检索结果-内蒙古大学图书馆

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthesized Acoustic Vortex-Frequency Comb via Rotational Doppler Effect

引用

Physical Review Letters 2025年第13期134卷 137001-137001页

作者： Yurou Jia Xuan Zhang Suying Zhang Guoqiang Xu Taoyu Chen Hongtao Zhou Yechao Bai Ying Cheng Dajian Wu Department of Physics MOE Key Laboratory of Modern Acoustics Collaborative Innovation Center of Advanced Microstructures Jiangsu Physical Science Research Center Nanjing University Nanjing 210093 China Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Mechanics School of Mechanical Engineering Tianjin University Tianjin 300350 China School of Electronic Science and Engineering Nanjing University Nanjing 210023 China Jiangsu Key Lab on Opto-Electronic Technology School of Physics and Technology Nanjing Normal University Nanjing 210023 China

The synergistic control of light’s frequency and orbital angular momentum (OAM) via integrated nonlinear ring microresonators is crucial for creating spatiotemporal optical waveforms and advancing optical metrology. A direct analog of this capability in acoustics is challenging due to the nonlinearity-based mechanisms’ dependence on external driving and limited frequency conversion efficiency. Here, we present an acoustic synthesized comb structure derived from spatiotemporal metasurfaces, concurrently controlling frequency and OAM characteristics with high conversion efficiency and removing the constraints of critical driving frequency and power level in nonlinear mechanisms. By optimizing comb structures, energy distributions among OAM modes are adjusted to different frequency lines. We finally propose spatiotemporal metalens devices based on vortex-frequency combs, enabling synchronously multiple-order spatial differential operations for parallel data processing. This Letter is groundbreaking in integrating spectral- and spatial-domain acoustic waves, promising multifunctional imaging and advantages in spatiotemporal beams.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Predicting CRISPR Cas9 Off-Target Activities With a Two-Stage Deep Learning Framework

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 956-962页

作者： Tianshan Zhang Bei Jiang Guang Yang Zhijie Bao Jiajie Peng AI for Science Interdisciplinary Research Center School of Computer Science Northwestern Polytechnical University Xi'an China Key Laboratory of Big Data Storage and Management Ministry of Industry and Information Technology Northwestern Polytechnical University Shanxi China The National Engineering Laboratory for In tegrated Aerospace Ground Ocean Big Data Application Technology Shanxi China Tianjin second people's hospital Tianjin China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China

The CRISPR-Cas9 system, found across bacteria and archaea, enables efficient genome engineering in eukaryotic cells. There is a challenge that Cas9 guide RNA may cause off-target activities. Although numbers of methods have been proposed to predict off-target activities in guide RNA designing, this procedure involves numerous potential off-target sites, which causes label imbalance problem. To address this problem, we developed a deep learning framework, named CAF-Net (Cas9 Augmentation and Finetune Network), for predicting off-target activities of CRISPR-Cas9. First, we pretrain an embedding model to extract features from target and guide sequence pairs. Subsequently, data augmentation is applied to these features. And finally, the model is finetuned with synthetic samples. Evaluation results demonstrate its performance on published datasets.

关键词： RNA Bioinformatics Feature extraction DNA Genomics Convolutional neural networks Computational modeling Transformers Predictive models CRISPR

来源：评论

学校读者我要写书评

暂无评论

Adaptive ELM-Based Time-Constrained Control of Uncertain Robotic Manipulators With Minimum Learning Computation

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Jin, Xiaozheng Hou, Yuhan Wu, Xiaoming Chi, Jing Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Shandong Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Jinan250013 China Qilu Institute of Technology School of Intelligent Manufacturing and Control Engineering Shandong Jinan250200 China Shandong University of Finance and Economics School of Computing and Artificial Intelligence Shandong Jinan250014 China

This paper studies the extreme learning machine (ELM)-based time-constrained trajectory tracking control of a class of robotic manipulator systems with model/input uncertainties, matched and mismatched disturbances. A uniform robust exact differentiator (URED) is developed to construct a multi-layer virtual control framework of the robotic manipulator system. Under the control framework, adaptive ELM-based control strategies are proposed to suppress the influence of the uncertainties and disturbances layer-by-layer, combining with the minimum learning parameter (MLP) technique which is employed to reduce the calculation complexity of ELM parameters. The significance of this study is that general model/input uncertainties, matched and mismatched disturbances can be effectively compensated within a limited time, so that bounded trajectory tracking of the robotic manipulator can be achieved avoiding the complexity explosion issue. The time-constrained stability of the closed-loop robotic error systems is proved through Lyapunov stability theory. Finally, comparative simulations are employed to display the feasibility and superiority of the designed robust adaptive ELM-based control schemes of a robotic manipulator system. © 2013 IEEE.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Compression, Transmission and Computation for Cooperative Perception Aided Intelligent Vehicular Networks

引用

IEEE Transactions on Vehicular technology 2025年

作者： Lu, Binbin Huang, Xumin Wu, Yuan Qian, Liping Zhou, Sheng Niyato, Dusit University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science Macau China Guangdong University of Technology School of Automation Guangzhou510006 China University of Macau State Key Lab of Internet of Things for Smart City Macau China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer Information Science Macau China Zhuhai UM Science and Technology AQ2 Research Institute Zhuhai519301 China Zhejiang University of Technology Institute of Cyberspace Security Hangzhou310023 China Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China Nanyang Technological University School of Computer Science and Engineering Singapore

Cooperative perception is a promising paradigm to tackle the perception limitations of a single intelligent vehicle (IV) to enhance the driving safety and efficiency in intelligent vehicular networks. However, the real-time transmission and computation-intensive fusion of raw sensing data raise new challenges for satisfying the stringent delay requirement of delay-sensitive applications. In this paper, we formulate a joint optimization problem of the cooperative IV selection, compression ratio selection, transmit power control, task offloading decision and computation allocation to minimize the end-to-end delay consisting of compression, transmission and computation. In particular, to meet the perception probability requirement, the quality and quantity-aware matching algorithm is proposed to optimize the cooperative IV selection. To guarantee the queue stability of offloading tasks, we develop the Lyapunov optimization algorithm to determine the upper bound of the offloading tasks and the corresponding optimal computation allocation. The Lyapunov aided deep reinforcement learning algorithm is further proposed to dynamically adjust the task offloading decision and compression ratio selection to minimize the end-to-end delay with the transmit power control being optimized by the successive convex approximation algorithm. Simulation results demonstrate that, compared to several benchmark algorithms, our proposed algorithm achieves the lowest end-to-end delay while guaranteeing the requirements on perception probability and queue stability effectively. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of Electronic Prescription Systems in the European Union: Benchmarking Development, Use, and Future Trends

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3712-3722页

作者： Bruthans, Jan Duftschmid, Georg Hammar, Tora Kardas, Przemyslaw Bertalan, Lorant Hug, Martin J. Bullow, Cille Muscat, Hugo Agius Lillevali, Anett Jormanainen, Vesa Fernandez-Llimos, Fernando Fidalgo, Luz Karanikas, Haralampos Nyssen, Marc Popescu, Nirvana Cudejkova, Maria Tachkov, Konstantin Hadziabdic, Maja Ortner Neofytou, Marios Dauksiene, Jurgita Huisman, Anneke Ryan, Brid Kasparans, Aris Napoleoni, Matteo Perfili, Mirko Smet, Daisy Calafiore, Matthieu Stanimirovic, Dalibor Czech Technical University in Prague Department of Biomedical Technology Faculty of Biomedical Engineering Prague Czech Republic Medical University of Vienna Section for Medical Information Management Center for Medical Data Science Vienna Austria Linnaeus University eHealth Institute Kalmar Sweden Medical University of Lodz Medication Adherence Research Centre Department of Family Medicine Lodz Poland Semmelweis University Faculty of Health Sciences Budapest Hungary Medical Center-University of Freiburg Pharmacy Freiburg Germany Bispebjerg and Frederiksberg University Hospital Department of Clinical Pharmacology Copenhagen Denmark Ministry for Health and Active Ageing Directorate for Health Information & Research Valletta Malta Estonian Health Insurance Fund Tallinn Estonia University of Helsinki Department of Public Health Faculty of Medicine Helsinki Finland University of Porto Applied Molecular Biosciences Unit Laboratory of Pharmacology Faculty of Pharmacy Porto Portugal Ministry of Health Madrid Spain University of Thessaly Department of Computer Science and Biomedical Informatics Lamia Greece Vrije Universiteit Brussel Department of Public Health Brussel Belgium National University of Science and Technology POLITEHNICA Bucharest Computer Science Department Bucharest Romania National Health Information Centre Bratislava Slovakia Medical University of Sofia Faculty of Pharmacy Sofia Bulgaria University of Zagreb Faculty of Pharmacy and Biochemistry Zagreb Croatia University of Cyprus Electronic Health Laboratory Computer Science Department Nicosia Cyprus Lithuanian University of Health Sciences Drug technology and Social Pharmacy Department Vilnius Lithuania Royal Dutch Pharmacists Association The Hague Netherlands Health Service Executive ePharmacy Programme Dublin Ireland National Health Service of Latvia Riga Latvia GE Healthcare Milan Italy Bambino Gesu' Children's Research Hospital IRCCS Rome Italy Agence eSanté Luxembourg Luxe

While Electronic Prescription Systems (EPS) adoption varies across EU Member States, there's a lack of comprehensive comparative analysis. Existing studies focus on single EPSs, employ diverse methodologies, and lack up-to-date data. This study fills this gap by providing a comprehensive overview of EPS development, functionalities, and usage statistics in each EU Member State. Most EU Member States widely adopted EPS by 2022, with exceptions including Germany, France, and Luxembourg, where pilot projects or just plans existed at that time. Out of the 27 EPSs, 25 employ a similar design featuring a central server and end-user software or web-based applications. Among these, 22 are structured as single national systems. The fundamental technical solution is remarkably similar across the EU. Despite these similarities, functionalities, authentication methods, prescription validity, and medication coverage differ significantly among EPSs. A multinational team, including co-authors from each EU Member State, collected data using a structured questionnaire. The study underscores the need for standardized methodologies in EPS research and emphasizes the importance of comprehensive comparative analysis to inform healthcare policies and digitalization efforts. © 2013 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs 25

UICopilot: Automating UI Synthesis via Hierarchical Code Gen...

引用

Proceedings of the ACM on Web Conference 2025

作者： Yi Gui Yao Wan Zhen Li Zhongyi Zhang Dongping Chen Hongyu Zhang Yi Su Bohua Chen Xing Zhou Wenbin Jiang Xiangliang Zhang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology Wuhan China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame USA

ISBN: (纸本)9798400712746

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V.

关键词： UI automation

来源：评论

学校读者我要写书评

暂无评论

Constraint Boundary Wandering Framework: Enhancing Constrained Optimization with Deep Neural Networks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wu, Shuang Chen, Shixiang Shen, Li Zhang, Lefei Tao, Dacheng Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China University of Science and Technology of China Key Laboratory of the Ministry of Education for Mathematical Foundations and Applications of Digital Technology School of Mathematical Sciences China Shenzhen Campus of Sun Yat-sen University School of Cyber Science and Technology Shenzhen518107 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

Constrained optimization problems are pervasive in various fields, and while conventional techniques offer solutions, they often struggle with scalability. Leveraging the power of deep neural networks (DNNs) in optimization, we present a novel learning-based approach, the Constraint Boundary Wandering Framework (CBWF), to address these challenges. Our contributions include introducing a boundary wandering strategy inspired by the active-set method, enhancing equality constraint feasibility, and treating the Lipschitz constant as a learnable parameter. Additionally, we evaluate the regularization term, illustrating that the nonsmooth L2 norm yields superior results. Extensive testing on synthetic datasets and the ACOPT dataset demonstrates CBWF's superiority, outperforming existing deep learning-based solvers in terms of both objective and constraint loss. © 1979-2012 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

LMP-GAN: Out-Of-Distribution Detection For Non-Control Data Malware Attacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wood, David Kapp, David Kebede, Temesgen Hirakawa, Keigo Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) samples - unlike the fully supervised variant, the distribution of the outlier samples are never explicitly modeled in OOD detection tasks. In this work, we design a novel GAN-based OOD detection network specifically designed to protect a cyber-physical signal systems from novel Trojan malware called non-control data (NCD) attack that evades conventional malware detection techniques. Inspired in part by the classical locally most powerful (LMP) test in statistical inferences, the proposed LMP-GAN trains the OOD detector (discriminator) by generating OOD samples that are aimed at making maximal alteration to the inlier samples while evading detection. We experimentally compare the results to the state-of-the-art anomaly detection methods to demonstrate the benefits and the appropriateness of the LMP-GAN OOD detector. © 2025 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

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：