检索结果-内蒙古大学图书馆

Generative AI in Data Center Networking: Fundamentals, Perspectives, and Case Study

IEEE Network 2025年

作者： Liu, Yinqiu Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Wen, Yonggang Kim, Dong In Nanyang Technological University College of Computing and Data Science Singapore University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Guangdong University of Technology School of Automation China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore Sungkyunkwan University College of Information and Communication Engineering Korea Republic of

Generative AI (GenAI), exemplified by Large Language Models (LLMs), such as OpenAI’s ChatGPT, is revolutionizing various fields. Central to this transformation is Data Center Networking (DCN), which not only provides the infrastructure support for GenAI operation, but also provisions GenAI services to users. Hence, this article explores the interplay between GenAI and DCNs, analyzing their symbiotic relationship and mutual advances. We begin by reviewing the current challenges of DCNs and GenAI-based solutions, such as data augmentation, process automation, and domain transfer. We then discuss the distinctive characteristics of GenAI workloads on DCNs, gaining insights that catalyze the evolution of DCNs to more effectively support GenAI. Moreover, to illustrate the seamless integration of GenAI with DCNs, we present a case study on GenAI-empowered DCN digital twins. Specifically, we employ an LLM equipped with retrieval augmented generation to formulate optimization problems for DCNs (e.g., resource allocation and routing) and adopt diffusion-deep reinforcement learning to solve optimization. The experimental results on a representative DCN optimization problem, i.e., knowledge placement, demonstrate the validity and efficiency of our proposals. We anticipate that this article can promote further research to enhance the virtuous interaction between GenAI and DCNs. © 1986-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

IR Design for Application-Specific Natural Language: 、A Case Study on Traffic Data

arXiv

引用

arXiv 2023年

作者： Hu, Wei Wang, Xuhong Wang, Ding Yao, Shengyue Mao, Zuqiu Li, Li Wang, Fei-Yue Lin, Yilun Urban Computing Lab Shanghai AI Laboratory Shanghai China 51 WORLD Shanghai China The Department of Automation Tsinghua University Beijing China The Institute of Automation Chinese Academy of Sciences Beijing China The Macau Institute of Systems Engineering Macau University of Science and Technology China

In the realm of software applications in the transportation industry, Domain-Specific Languages (DSLs) have enjoyed widespread adoption due to their ease of use and various other benefits. With the ceaseless progress in computer performance and the rapid development of large-scale models, the possibility of programming using natural language in specified applications - referred to as Application-Specific Natural Language (ASNL) - has emerged. ASNL exhibits greater flexibility and freedom, which, in turn, leads to an increase in computational complexity for parsing and a decrease in processing performance. To tackle this issue, our paper advances a design for an intermediate representation (IR) that caters to ASNL and can uniformly process transportation data into graph data format, improving data processing performance. Experimental comparisons reveal that in standard data query operations, our proposed IR design can achieve a speed improvement of over forty times compared to direct usage of standard XML format data. © 2023, CC BY.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning Based Human Activity Recognition Using Body Sensors 9

Contrastive Learning Based Human Activity Recognition Using ...

引用

9th International Conference on Big Data computing and Communications, BigCom 2023

作者： Xie, Chuanshi Zhou, Yu Yu, Dandan Sun, Shilong Zhang, Xiao Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The First Affiliated Hospital of Dalian Medical University Information Center Dalian China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China South-Central Minzu University Department of Computer Science China South-Central Minzu University Key Laboratory of Cyber-Physical Fusion Intelligent Computing State Ethnic Affairs Commission Wuhan430074 China

ISBN: (纸本)9798350331240

Pervasive sensing and wearable sensor techniques have been increasingly employed to monitor and recognize human activities through body sensors in areas of smart healthcare and manufacturing. However, conventional machine learning or deep learning based human activity recognition (HAR) requires a large amount of labeled data, which is cost-expensive in real-world scenarios. To tackle this issue, we propose a contrastive learning framework for HAR (CL-HAR), which utilizes the generated unlabeled data as the input and explores the supervised features of the unlabeled data under the principle of self-supervised learning. A simple yet effective backbone network as a feature extractor for subsequent activity recognition is proposed. By using a small portion of the labeled samples as the training set which is fed into our learned feature extractor, we build a classifier and use the rest of the data to verify the feasibility and effectiveness of our CL method. Extensive experiments on three benchamark datasets and one real-world dataset demonstrate that CL-HAR can achieve better classification accuracy than compared supervised and semi-supervised methods with less labelled samples, which is of practical use. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Analysis of current harmonics in data center power system

Analysis of current harmonics in data center power system

引用

Proceedings of the International Convention MIPRO

作者： K. Raič Raguž M. Miletić V. Zelenič ić D. Sumina I. Erceg Ž . Nastasić Department of Electric Machines Drives and Automation Faculty of Electrical Engineering and Computing Zagreb Croatia Databox d.o.o. Zagreb Croatia

ISBN: (数字)9789532331035

ISBN: (纸本)9781665484343

This paper presents power quality analysis at different points in a data center. Electrical distribution network scheme and data center description are also given. The method of measurements performed is briefly described and the results of real measurements of current and voltage Total Harmonic Distortion (THD) are presented and compared with IEEE 519-2014 recommended practice and requirements for harmonic control in electric power system. All measured values comply with the standard but measurements at downstream levels closer to the nonlinear loads have larger THD.

关键词： Total harmonic distortion Voltage measurement Power measurement Current measurement Power quality Harmonic analysis Distortion measurement

来源：评论

学校读者我要写书评

暂无评论

Uncovering neural scaling laws in molecular representation learning 23

Uncovering neural scaling laws in molecular representation l...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dingshuo Chen Yanqiao Zhu Jieyu Zhang Yuanqi Du Zhixun Li Qiang Liu Shu Wu Liang Wang Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences Department of Computer Science University of California Los Angeles The Paul G. Allen School of Computer Science and Engineering University of Washington Department of Computer Science Cornell University Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong

Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a surge of interest in advancing model-centric techniques, the influence of both data quantity and quality on molecular representations is not yet clearly understood within this field. In this paper, we delve into the neural scaling behaviors of MRL from a data-centric viewpoint, examining four key dimensions: (1) data modalities, (2) dataset splitting, (3) the role of pre-training, and (4) model capacity. Our empirical studies confirm a consistent power-law relationship between data volume and MRL performance across these dimensions. Additionally, through detailed analysis, we identify potential avenues for improving learning efficiency. To challenge these scaling laws, we adapt seven popular data pruning strategies to molecular data and benchmark their performance. Our findings underline the importance of data-centric MRL and highlight possible directions for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced chaos-based image compression-encryption algorithm utilizing 2D compressive sensing and genetic algorithm optimization

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Nanfak, Arnaud de Dieu Nkapkop, Jean Mvogo Ngono, Joseph Tabekoueng Njitacke, Zeric Lessouga Etoundi, Christophe Magloire Effa, Joseph Yves Laboratory of Electronic Electrical Engineering Automation and Telecommunication National Higher Polytechnic School of Douala University of Douala PO Box 2701 Douala Cameroon Technology and Applied Sciences Laboratory University Institute of Technology University of Douala P.O. Box 8698 Douala Cameroon Applied Computing Laboratory Faculty of Science University of Douala P.O. Box 2701 Douala Cameroon University of Buea P.O. Box 63 Buea Cameroon Department of Physics Faculty of Science University of Ngaoundere P.O. Box 454 Ngaoundere Cameroon

This paper introduces an innovative image compression and encryption algorithm that leverages the genetic algorithm (GA), compressive sensing (CS), and a newly developed hyperchaotic map. In this algorithm, the GA is employed to optimize the compression parameters, including those related to generating the measurement matrix and performing thresholding operation. The optimization objective is centred around on the Peak-Signal-to-Noise-Ratio (PSNR) of the reconstructed image. The encryption part involves employing the Arnold transform and byte-wise XOR operator for confusion and diffusion, respectively. The generation of the measurement matrix and chaotic sequences for encryption is facilitated by a novel two-dimensional fractional-Sine–Cosine (2DFSC) hyperchaotic map introduced in this research. Simulation outcomes demonstrate dynamic parameter values adjustments through optimization, resulting in improved decompression efficiency across different compression rates and image types. Assessment of security and decompression performance confirms the effectiveness of the proposed algorithm, showing a good compression effect, a good reconstruction efficacity even for low compression ratio, good speed and high security compared to some recent similar systems. This work may therefore be suitable to compress and secure data in wireless body area network applications, including those related to the internet of medical things. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Towards Open-Set Document Layout Segmentation Through Class-Specific Prototype Learning

SSRN

引用

SSRN 2023年

作者： Sang, Yuman Yu, Shenbao Zeng, Yifeng Pan, Yinghui Yao, Zhangrui Department of Automation Xiamen University Xiamen China Department of Computer and Information Sciences Northumbria University Newcastle upon Tyne United Kingdom National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Open-set segmentation is an emerging and challenging topic, especially when it is combined with domain-specific tasks. Beyond recognizing known classes, the system needs to reject the unknowns. In this paper, we study the open-set document layout segmentation problem and propose a two-phase framework (OpenDLS) that accurately recognizes pixels in document images from known classes and rejects those from the unknowns. In the first phase, we propose a class-specific prototype learning strategy and design two loss functions for model training. In addition, considering the multifarious appearance of objects, a multi-scale feature fusion module is developed. In the second phase, we propose three rejection rules to detect the pixels that belong to unknown classes. To the best of our knowledge, this is the first work to investigate the open-set document layout segmentation task. Extensive experiments demonstrate the effectiveness of our framework in both known class classification and unknown class identification. © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

SoftGPT: Learn Goal-Oriented Soft Object Manipulation Skills by Generative Pre-Trained Heterogeneous Graph Transformer

SoftGPT: Learn Goal-Oriented Soft Object Manipulation Skills...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Junjia Liu Zhihao Li Wanyu Lin Sylvain Calinon Kay Chen Tan Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong SAR Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Idiap Research Institute Martigny Switzerland

Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from human demonstration is an effective way for robot applications, developing prior knowledge of the representation and dynamics of soft objects is necessary. In this regard, we propose a pretrained soft object manipulation skill learning model, namely SoftGPT, that is trained using large amounts of exploration data, consisting of a three-dimensional heterogeneous graph representation and a GPT-based dynamics model. For each downstream task, a goal-oriented policy agent is trained to predict the subsequent actions, and SoftGPT generates the consequences of these actions. Integrating these two approaches establishes a thinking process in the robot's mind that provides rollout for facilitating policy learning. Our results demonstrate that leveraging prior knowledge through this thinking process can efficiently learn various soft object manipulation skills, with the potential for direct learning from human demonstrations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A federated learning attack method based on edge collaboration via cloud

A federated learning attack method based on edge collaborati...

引用

作者： Yang, Jie Baker, Thar Gill, Sukhpal Singh Yang, Xiaochuan Han, Weifeng Li, Yuanzhang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computer Science Beijing Institute of Technology Beijing China School of Mechanical Manufacturing and Automation Engineer of China Railway Tunnel Bureau Group Co. Ltd Henan Zhengzhou China

Federated learning (FL) is widely used in edge-cloud collaborative training due to its distributed architecture and privacy-preserving properties without sharing local data. FLTrust, the most state-of-the-art FL defense method, is a federated learning defense system with trust guidance. However, we found that FLTrust is not very robust. Therefore, in the edge collaboration scenario, we mainly study the poisoning attack on the FLTrust defense system. Due to the aggregation rule, FLTrust, with trust guidance, the model updates of participants with a significant deviation from the root gradient direction will be eliminated, which makes the poisoning effect on the global model not obvious. To solve this problem, under the premise of not being deleted by the FLTrust aggregation rules, we construct malicious model updates that deviate from the trust gradient to the greatest extent to achieve model poisoning attacks. First, we utilize the rotation of high-dimensional vectors around axes to construct malicious vectors with fixed orientations. Second, the malicious vector is constructed by the gradient inversion method to achieve an efficient and fast attack. Finally, a method of optimizing random noise is used to construct a malicious vector with a fixed direction. Experimental results show that our attack method reduces the model accuracy by 20%, severely undermining the usability of the model. Attacks are also successful hundreds of times faster than the FLTrust adaptive attack method. © 2022 John Wiley & Sons Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Passive Mixing in Microfluidics Utilizing Porous PDMS Sponge

Novel Approach for Passive Mixing in Microfluidics Utilizing...

引用

Computer Science (COMSCI), International Scientific Conference on

作者： Emil Grigorov Boris Kirov Jordan A. Denev Vassil Galabov German Engineering Education and Industrial Management Technical University of Sofia Sofia Bulgaria Department Industrial Automation Technical University of Sofia Sofia Bulgaria Steinbuch Centre for Computing Karlsruhe Institute of Technology Karlsruhe Germany

Mixing in microfluidic devices has been always a significant challenge due to the small channel dimensions and the strongly laminar flow character of the fluids. However, mixing is an essential process in various biological, chemical and pharma processes. This paper introduces a new approach to passive mixing in microfluidic devices, utilizing a quick and cheap way with a sugar cube as prototype to produce a) porous medium. The authors present experimental and numerical analyses of the method, showing that the efficiency of mixing decreases as the volume flow rates of the fluids increase for flows studied with Re in the range 0,028-0,26. The largest porous mediumtested achieved a maximum mixing efficiency of 98%, suggesting that larger geometries may yield even higher efficiencies. A decrease in mixing efficiency along the length of the sponge with increasing volume flow rates was also observed (experimentally and numerically), possibly due to increased backflow. Despite the complexity of the Polydimethylsiloxan (PDMS) sponge, numerical analysis indicates a linear relationship between pressure drop and Reynolds number.

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：