检索结果-内蒙古大学图书馆

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and systems for Video technology 2025年第6期35卷 5776-5790页

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： Adaptation models Transformers Data models Correlation Circuits and systems Electronic mail Robustness Uncertainty Training Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Improved Multi-Path Routing for QoS on MANET

引用

Computer systems science & engineering 2023年第6期45卷 2521-2536页

作者： M.Vargheese Surbhi Bhatia Shakila Basheer Pankaj Dadheech Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl HasaSaudi Arabia Department of Information Systems College of Computer and Information SciencePrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&Gramothan(SKIT)Jaipur302017RajasthanIndia

A Mobile Ad hoc NETwork(MANET)is a self-configuring network that is not reliant on *** paper introduces a new multipath routing method based on the Multi-Hop Routing(MHR)*** is the consecutive selection of suitable relay nodes to send information across nodes that are not within direct range of each *** to ensure good MHR leads to several negative consequences,ultimately causing unsuccessful data transmission in a *** research work consists of three *** first to attempt to propose an efficient MHR protocol is the design of Priority Based Dynamic Routing(PBDR)to adapt to the dynamic MANET environment by reducing Node Link Failures(NLF)in the *** is achieved by dynamically considering a node’s mobility parameters like relative velocity and link duration,which enable the next-hop *** method works more efficiently than the traditional *** the second stage is the Improved Multi-Path Dynamic Routing(IMPDR).The enhancement is mainly focused on further improving the Quality of Service(QoS)in MANETs by introducing a QoS timer at every node to help in the QoS routing of *** QoS is the most vital metric that assesses a protocol,its dynamic estimation has improved network performance *** method uses distance,linkability,trust,and QoS as the four parameters for the next-hop *** is compared against traditional routing *** Network Simulator-2(NS2)is used to conduct a simulation analysis of the protocols under *** proposed tests are assessed for the Packet Delivery Ratio(PDR),Packet Loss Rate(PLR),End-to-End Delay(EED),and Network Throughput(NT).

关键词： Multi-path routing quality of service node-link failure packet delivery ratio

来源：评论

学校读者我要写书评

暂无评论

MULTI-ROBOT PATH PLANNING AND COOPERATIVE OBSTACLE AVOIDANCE BASED ON MONTE-CARLO TREE SEARCH 10

MULTI-ROBOT PATH PLANNING AND COOPERATIVE OBSTACLE AVOIDANCE...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Dai, Juan Jing, Yanzhang Su, Zhong Zhu, Cui Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science & Technology University Beijing China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing China School of Automation Beijing Information Science & Technology University Beijing China School of Information and Communication Engineering Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

With the rapid development of artificial intelligence technologies, multi-robot cooperative processing tasks are becoming more and more common in various applications. However, traditional single-robot planning algorithms show obvious limitations in dealing with complex social interactions and dynamic environments in the real world. To address this challenge, this paper applies Monte Carlo Tree Search (MCTS) to multi-robot path planning and proposes a collaborative obstacle avoidance motion planning algorithm based on MCTS. Specifically, the algorithm prunes the Monte Carlo tree by excluding cases that do not meet the robot speed constraints and potential collisions, which significantly improves the computational speed and success rate of the algorithm, making it applicable to the multi-robot path conflict problem. In addition, we design a policy space that conforms to the robot's operation and a cost function that meets the requirements of robot path planning to plan an efficient cooperative path for each robot. Through a series of simulation experiments, we demonstrate the algorithm's path planning and obstacle avoidance performance in a variety of conflict scenarios. The results show that the method is highly cooperative and effective in complex environments. © The Institution of engineering & technology 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年第12期12卷 19189-19201页

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Distributed Deep Reinforcement Learning-based Approach for Fast Preventive Control Considering Transient Stability Constraints

引用

CSEE Journal of Power and Energy systems 2023年第1期9卷 197-208页

作者： Hongtai Zeng Yanzhen Zhou Qinglai Guo Zhongmin Cai Hongbin Sun State Key Laboratory of Power Systems Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Automation Science and Technology Xi’an Jiaotong UniversityXi’an 710000China

Preventive transient stability control is an effective measure for the power system to withstand high-probability severe *** is mathematically an optimal power flow problem with transient stability *** to the constraints involved for differential algebraic equations of transient stability,it is difficult and time-consuming to solve this *** address these issues,this paper presents a novel deep reinforcement learning(DRL)framework for preventive transient stability control of power systems.A distributed deep deterministic policy gradient is utilized to train a DRL agent that can learn its control policy through massive interactions with a grid *** properly trained,the DRL agent can instantaneously provide effective strategies to adjust the system to a safe operating position with a near-optimal operational *** effectiveness of the proposed method is verified through numerical experiments conducted on a New England 39-bus system and NPCC 140-bus system.

关键词： Deep reinforcement learning preventive Control transient stability

来源：评论

学校读者我要写书评

暂无评论

Detection of Perfect Stealthy Attacks on Cyber-Physical systems Subject to Measurement Quantizations: A Watermark-Based Strategy

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 114-125页

作者： Yu-Ang Wang Zidong Wang Lei Zou Bo Shen Hongli Dong the College of Information Science and Technology Donghua University the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education IEEE the College of Electrical Engineering and Automation Shandong University of Science and Technology the Department of Computer Science Brunel University London Uxbridge the Sanya Offshore Oil and Gas Research Institute Northeast Petroleum University the Artificial Intelligence Energy Research Institute Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University

In this paper, the attack detection problem is investigated for a class of closed-loop systems subjected to unknownbutbounded noises in the presence of stealthy attacks. The measurement outputs from the sensors are quantized before transmission.A specific type of perfect stealthy attack, which meets certain rather stringent conditions, is taken into account. Such attacks could be injected by adversaries into both the sensor-toestimator and controller-to-actuator channels, with the aim of disrupting the normal data flow. For the purpose of defending against these perfect stealthy attacks, a novel scheme based on watermarks is developed. This scheme includes the injection of watermarks(applied to data prior to quantization) and the recovery of data(implemented before the data reaches the estimator).The watermark-based scheme is designed to be both timevarying and hidden from adversaries through incorporating a time-varying and bounded watermark signal. Subsequently, a watermark-based attack detection strategy is proposed which thoroughly considers the characteristics of perfect stealthy attacks,thereby ensuring that an alarm is activated upon the occurrence of such attacks. An example is provided to demonstrate the efficacy of the proposed mechanism for detecting attacks.

关键词： Attack detection cyber-physical systems (CPSs) perfect stealthy attacks watermark-based strategy

来源：评论

学校读者我要写书评

暂无评论

Robust Underwater Positioning System Using LED Markers and Perspective-n-Point Solver

Robust Underwater Positioning System Using LED Markers and P...

引用

2025 IEEE Underwater technology, UT 2025

作者： Kitano, Emi Ebihara, Tadashi Wakatsuki, Naoto Maeda, Yuka Graduate School of Science and Technology University of Tsukuba Ibaraki Japan Institute of Systems and Information Engineering University of Tsukuba Ibaraki Japan

ISBN: (纸本)9798331534189

Swarm operations of underwater robots are gaining attention as a means of performing more complex and efficient tasks underwater. For successful operation, each underwater robot must know its position and pose. Traditional underwater acoustic positioning using ultrasonic waves has the advantage of providing wide-area coverage. However, the large size of those systems makes them difficult to mount on smaller robots such as those used in underwater robot swarms. This paper proposes a new simultaneous position and pose measurement system suitable for underwater robot swarm operations. In this system, a camera is mounted on each robot, and the relative position and pose of the light-emitting diodes (LEDs) are based on the coordinates of several known LEDs and the images captured by the camera. The effectiveness of the proposed positioning system using LEDs and cameras is verified through experiments in a test tank. © 2025 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Effect of Retained Austenite on Corrosion Behavior of Ultrafine Bainitic Steel in Marine Environment

引用

Acta Metallurgica Sinica(English Letters) 2023年第5期36卷 717-731页

作者： Xian Zhang Li Gong Yanpeng Feng Zhihui Wang Miao Yang Lin Cheng Jing Liu Kaiming Wu Hubei Province Key Laboratory of Systems Science in Metallurgical Process The State Key Laboratory of Refractories and MetallurgyCollaborative Innovation Center for Advanced SteelsWuhan University of Science and TechnologyWuhan430081China School of Chemistry Chemical Engineering and Life SciencesWuhan University of TechnologyWuhan430070China

In this study,the impact of retained austenite on corrosion initiation,propagation,and resistance of ultrafine bainitic steels in marine environments based on the one-step and two-step bainitic isothermal transformation was investigated using a combination of theoretical calculations and experimental *** to the results,the microstructure of ultrafine bainitic steels was composed of parallel arranged bainite ferrite(BF)and retained austenite(RA).The fraction of the block RA was significantly reduced,whereas the amount of the film RA increased through the two-step bainitic *** the initial stage of corrosion,micro-galvanic effects occurred between the multiphases due to the difference in nobility,leading to the selective dissolution of BF sheaves,which is adjacent to the block RA in the one-step bainitic ***,uniformly distributed film RA in the two-step bainitic steel acted as a barrier against corrosion *** electrochemical measurements and neutral salt spray tests revealed a relatively lower corrosion rate for the two-step bainitic steel,indicating a higher corrosion resistance than the one-step bainitic *** corrosion products layer mainly consisted ofα-FeOOH,γ-FeOOH,and Fe_(3)O_(4),which were stable and favorable for the formation of a protective rust layer.

关键词： Ultrafine bainitic steel Retained austenite Marine environment Corrosion behavior First principle modeling

来源：评论

学校读者我要写书评

暂无评论

Low-bias,high-photoresponsivity SnSe2 nanofilm with an Au split-ring array-based THz detector toward 6G communication

引用

science China(information sciences) 2023年第6期66卷 311-312页

作者： Qi SONG Zhiwen ZHOU Yifei XU Min ZHANG Junbo YANG Huawei LIANG Tianwu WANG Peiguang YAN College of Physics and Optoelectronic Engineering Shenzhen University Shandong Key Laboratory of Optical Communication Science and Technology School of Physics Science and Information TechnologyLiaocheng University College of Liberal Arts and Sciences National University of Defense Technology GBA Research Institute Aerospace Information Research Institute of Chinese Academy of Science

6G technology with the four characteristics of an intelligent endogenous,secure endogenous,multi-domain convergence,and integrated computing network,will help society toward an intelligent era [1]. The low power consumption and high photoresponsivity of 6G core devices,and particularly the improvement of detector performance,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Operando modeling and measurements:Powerful tools for revealing the mechanism of alkali carbonate-based sorbents for CO_(2)capture in real conditions

引用

Frontiers in Energy 2023年第3期17卷 380-389页

作者： Tianyi CAI Mengshi WANG Xiaoping CHEN Ye WU Jiliang MA Wu ZHOU School of Energy and Power Engineering Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Key Laboratory of Energy Thermal Conversion and Control of the Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing 210096China Key Laboratory of Thermal Control of Electronic Equipment and Advanced Combustion Laboratory of the Ministry of Industry and Information Technology School of Energy and Power EngineeringNanjing University of Science and TechnologyNanjing 210094China

Alkalicarbonate-based sorbents(ACSs),including Na_(2)CO_(3)-and K2CO_(3)-based sorbents,are promising for CO_(2)***,the complex sorbent components and operation conditions lead to the versatile kinetics of CO_(2)sorption on these *** paper proposed that operando modeling and measurements are powerful tools to understand the mechanism of sorbents in real operating conditions,facilitating the sorbent development,reactor design,and operation parameter *** reviewed the theoretical simulation achievements during the development of *** elucidated the findings obtained by utilizing density functional theory(DFT)calculations,ab initio molecular dynamics(AIMD)simulations,and classical molecular dynamics(CMD)simulations as *** hygroscopicity of sorbent and the humidity of gas flow are crucial to shifting the carbonation reaction from the gas-solid mode to the gas-liquid mode,boosting the ***,it briefly introduced a machine learning(ML)approach as a promising method to aid sorbent ***,it demonstrated a conceptual compact operando measurement system in order to understand the behavior of ACSs in the real operation *** proposed measurement system includes a micro fluidizedbed(MFB)reactor for kinetic analysis,a multi-camera sub-system for 3D particle movement tracking,and a combined Raman and IR sub-system for solid/gas components and temperature *** is believed that this system is useful to evaluate the real-time sorbent performance,validating the theoretical prediction and promoting the industrial scale-up of ACSs for CO_(2)capture.

关键词： CO_(2)capture carbonation theoretical modeling operando techniques reaction visualization

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：