Time (RT) simulation for safety-critical embedded applications, leveraging Rust’s abstractions to simplify code sharing and cross-compilation. The paper outlines the implementation design and Application Programming Interface (API), which facilitates the creation of both atomic and coupled DEVS models. The RT simulator integrates with hardware, handling external interrupts and enabling interactions with the embedded system. A use case on a RISC-V microcontroller demonstrates xDEVS no_std’s capabilities, illustrating how it can effectively orchestrate tasks of Cyber-Physical System (CPS) on embedded platforms.

关键词： Embedded systems Microcontrollers Programming Cyber-physical systems Real-time systems Mathematical models Hardware Discrete-event systems Complex systems Application programming interfaces

来源：评论

学校读者我要写书评

暂无评论

Application of fuzzy neural network in the system of concrete undamaged inspection

Application of fuzzy neural network in the system of concret...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Jing Xu Qingchun Meng Songsen Yang Wen Zhang Changhong Song Department of Civil Engineering Qingdao Institute of Architecture and Engineering Qingdao China Department of Computer Science Ocean University of China Qingdao China State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

ISBN: (纸本)0780382730

The accuracy of concrete strength inspection has a great influence on the safety evaluation of the building. In order to increase the accuracy, Fuzzy Neural Network (FNN) was built up to evaluate concrete stmngth: It takes full advantage of the characteristics of the common concrete testing methods: drill and rebound, and the abilities of FNN including automatic learning, generation and fuzzy logic inference. The experiment shows that the max relative error of the predicted results is 1.12%, which is satisfied with the requirements of the engineering. The method effieieatly maps the complex non-linear relationship between the drill values and the rebound values, and provides a efficient way for the concrete strength inspection and evaluation.

关键词： Fuzzy neural networks Intelligent networks Concrete Inspection Application software computer science Oceans Civil engineering Intelligent systems Intelligent structures

来源：评论

学校读者我要写书评

暂无评论

Internet-of-Things technology and applications for clean energy systems

Energy Conversion and Economics

引用

Energy Conversion and Economics 2021年第4期2卷 183-185页

作者： Strunz, Kai Wang, Xuanyuan Guo, Qinglai Xie, Le Zhang, Song Fang, Xin Wang, Jianxiao School of Electrical Engineering and Computer Science Berlin10587 Germany State Grid Jibei Electric Power Co. LTD. Beijing China Department of Electrical Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Texas A&M University College StationTX United States Department of Business Architecture and Technology ISO New England Inc. HolyokeMA United States Power Systems Engineering Center National Renewable Energy Laboratory GoldenCO United States School of Electrical and Electronic Engineering North China Electric Power University Beijing China

[...]future research interests regarding IESSs are summarised. A multi-stage PMU placement strategy was developed to alleviate power system vulnerability to possible false data injection attacks, where forward dynamic programming was used to distribute the capital cost of PMUs over a certain period. Three clustering methods, including linear regression, density-based spatial clustering of applications with noise (DBSCAN), and Gaussian mixture models (GMM), were combined for bad PMU data detection.

关键词：

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：