检索结果-内蒙古大学图书馆

ARCS Workshop 2018;31th International Conference on architecture of Computing Systems

作者： Christian Widerspick Wolfgang Bauer Dietmar Fey Department of Computer Science Chair of Computer Architecture Friedrich-Alexander-University Erlangen-Nuremberg

The use of GPUs in the automotive sector is a possibility to provide a lot of computing power for complex algorithms required for autonomous driving. In order to be able to make statements about the real-time capability of algorithms, it is necessary to be able to make precise statements about the runtime behavior. This work deals with the execution time of instructions on the NVIDIA Drive PX2 evaluation platform designed for an automotive environment. It is to be shown what influence block and warp variables have on execution times and whether these values can be used to estimate the total runtime of algorithms. This provides a deeper insight into the functionality of the modern Pascal architecture.

关键词： execution time PANX2 gene real-time capability algorithms driving platform Statement computational power Automobile driving instruction simulating DRIVES Platform Runtime

来源：评论

学校读者我要写书评

暂无评论

H2-MARL: Multi-agent reinforcement learning for Pareto optimality in hospital capacity strain and human mobility during epidemic

引用

Expert Systems with Applications 2025年 291卷

作者： Xueting Luo Hao Deng Jihong Yang Yao Shen Huanhuan Guo Zhiyuan Sun Mingqing Liu Jiming Wei Shengjie Zhao School of Computer Science and Technology Tongji University Shanghai 201804 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai 201804 China China Land Surveying and Planning Institute Beijing 100035 China College of Architecture and Urban Planning Tongji University Shanghai 200092 China Chongqing Institute of Planning and Natural Resources Investigation and Monitoring Chongqing 401121 China College of Electronic and Information Engineering Tongji University Shanghai 201804 China Guangdong Urban-rural Planning and Design Research Institute Technology Group Co. Ltd. Guangzhou 510290 China

Effectively balancing the losses from mobility restrictions and hospital capacity strain has drawn significant attention in the aftermath of COVID-19. Reinforcement learning (RL)-based strategies for human mobility management have recently advanced in addressing the dynamic evolution of cities and epidemics; however, they still face challenges in achieving coordinated control at the township level and adapting to cities of varying scales. To address the above issues, we propose a multi-agent RL approach that achieves Pareto optimality in managing hospital capacity and human mobility (H2-MARL), applicable across cities of different population scales. We first develop a township-level infection model with online-updatable parameters to simulate disease transmission and construct a city-wide dynamic spatiotemporal epidemic simulator. On this basis, H2-MARL is designed to treat each division as an agent, with a trade-off dual-objective reward function formulated and an experience replay buffer enriched with expert knowledge built. To evaluate the effectiveness of the model, we construct a township-level human mobility dataset containing over one billion records from four representative cities of varying scales. Extensive experiments demonstrate that H2-MARL has the optimal dual-objective trade-off capability, which can simultaneously minimize hospital capacity strain and human mobility restriction loss. Meanwhile, the applicability of the proposed model to epidemic control in cities of varying scales is verified, which showcases its feasibility and versatility in practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pipelining Loop Optimization Method for Dataflow architecture

引用

Journal of computer science & Technology 2018年第1期33卷 116-130页

作者： Xu Tan Xiao-Chun Ye Xiao-Wei Shen Yuan-Chao Xu Da Wang Lunkai Zhang Wen-Ming Li Dong-Rui Fan Zhi-Min Tang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 1000J9 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214125 China College of Information Engineering Capital Normal University Beijing 100048 China Department of Computer Science The University of Chicago Chicago IL 60637 U.S.A.

With the coming of exascale supercomputing era, power efficiency has become the most important obstacle to build an exascale system. Dataflow architecture has native advantage in achieving high power efficiency for scientific applications. However, the state-of-the-art dataflow architectures fail to exploit high parallelism for loop processing. To address this issue, we propose a pipelining loop optimization method （PLO）, which makes iterations in loops flow in the processing element （PE） array of dataflow accelerator. This method consists of two techniques, architecture-assisted hardware iteration and instruction-assisted software iteration. In hardware iteration execution model, an on-chip loop controller is designed to generate loop indexes, reducing the complexity of computing kernel and laying a good f（mndation for pipelining execution. In software iteration execution model, additional loop instructions are presented to solve the iteration dependency problem. Via these two techniques, the average number of instructions ready to execute per cycle is increased to keep floating-point unit busy. Simulation results show that our proposed method outperforms static and dynamic loop execution model in floating-point efficiency by 2.45x and 1.1x on average, respectively, while the hardware cost of these two techniques is acceptable.

关键词： dataflow model control-flow model loop optimization exascale computing scientific application

来源：评论

学校读者我要写书评

暂无评论

Discrete-Time Modeling of NFV Accelerators that Exploit Batched Processing

Discrete-Time Modeling of NFV Accelerators that Exploit Batc...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Stanislav Lange Leonardo Linguaglossa Stefan Geissler Dario Rossi Thomas Zinner University of Würzburg Institute of Computer Science Chair of Communication Networks Wüurzburg Germany Telecom ParisTech Paris France TU Berlin Berlin Germany

Network Functions Virtualization (NFV) is among the latest network revolutions, bringing flexibility and avoiding network ossification. At the same time, all-software NFV implementations on commodity hardware raise performance issues with respect to ASIC solutions. To address these issues, numerous software acceleration frameworks for packet processing have appeared in the last few years. Common among these frameworks is the use of batching techniques. In this context, packets are processed in groups as opposed to individually, which is required at high-speed to minimize the framework overhead, reduce interrupt pressure, and leverage instruction-level cache hits. Whereas several system implementations have been proposed and experimentally benchmarked, the scientific community has so far only to a limited extent attempted to model the system dynamics of modern NFV routers exploiting batching acceleration. In this paper, we fill this gap by proposing a simple generic model for such batching-based mechanisms, which allows a very detailed prediction of highly relevant performance indicators. These include the distribution of the processed batch size as well as queue size, which can be used to identify loss-less operational regimes or quantify the packet loss probability in high-load scenarios. We contrast the model prediction with experimental results gathered in a high-speed testbed including an NFV router, showing that the model not only correctly captures system performance under simple conditions, but also in more realistic scenarios in which traffic is processed by a mixture of functions.

关键词： Software Computational modeling Predictive models Packet loss System performance Hardware

来源：评论

学校读者我要写书评

暂无评论

Big mobility data reveals hyperlocal air pollution exposure disparities in the Bronx, New York

Nature Cities

引用

Nature Cities 2024年第8期1卷 512-521页

作者： Iacopo Testi An Wang Sanjana Paul Simone Mora Fábio Duarte Paolo Santi Carlo Ratti Erica Walker Marguerite Nyhan Senseable City Lab Department of Urban Studies and Planning Massachusetts Institute of Technology Cambridge MA USA Department of Civil and Environmental Engineering The Hong Kong Polytechnic University Hong Kong SAR China Department of Computer Science Norwegian University of Science and Technology Trondheim Norway Istituto di Informatica e Telematica Consiglio Nazionale delle Ricerche Pisa Italy ABC Department Politecnico di Milano Milan Italy School of Public Health Brown University Providence RI USA School of Engineering and Architecture University College Cork Cork Ireland

Air pollution disproportionately affects socially disadvantaged populations. Our study bridges the existing gap in quantifying mobility-based exposure and its associated disparity issues. We combined the granular mobility of over 500,000 unique anonymized users daily and hyperlocal air pollution data in 100 × 100-m grid cells to quantify disparities in particulate matter exposure in a racially diverse and dense urban area of New York City. Our approach advances the study of exposure and its disparity from individualized exposure tracking to a population-representative scale. We observed apparently different spatial patterns between personal exposure and exposure disparities, noting that people from Hispanic-majority and low-income neighborhoods were those most severely and disproportionately exposed to fine particulate matter (PM2.5) pollution. We reveal that race and ethnicity are much stronger indicators of exposure disparity than income. Our study further demonstrates that within-group variation contributes a major portion to exposure disparities, suggesting more granular mitigation plans are needed to target high-exposure individuals from socially disadvantaged groups in addition to generic air quality improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FS-Net: Medical Image Denoising via Local Receptive Field Smoothing Network

FS-Net: Medical Image Denoising via Local Receptive Field Sm...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Wang Xiaowei Jiaxin Xiong Rui Wang Worku J. Sori Jingtian Wang Liu Shaohui Feng Jiang Command Automation College PLA Army Engineering University Nanjing China School of Computer Beijing Institute of Technology Beijing China School of Architecture Harbin Institute of Technology) Harbin China School of Computer Science and Technology Harbin institute of technology Harbin China Mary Star of the Sea High School CA USA School of Computer Science and Jinling Hospital Harbin China

Noise is one of the most challenging tasks in medical images which is happening during transmission and acquisition, and as a result, it complicates a subsequent medical image analysis task. This paper proposes a novel local receptive field smoothing network (FS-Net) for medical image denoising by introducing smoothing priors of receptive field of intermediate CNN layers. First, for a receptive field of a CNN, each of its values smoothing properties are retained by weighting their local neighborhoods (i.e., after smoothing, each new neurons are the weighted average of its neighborhoods). The weights are calculated using the similarity of their corresponding receptive field (i.e., the similarity between the receptive field used to calculate a receptive fields value and the receptive field used to calculate their corresponding neighborhoods) and this keeps the smoothing properties. Second, by applying this smoothing prior on receptive fields of intermediate CNN layers, an end to end FSNet which directly approximate the latent clean images from its noisy version is designed. The receptive fields smoothing helps to train deeper architecture and improves the reconstructed image quality. Experimental results on Breast Mammography images reveal that the proposed method outperforms other states of the art denoising methods.

关键词： Smoothing methods Image denoising Medical diagnostic imaging Noise reduction Noise measurement Computational modeling

来源：评论

学校读者我要写书评

暂无评论

swMD: Performance Optimizations for Molecular Dynamics Simulation on Sunway Taihulight

swMD: Performance Optimizations for Molecular Dynamics Simul...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Kun Li Shigang Li Bei Wang Yifeng Chen Yunquan Zhang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing Department of Computer Science ETH Zurich HCST Key Lab at School of EECS Peking University Beijing

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Molecular dynamics is an extensively utilized computational tool for solids, liquids and molecules simulation. Currently, much research on molecular dynamics simulation focuses on simplifying forces or parallelizing tasks to reduce the overheads of forces computation. However, the molecular dynamics simulation still remains challenging since the communication and neighbor list construction are time-consuming in the existing algorithm. In this paper, we propose a swMD optimization strategy including a new communication mode called ghost communication to reduce superfluous communication overheads and an innovative neighbor list algorithm to improve the construction efficiency of it. Moreover, we accelerate computation by utilizing many-core resources on Sunway Taihulight and present an auto-tuning Producer-Consumer pairing algorithm to make neighbor list construction happen in fast register communication. Compared to traditional methods, swMD optimization strategy obtains a maximal 82.2% and an average of 79.4% performance improvement. We also evaluate the scalability up to 266,240 cores and the results demonstrate the high efficiency of swMD optimization strategy on communication, computation and neighbor list construction respectively.

关键词： Heuristic algorithms computer architecture Computational modeling Microprocessors Program processors Registers Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Platinum Diselenide Waveguide-Integrated Infrared Photodetectors

arXiv

引用

arXiv 2021年

作者： Parhizkar, Shayan Prechtl, Maximilian Giesecke, Anna-Lena Suckow, Stephan Wahl, Sophia Lukas, Sebastian Hartwig, Oliver Negm, Nour Quellmalz, Arne Gylfason, Kristinn B. Schall, Daniel Wuttig, Matthias Duesberg, Georg S. Lemme, Max C. Chair of Electronic Devices RWTH Aachen University Otto-Blumenthal-Str. 2 Aachen52074 Germany AMO GmbH Advanced Microelectronic Center Aachen Otto-Blumenthal-Str. 25 Aachen52074 Germany Center for Integrated Sensor Systems University of the Bundeswehr Munich Neubiberg85577 Germany Institute of Physics IA RWTH Aachen University Aachen52074 Germany Division of Micro and Nanosystems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-10044 Sweden Black Semiconductor GmbH Schloss-Rahe-Str. 15 Aachen52072 Germany

Low cost, easily integrable photodetectors (PDs) for silicon (Si) photonics are still a bottleneck for photonic integrated circuits (PICs), especially for wavelengths above 1.8 µm. Multilayered platinum diselenide (PtSe2) is a semi-metallic two-dimensional (2D) material that can be synthesized below 450°C. We integrate PtSe2 based PDs directly by conformal growth on Si waveguides. The PDs operate at 1550 nm wavelength with a maximum responsivity of 11 mA/W and response times below 8.4 µs. Fourier transform infrared spectroscopy (FTIR) in the wavelength range from 1.25 µm to 28 µm indicates the suitability of PtSe2 for PDs far into the infrared wavelength range. Our PtSe2 PDs integrated by direct growth outperform PtSe2 PDs manufactured by standard 2D layer transfer. The combination of IR responsivity, chemical stability, selective and conformal growth at low temperatures, and the potential for high carrier mobility, make PtSe2 an attractive 2D material for optoelectronics and PICs. Copyright © 2021, The Authors. All rights reserved.

关键词： Selenium compounds

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving Artificial Intelligence Techniques in Biomedicine

arXiv

引用

arXiv 2020年

作者： Torkzadehmahani, Reihaneh Nasirigerdeh, Reza Blumenthal, David B. Kacprowski, Tim List, Markus Matschinske, Julian Späth, Julian Wenke, Nina Kerstin Bihari, Béla Frisch, Tobias Hartebrodt, Anne Hauschild, Anne-Christin Heider, Dominik Holzinger, Andreas Hötzendorfer, Walter Kastelitz, Markus Mayer, Rudolf Nogales, Cristian Pustozerova, Anastasia Röttger, Richard Schmidt, Harald H.H.W. Schwalber, Ameli Tschohl, Christof Wohner, Andrea Baumbach, Jan Chair of Experimental Bioinformatics Technical University of Munich Freising Germany Division of Data Science in Biomedicine Peter L. Reichertz Institute for Medical Informatics TU Braunschweig and Hannover Medical School Braunschweig Germany Gnome Design SRL Sfântu Gheorghe Romania Institute of Mathematics and Computer Science University of Southern Denmark Odense Denmark Department of Mathematics and Computer Science Philipps-University of Marburg Marburg Germany Institute for Medical Informatics/Statistics Medical University Graz Graz Austria Research Institute AG & Co KG Vienna Austria SBA Research Gemeinnützige GmbH Vienna Austria Department of Pharmacology and Personalised Medicine MeHNS FHML Maastricht University Maastricht Netherlands Concentris Research Management GmbH Fürstenfeldbruck Germany

Artificial intelligence (AI) has been successfully applied in numerous scientific domains. In biomedicine, AI has already shown tremendous potential, e.g. in the interpretation of next-generation sequencing data and in the design of clinical decision support systems. However, training an AI model on sensitive data raises concerns about the privacy of individual participants. For example, summary statistics of a genome-wide association study can be used to determine the presence or absence of an individual in a given dataset. This considerable privacy risk has led to restrictions in accessing genomic and other biomedical data, which is detrimental for collaborative research and impedes scientific progress. Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals’ privacy. This paper provides a structured overview of recent advances in privacy-preserving AI techniques in biomedicine. It places the most important state-of-the-art approaches within a unified taxonomy and discusses their strengths, limitations, and open problems. As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy preserving techniques. This would allow to merge the advantages to provide privacy guarantees in a distributed way for biomedical applications. Nonetheless, more research is necessary as hybrid approaches pose new challenges such as additional network or computation overhead. © 2020, CC BY.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Continual learning of new sound classes using generative replay

arXiv

引用

arXiv 2019年

作者： Wang, Zhepei Subakan, Cem Tzinis, Efthymios Smaragdis, Paris Charlin, Laurent University of Illinois at Urbana-Champaign Department of Computer Science Mila-Quebec Artificial Intelligence Institute HEC Montreál Canada CIFAR AI Chair Adobe Research

Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as "catastrophic forgetting." We develop a generative replay procedure for generating training audio spectrogram data, in place of keeping older training datasets. We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data. We thus conclude that we can extend a trained sound classifier to learn new classes without having to keep previously used datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Refining

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：