检索结果-内蒙古大学图书馆

arXiv 2025年

作者： An, Shan Meng, Ziyu Tang, Chao Zhou, Yuning Liu, Tengyu Ding, Fangqiang Zhang, Shufang Mu, Yao Song, Ran Zhang, Wei Hou, Zeng-Guang Zhang, Hong School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Control Science and Engineering Shandong University Jinan250061 China State Key Laboratory of General Artificial Intelligence Beijing100086 China Department of Mechanical and Process Engineering ETH Zurich Zurich8092 Switzerland Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China School of Informatics University of Edinburgh EH8 9AB United Kingdom Department of Computer Science University of Hong Kong 999077 Hong Kong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology 999078 China

Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive force modulation, enables complex interactions similar to human hand dexterity. With recent advances in robotics and machine learning, there is a growing demand for these systems to operate in complex and unstructured environments. Traditional model-based approaches struggle to generalize across tasks and object variations due to the high-dimensionality and complex contact dynamics of dexterous manipulation. Although model-free methods such as reinforcement learning (RL) show promise, they require extensive training, large-scale interaction data, and carefully designed rewards for stability and effectiveness. Imitation learning (IL) offers an alternative by allowing robots to acquire dexterous manipulation skills directly from expert demonstrations, capturing fine-grained coordination and contact dynamics while bypassing the need for explicit modeling and large-scale trial-and-error. This survey provides an overview of dexterous manipulation methods based on imitation learning (IL), details recent advances, and addresses key challenges in the field. Additionally, it explores potential research directions to enhance IL-driven dexterous manipulation. Our goal is to offer researchers and practitioners a comprehensive introduction to this rapidly evolving domain. Copyright © 2025, The Authors. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Sustained petaflop and beyond: Can parallel computing systems meet the challenges?

Sustained petaflop and beyond: Can parallel computing system...

引用

19th IEEE International parallel and Distributed Processing Symposium, IPDPS 2005

作者： Gao, Guang R. Computer Architecture and Parallel System Laboratory Dept. of Electrical and Computer Engineering University of Delaware Department of Electrical and Computer Engineering University of Delaware

ISBN: (纸本)0769523129

Breakthrough-quality scientific discoveries in the new millennium (such as those expected in computation biology and others), along with optimal engineering designs, have created a demand for High-End Computing (HEC) systems with sustained performance requirements at a petaflop scale and beyond. Despite the very pessimistic (if not negative) views on parallel computing systems that have prevailed in 1990s, there seems to be no other viable alternatives for such HEC systems. In this talk, we present a fresh look at the problems facing the design of petascale parallel computing systems. We review several fundamental issues that such HEC parallel computing systems must resolve. These issues include: execution models that support dynamic and adaptive multithreading, fine-grain synchronization, and global name-space and memory consistency. Related issues in parallel programming, dynamic compilation models, and system software design will also be discussed. Present solutions and future direction will be discussed based on (1) application demand (e.g. computation biology and others), (2) the recent trend as demonstrated by the HTMT, HPCS, and the Blue-Gene Cyclops (e.g. Cyclops-64) architectures, and (3) a historical perspective on influential models such as dataflow, along with concepts learned from these models.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

UAV-Aided Covert Federated Learning Networks

引用

IEEE Network 2025年

作者： Wang, Chao Guo, Shaoyong Xiong, Zehui Xing, Chengwen Zhao, Nan Niyato, Dusit Karagiannidis, George Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore Beijing Institute of Technology School of Information and Electronics Beijing100081 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Greece

With the increasing emphasis on data privacy, federated learning (FL) networks show great potential through distributed training without directly sharing the raw data. However, the coverage of FL terrestrial servers is usually limited. Therefore, we propose leveraging the unmanned aerial vehicle (UAV) as a mobile flying server to further improve the wireless coverage and training efficiency of FL. Nevertheless, frequent exchanges of model parameters in UAV-assisted FL can result in serious security risks. In order to achieve this, we propose a covert FL scheme assisted by the UAV, which can protect the transmission key features of local models from being detected by wardens. Furthermore, we discuss the FL network and covert communications, as well as the exceptional features of UAV-assisted covert FL. Finally, we present two case studies, one of which focuses on minimising the network latency, while the other concentrates on reducing the energy consumption of covert FL. The simulation results demonstrate the efficacy of the proposed schemes in addressing future challenges. © 1986-2012 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

引用

Frontiers of Information Technology & Electronic engineering 2017年第6期18卷 796-807页

作者： Zhen-hua YUAN Chen CHEN Xiang CHENG Guo-cheng LV Liu-qing YANG Ye JIN State Key Laboratory of Advanced Optical Communication Systems and Networks Peking University Department of Electrical & Computer Engineering Colorado State University

This article is focused on secure relay beamformer design with a correlated channel model in the relay-eavesdropper network. In this network, a single-antenna source-destination pair transmits secure information with the help of an amplify-and-forward (AF) relay equipped with multiple antennas, and the legitimate and eavesdropping channels are correlated. The relay cannot obtain the instantaneous channel state information (CSI) of the eavesdropper, and has only the knowledge of correlation information between the legitimate and eavesdropping channels. Depending on this information, we derive the conditional distribution of the eavesdropping channel. Two beamformers at the relay are studied for the approximate ergodic secrecy rate:(1) the generalized match-andforward (GMF) beamformer to maximize the legitimate channel rate, and (2) the general-rank beamformer (GRBF).In addition, one lower-bound-maximizing (LBM) beamformer at the relay is discussed for maximizing the lower bound of the ergodic secrecy rate. We find that the GMF beamformer is the optimal rank-one beamformer, that the GRBF is the iteratively optimal beamformer, and that the performance of the LBM beamformer for the ergodic secrecy rate gets close to that of the GRBF for the approximate secrecy rate. It can also be observed that when the relay has lower power or the channel gain of the second hop is low, the performance of the GMF beamformer surpasses that of the GRBF. Numerical results are presented to illustrate the beamformers' performance.

关键词： Physical layer security Relay beamforming Correlated channels Ergodic secrecy rate

来源：评论

学校读者我要写书评

暂无评论

Multimodal Price Prediction

引用

Annals of Data Science 2023年第3期10卷 619-635页

作者： Zehtab-Salmasi, Aidin Feizi-Derakhshi, Ali-Reza Nikzad-Khasmakhi, Narjes Asgari-Chenaghlu, Meysam Nabipour, Saeideh Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran Department Computer and Electrical Engineering University of Mohaghegh Ardabili Ardabil Iran

Price prediction is one of the examples related to forecasting tasks and is a project based on data science. Price prediction analyzes data and predicts the cost of new products. The goal of this research is to achieve an arrangement to predict the price of a cellphone based on its specifications. So, five deep learning models are proposed to predict the price range of a cellphone, one unimodal and four multimodal approaches. The multimodal methods predict the prices based on the graphical and non-graphical features of cellphones that have an important effect on their valorizations. Also, to evaluate the efficiency of the proposed methods, a cellphone dataset has been gathered from GSMArena. The experimental results show 88.3% F1-score, which confirms that multimodal learning leads to more accurate predictions than state-of-the-art techniques. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Price prediction Multimodal learning Convolutional neural network Inception Classification Prediction Multimodal Price Deep learning Data science Mobile phone

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Fusion Framework Using Deep Learning for Visual-Textual Sentiment Classification

引用

computers, Materials & Continua 2023年第8期76卷 2145-2177页

作者： Israa K.Salman Al-Tameemi Mohammad-Reza Feizi-Derakhshi Saeed Pashazadeh Mohammad Asadpour Computerized Intelligence Systems Laboratory Department of Computer EngineeringFaculty of Electrical and Computer EngineeringUniversity of TabrizTabriz51368Iran Department of Computer Engineering Faculty of Electrical and Computer EngineeringUniversity of TabrizTabriz51368Iran State Company for Engineering Rehabilitation and Testing Iraqi Ministry of Industry and MineralsBaghdad10011Iraq

Multimodal Sentiment Analysis(SA)is gaining popularity due to its broad application *** existing studies have focused on the SA of single modalities,such as texts or photos,posing challenges in effectively handling social media data with multiple ***,most multimodal research has concentrated on merely combining the two modalities rather than exploring their complex correlations,leading to unsatisfactory sentiment classification *** by this,we propose a new visualtextual sentiment classification model named Multi-Model Fusion(MMF),which uses a mixed fusion framework for SA to effectively capture the essential information and the intrinsic relationship between the visual and textual *** proposed model comprises three deep neural *** different neural networks are proposed to extract the most emotionally relevant aspects of image and text ***,more discriminative features are gathered for accurate sentiment ***,a multichannel joint fusion modelwith a self-attention technique is proposed to exploit the intrinsic correlation between visual and textual characteristics and obtain emotionally rich information for joint sentiment ***,the results of the three classifiers are integrated using a decision fusion scheme to improve the robustness and generalizability of the proposed *** interpretable visual-textual sentiment classification model is further developed using the Local Interpretable Model-agnostic Explanation model(LIME)to ensure the model’s explainability and *** proposed MMF model has been tested on four real-world sentiment datasets,achieving(99.78%)accuracy on Binary_Getty(BG),(99.12%)on Binary_iStock(BIS),(95.70%)on Twitter,and(79.06%)on the Multi-View Sentiment Analysis(MVSA)*** results demonstrate the superior performance of our MMF model compared to single-model approaches and current state-of-the-art techniques based on model evaluation cr

关键词： Sentiment analysis multimodal classification deep learning joint fusion decision fusion interpretability

来源：评论

学校读者我要写书评

暂无评论

A NEURAL-NETWORK CONTENTION CONTROLLER FOR PACKET-SWITCHING NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第6期6卷 1402-1410页

作者： BINH, LN CHONG, HC Applied Photonics and Optical Communications Laboratory Department of Electrical and Computer Systems Engineering Monash University Melbourne VIC Australia

A novel approach to solving the output contention in packet switching networks with synchronous switching mode is presented. A contention controller has been designed based on the K-winner-take-all neural-network technique with a speedup factor to achieve a real-time computation of a nonblocking switching high-speed high-capacity packet switch without packet loss, Simulation results for evaluation of the performance of the K-winner network controller with 10 neurons are presented to study the constraints of the ''frozen state'' as well as those of same initial state. An optoelectronic contention controller constructed from a K-winner neural network is proposed.

关键词： Packet switching Neural networks Communication switching Optical packet switching Optical switches Throughput computer networks Switching circuits Computational modeling Optical fiber communication

来源：评论

学校读者我要写书评

暂无评论

AN ABSOLUTE CHARGE SENSOR FOR FLUID ELECTRIFICATION MEASUREMENTS

引用

IEEE TRANSACTIONS ON electrical INSULATION 1991年第2期26卷 181-199页

作者： MORIN, AJ ZAHN, M MELCHER, JR OTTEN, DM Department of Electrical Engineering and Computer Science Laboratory for Electromagnetic and Electronic Systems Massachusetts Institute of Technology Cambridge MA USA

A new instrument, the Absolute Charge Sensor (ACS), has been developed that measures the net charge density entrained in a fluid flow, independent of the fluid's electrical properties, velocity, and any electrification processes within the instrument. Through a shielded sampling probe, the ACS periodically transfers a small volume of charged fluid to an electrically isolated Faraday cage with no fluid exiting. The charge density is calculated from the known filling flow rate and either the current or voltage, respectively measured by low or high impedance electrometers connected to the electrically isolated Faraday cage. The ACS overcomes the ambiguity in current or voltage measurements of probes placed into the fluid flow where it is impossible to separate contributions from impacting charge in the flow from charge separated at the probe interface by the very charge generation and transport processes that are under study. The instrument is typically operated to measure charge densities as low as a few mu-C/m3 using a sampling flow rate of 0.18 cm3 with a sampling period on the order of 1 min. A Couette charger apparatus that simulates flow electrification processes in transformers and fuel pumps has been used to test the ACS using transformer oil or gasoline. Results show good correlation between the ACS and continuous flow measurements. In preparation for field tests of electrification charging of transformer components, laboratory tests were also performed in a pump driven flow loop. ACS measurements of charge density were made at the inlet and outlet of an oil drum electrically grounded through an electrometer. Charge density measurements in flow having Reynolds numbers as high as 3000 were in good agreement with the charge conservation law, i.e. the difference in convection currents into and out of the grounded oil drum equal the measured current through the electrometer.

关键词： charge measurement electric sensing devices electrometers flow measurement insulating oils insulation testing 1 min Couette charger apparatus absolute charge sensor current measurement electrically isolated Faraday cage electrometers filling flow rate fluid electrification measurements fluid flow fuel pumps gasoline net charge density sampling period shielded sampling probe transformer oil transformers voltage measurements Charge measurement Current measurement Density measurement Electric variables measurement Fluid flow Fluid flow measurement Instruments Probes Sampling methods Voltage measurement

来源：评论

学校读者我要写书评

暂无评论

An FDTD near- to far-zone transformation for scatterers buried in stratified grounds

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 1996年第8期44卷 1150-1157页

作者： Demarest, K Huang, ZB Plumb, R Radar Systems and Remote Sensing Laboratory Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

The finite-difference time-domain (FDTD) technique is being used with increasing frequency for modeling the scattering characteristics of buried objects, FDTD has, for some time, been able to model the near-zone scatterered fields of buried objects due to near-zone sources. This is adequate for modeling the scattered returns of ground-based ground-penetrating radars, but not for airborne radars, This paper describes an FDTD-compatible technique whereby far-zone scattered fields of objects buried in a stratified ground can be calculated, This technique uses the equivalence principle to model a buried object in terms of equivalent electric and magnetic currents, The fields radiated by these currents in the presence of a stratified ground are then calculated using the reciprocity theorem and the wed-known field equations for plane waves in stratified media, Numerical results are presented that show excellent agreement between this technique and both analytical and numerical results.

关键词： airborne radar electric current electromagnetic fields electromagnetic wave propagation electromagnetic wave scattering finite difference time-domain analysis radar cross-sections EM wave propagation analytical results buried objects burie Electromagnetic wave propagation Scattering RECIPROCITY THEOREM electric current Electromagnetic wave scattering airborne radar Buried object detection Finite difference time domain method Electromagnetic fields Electricity Radar cross section EQUIVALENCE PRINCIPLE wave propagation

来源：评论

学校读者我要写书评

暂无评论

Available transmission capacity (ATC) and its value under open access

引用

IEEE TRANSACTIONS ON POWER systems 1997年第2期12卷 636-645页

作者： Ilic, MD Yoon, YT Zobian, A Department of Electrical Engineering and Computer Science Laboratory for Electromagnetic and Electronic Systems Massachusetts Institute of Technology Cambridge MA USA

Strictly engineering aspects of Available Transmission Capacity (ATC) are analyzed first. Non-linear network theory is used to provide several key conditions under which one could define a notion of Available Transmission Capacity (ATC) and specific novel algorithms for its evaluation. Next, the fundamental problem which prevents one from developing an economically efficient distributed transmission market based on the Available Transmission Capacity (ATC) is identified. It is suggested that for an electric power network of an arbitrary topology it is not possible to map the computed ATC onto its market value. All findings are illustrated using examples of small power systems.

关键词： Network topology Power system stability Power system economics Power generation economics computer networks Load flow Equations Resistors Power engineering and energy Laboratories

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：