检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Karp, Martin Massaro, Daniele Jansson, Niclas Hart, Alistair Wahlgren, Jacob Schlatter, Philipp Markidis, Stefano Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden Engineering Mechanics KTH Royal Institute of Technology Stockholm Sweden PDC Centre for High Performance Computing KTH Royal Institute of Technology Stockholm Sweden United Kingdom

We present our approach to making direct numerical simulations of turbulence with applications in sustainable shipping. We use modern Fortran and the spectral element method to leverage and scale on supercomputers powered by the Nvidia A100 and the recent AMD Instinct MI250X GPUs, while still providing support for user software developed in Fortran. We demonstrate the efficiency of our approach by performing the world’s first direct numerical simulation of the flow around a Flettner rotor at Re=30’000 and its interaction with a turbulent boundary layer. We present one of the first performance comparisons between the AMD Instinct MI250X and Nvidia A100 GPUs for scalable computational fluid dynamics. Our results show that one MI250X offers performance on par with two A100 GPUs and has a similar power efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

A review of uncertainty estimation and its application in medical imaging

Meta-Radiology

引用

Meta-Radiology 2023年第1期1卷

作者： Zou, Ke Chen, Zhihao Yuan, Xuedong Shen, Xiaojing Wang, Meng Fu, Huazhu National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu 610065 China College of Intelligence and Computing Tianjin University Tianjin 300350 China Department of Mathematics Sichuan University Chengdu 610065 China Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A∗STAR) Singapore 138632 Singapore The College of Computer Science Sichuan University Chengdu 610065 China

The use of AI systems in healthcare for the early screening of diseases is of great clinical importance. Deep learning has shown great promise in medical imaging, but the reliability and trustworthiness of AI systems limit their deployment in real clinical scenes, where patient safety is at stake. Uncertainty estimation plays a pivotal role in producing a confidence evaluation along with the prediction of the deep model. This is particularly important in medical imaging, where the uncertainty in the model's predictions can be used to identify areas of concern or to provide additional information to the clinician. In this paper, we review the various types of uncertainty in deep learning, including aleatoric uncertainty and epistemic uncertainty. We further discuss how they can be estimated in medical imaging. More importantly, we review recent advances in deep learning models that incorporate uncertainty estimation in medical imaging. Finally, we discuss the challenges and future directions in uncertainty estimation in deep learning for medical imaging. We hope this review will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of uncertainty estimation models in medical imaging. © 2023 The Authors

关键词： Deep learning Medical image analysis Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

EAFP-Med: An Efficient Adaptive Feature Processing Module Based on Prompts for Medical Image Detection

arXiv

引用

arXiv 2023年

作者： Li, Xiang Lan, Long Lahza, Husam Yang, Shaowu Wang, Shuihua Yang, Wenjing Liu, Hengzhu Zhang, Yudong College of Computer Science and Technology National University of Defense Technology Changsha410073 China Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Biological Sciences Xi'an Jiaotong-Liverpool University Jiangsu Suzhou215123 China School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom School of Computer Science and Engineering Southeast University Jiangsu Nanjing210096 China Department of Mathematical Sciences University of Liverpool LiverpoolL69 3BX United Kingdom

In the face of rapid advances in medical imaging, cross-domain adaptive medical image detection is challenging due to the differences in lesion representations across various medical imaging technologies. To address this issue, we draw inspiration from large language models to propose EAFP-Med, an efficient adaptive feature processing module based on prompts for medical image detection. EAFP-Med can efficiently extract lesion features of different scales from a diverse range of medical images based on prompts while being flexible and not limited by specific imaging techniques. Furthermore, it serves as a feature preprocessing module that can be connected to any model front-end to enhance the lesion features in input images. Moreover, we propose a novel adaptive disease detection model named EAFP-Med ST, which utilizes the Swin Transformer V2 – Tiny (SwinV2-T) as its backbone and connects it to EAFP-Med. We have compared our method to nine state-of-the-art methods. Experimental results demonstrate that EAFP-Med ST achieves the best performance on all three datasets (chest X-ray images, cranial magnetic resonance imaging images, and skin images). EAFP-Med can efficiently extract lesion features from various medical images based on prompts, enhancing the model's performance. This holds significant potential for improving medical image analysis and diagnosis. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Munkhjargal Gochoo Munkh-Erdene Otgonbold Erkhembayar Ganbold Jun-Wei Hsieh Ming-Ching Chang Ping-Yang Chen Byambaa Dorj Hamad Al Jassmi Ganzorig Batnasan Fady Alnajjar Mohammed Abduljabbar Fang-Pang Lin Department of Computer Science and Software Engineering United Arab Emirates University UAE Emirates Center for Mobility Research United Arab Emirates University UAE College of AI and Green Energy National Yang Ming Chiao Tung University Taiwan University at Albany — State University of New York NY USA Department of Computer Science National Yang Ming Chiao Tung University Taiwan Mongolian University of Science and Technology Mongolia National Center for High-Performance Computing Taiwan

With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of State-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080×1080 and 1280×1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70:30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640×640 and 1280×1280, respectively. The dataset will be available on the GitHub link with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence

TechRxiv

引用

TechRxiv 2024年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Wang, Wen Jiang, Xuefeng Gao, Bo Lu, Jinda Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Zhongguancun Laboratory Beijing China Department of Computer Science and Technology Tsinghua University Beijing China School of Computer and Information Technology The Engineering Research Center of Network Management Technology for High-Speed Railway Ministry of Education Beijing Jiaotong University Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data sources. To protect data privacy and unify data silos distributed among end devices in EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across multiple devices without compromising data privacy. However, the prevailing FL approaches cannot guarantee model generalization and adaptation on heterogeneous clients. Recently, Personalized Federated Learning (PFL) has drawn growing awareness in EI, as it enables a productive balance between local-specific training requirements inherent in devices and global-generalized optimization objectives for satisfactory performance. However, most existing PFL methods are based on the Parameters Interaction-based Architecture (PIA) represented by FedAvg, which suffers from unaffordable communication burdens due to large-scale parameters transmission between devices and the edge server. In contrast, Logits Interaction-based Architecture (LIA) allows to update model parameters with logits transfer and gains the advantages of communication lightweight and heterogeneous on-device model allowance compared to PIA. Nevertheless, previous LIA methods attempt to achieve satisfactory performance either relying on unrealistic public datasets or increasing communication overhead for additional information transmission other than logits. To tackle this dilemma, we propose a knowledge cache-driven PFL architecture, named FedCache, which reserves a knowledge cache on the server for fetching personalized knowledge from the samples with similar hashes to each given on-device sample. During the training phase, ensemble distillation is applied to on-device models for constructive optimization with personalized knowledge transferred from the server-side knowledge cache. Empirical experiments on four datasets demonstrate that FedCache achiev

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Unbiased Quantum Random Number Generator Based on Boson Sampling

arXiv

引用

arXiv 2022年

作者： Shi, Jinjing Zhao, Tongge Wang, Yizhi Yu, Chunlin Lu, Yuhu Shi, Ronghua Zhang, Shichao Wu, Junjie School of Computer Science and Engineering Central South University Changsha410083 China Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China China Greatwall Quantum Laboratory China Greatwall Technology Group CO. LTD. Changsha410073 China

It has been proven that Boson sampling is a much promising model of optical quantum computation, which has been applied to designing quantum computer successfully, such as "Jiuzhang". However, the meaningful randomness of Boson sampling results, whose correctness and significance were proved from a specific quantum mechanical distribution, has not been utilized or exploited. In this research, Boson sampling is applied to design a novel Quantum Random Number Generator (QRNG) by fully exploiting the randomness of Boson sampling results, and its prototype system is constructed with the programmable silicon photonic processor, which can generate uniform and unbiased random sequences and overcome the shortcomings of the existing discrete QRNGs such as source-related, high demand for the photon number resolution capability of the detector and slow self-detection generator speed. Boson sampling is implemented as a random entropy source, and random bit strings with satisfactory randomness and uniformity can be obtained after post-processing the sampling results. It is the first approach for applying the randomness of Boson sampling results to develop a practical prototype system for actual tasks, and the experiment results demonstrate the designed Boson sampling-based QRNG prototype system pass 15 tests of the NIST SP 800-22 statistical test component, which prove that Boson sampling has great potential for practical applications with desirable performance besides quantum advantage. Copyright © 2022, The Authors. All rights reserved.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Thermal-aware Energy Efficient Task Scheduling Framework

Thermal-aware Energy Efficient Task Scheduling Framework

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous computing and Communications (ISPA/IUCC)

作者： Jian Nong Jia Chen Yinqing Wang Wei Qin Xi He Faculty of Innovation Engineering-School of Computer Science and Engineering Macau University of Science and Technology Macau China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou China High Performance Computing Lab Wuzhou University Wuzhou China

Large energy consumption in data centers has become a challenging problem with the emergence of cloud computing and large scale data centers. In this paper, we present an architectural framework for thermal-aware resource management while considering energy efficiency. The framework consists of a layered architecture and integrates a set of easy-to-use client tools and a thermal-aware task management middleware to schedule tasks based on thermal conditions within a cluster and among different data centers. As part of this paper we focus on the development of a thermal-aware task scheduling component for a single data center. This component is fundamental to our future activities, while considering to balance the temperature distribution in a single data center, thus implicitly minimizing energy cost in data centers.

关键词： Data centers Temperature distribution Schedules Processor scheduling Thermal management Ubiquitous computing Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Modern computing: Vision and Challenges

arXiv

引用

arXiv 2024年

作者： Gill, Sukhpal Singh Wu, Huaming Patros, Panos Ottaviani, Carlo Arora, Priyansh Pujol, Victor Casamayor Haunschild, David Parlikad, Ajith Kumar Cetinkaya, Oktay Lutfiyya, Hanan Stankovski, Vlado Li, Ruidong Ding, Yuemin Qadir, Junaid Abraham, Ajith Ghosh, Soumya K. Song, Houbing Herbert Sakellariou, Rizos Rana, Omer Rodrigues, Joel J.P.C. Kanhere, Salil S. Dustdar, Schahram Uhlig, Steve Ramamohanarao, Kotagiri Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Center for Applied Mathematics Tianjin University Tianjin China Raygun Performance Monitoring Wellington New Zealand Department of Computer Science York Centre for Quantum Technologies University of York York United Kingdom Microsoft Schiphol Netherlands Distributed Systems Group Vienna University of Technology Vienna Austria Detecon International GmbH Munich Germany Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Department of Computer Science University of Western Ontario London Canada Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Institute of Science and Engineering Kanazawa University Japan Tecnun School of Engineering University of Navarra Spain Department of Computer Science and Engineering College of Engineering Qatar University Doha Qatar Bennett University Greater Noida India Machine Intelligence Research Labs AuburnWA United States Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Baltimore United States Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Department of Computer Science College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia COPELABS Lusófona University Lisbon Portugal Sydney Australia The University of Melbourne Victoria Australia Laboratory School of Computing and Information Systems The University of Melbourne Australia

Over the past six decades, the computing systems field has experienced significant transformations, profoundly impacting society with transformational developments, such as the Internet and the commodification of computing. Underpinned by technological advancements, computer systems, far from being static, have been continuously evolving and adapting to cover multifaceted societal niches. This has led to new paradigms such as cloud, fog, edge computing, and the Internet of Things (IoT), which offer fresh economic and creative opportunities. Nevertheless, this rapid change poses complex research challenges, especially in maximizing potential and enhancing functionality. As such, to maintain an economical level of performance that meets ever-tighter requirements, one must understand the drivers of new model emergence and expansion, and how contemporary challenges differ from past ones. To that end, this article investigates and assesses the factors influencing the evolution of computing systems, covering established systems and architectures as well as newer developments, such as serverless computing, quantum computing, and on-device AI on edge devices. Trends emerge when one traces technological trajectory, which includes the rapid obsolescence of frameworks due to business and technical constraints, a move towards specialized systems and models, and varying approaches to centralized and decentralized control. This comprehensive review of modern computing systems looks ahead to the future of research in the field, highlighting key challenges and emerging trends, and underscoring their importance in cost-effectively driving technological progress. © 2024, CC BY.

关键词： Obsolescence

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Actuated Snap-Through Buckling of a Pre-Buckled Bistable Hard-Magnetic Elastica

SSRN

引用

SSRN 2023年

作者： Zhang, Yingchao Ma, Yinji Yu, Jing Gao, Huajian School of Materials Science and Engineering Nanyang Technological University 637553 Singapore AML Department of Engineering Mechanics Tsinghua University Beijing100084 China Laboratory of Flexible Electronics Technology Tsinghua University Beijing100084 China Institute for Digital Molecular Analytics and Science Nanyang Technological University 637553 Singapore School of Mechanical and Aerospace Engineering Nanyang Technological University 637553 Singapore Institute of High Performance Computing A*STAR 138632 Singapore

Snap-through buckling of bistable structures is a classic topic in mechanics which has been widely studied and applied in various fields such as mechanical meta-materials and soft robotics. Obstacles that hinder broader applications of conventional bistable structures include the requirement of contact actuation to trigger instability and difficulty to control post-buckling configurations. In contrast, hard magnetic elastica (HME), a composite made of hard ferromagnetic particles and soft elastomer that deforms in response to an externally applied magnetic field, exhibits great potential to bring major advances in this field by allowing non-contact actuation and programmable control of snap-through buckling via magnetization distribution. Here, we develop a theoretical framework to trace the instability and post-buckling evolution process of snap-through buckling of a bistable HME. In contrast to the conventional snapping through end-end shortening, the design space for bistable HME includes two key parameters: the remanent magnetization density after pre-magnetization and the external magnetic field. We focus on two simple yet practical cases: a fixed amplitude of magnetization density along the HME with direction reversed at the magnetization interface (M-interface), and a uniform magnetic field with varied direction. We identify an optimal position for the single M-interface and direction for the uniform actuation field for pre-buckled beams with two-ends fixed, which can reduce the required actuation field for snapping to nearly half in comparison with the symmetric cases. Experiments and finite element analysis are performed to validate the model predictions. Our work may stimulate further studies on utilizing snap-through buckling in applications where fast and large shape transitions from one stable state to another can be actuated in a low-energy, non-contact mode through a remotely applied stimulus field. © 2023, The Authors. All rights reserved.

关键词： Magnetization

来源：评论

学校读者我要写书评

暂无评论

Weak Devices Matter: Model Heterogeneity in Resource-Constrained Federated Learning

Weak Devices Matter: Model Heterogeneity in Resource-Constra...

引用

IEEE International Conference on Communications (ICC)

作者： Tzu–Hsuan Peng Cheng-Wei Huang Ai-Chun Pang Te-Chuan Chiu Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan R.O.C Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan R.O.C High Performance and Scientific Computing Center National Taiwan University Taipei Taiwan R.O.C Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan R.O.C Department of Computer Science National Tsing Hua University Hsinchu Taiwan R.O.C

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Federated Learning (FL) is a promising framework for enabling edge intelligence while preserving privacy and enhancing communication efficiency. In real-world scenarios, limited and heterogeneous hardware resources among users threaten the overall training efficiency in FL. To address this issue, several model heterogeneity frameworks have emerged in recent years. However, existing studies primarily focus on mitigating idle times on powerful devices, overlooking the fact that strong devices may not always have a positive impact and can potentially become a burden instead. Furthermore, as the resource gap among clients widens or the number of weak devices increases, the model may be hindered by the influence of strong devices. Directly applying existing model heterogeneity frameworks leads to model performance degradation due to the neglect of contributions from weak devices. To make a performance breakthrough, we proposed a novel FL framework called Progressive Width Mixing (PWM), which extracts diverse features and balances the contribution of strong and weak devices and mitigates straggler effects under scenarios with various device distributions. To our best knowledge, we are the first model heterogeneity work that considered straggler effects from the weak devices' point of view. The experiments show that PWM maintains stability over different datasets and outperforms all baselines across various device distributions and non-IID scenarios. PWM makes a leap forward and surpasses all baselines by 7%, and mitigates the negative impact from the strong devices.

关键词： performance evaluation Training Privacy Philosophical considerations Federated learning Pulse width modulation System recovery

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：