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

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： dynamic prompt generation hierarchical heterogeneous graph Multimodal long document classification

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2025年

作者： Fidêncio, Aline Xavier Grün, Felix Klaes, Christian Iossifidis, Ioannis Robotics and BCI Laboratory Institute of Computer Science Ruhr West University of Applied Sciences Mülheim an der Ruhr Germany Faculty of Electrical Engineering and Information Technology Ruhr University Bochum Bochum Germany KlaesLab Department of Neurosurgery University Hospital Knappschaftskrankenhaus Ruhr University Bochum Bochum Germany Faculty of Computer Science Ruhr University Bochum Bochum Germany

Brain-computer interfaces (BCIs) are developed for individuals with motor disabilities to offer alternative methods of communication, such as controlling and interacting with external devices. These systems are designed to improve quality of life, particularly for those with limited mobility. BCIs that rely on non-invasive recordings, such as electroencephalography (EEG), have been developed for a wide range of scenarios due to their practicality and safety. However, BCI performance is often limited by non-stationarities in the EEG data, which can arise from changes in the subject’s mental state or device characteristics, such as electrode impedance. These challenges motivate ongoing research into the development of adaptive BCIs capable of handling such variations. Over the past years, the interest in using the so-called error-related potentials (ErrPs) to improve BCI performance has increased. This is because ErrPs represent the neural response to both self-made and external errors and can be measured using non-invasive techniques. These signals have been combined with different BCI paradigms and used in different works to improve BCI performance via error correction or adaptation. In this work we introduce and explore a new approach for creating an adaptive ErrP-based BCI by evaluating the use of reinforcement learning (RL). This study demonstrates the feasibility of a RL-driven adaptive brain-computer interface (BCI) framework that integrates error-related potentials (ErrPs) and motor imagery. By employing two RL agents to dynamically adapt to EEG non-stationarities, we validate the framework on both a publicly available motor imagery dataset and using a novel experimental protocol involving a fast-paced game designed to enhance user engagement. Results highlight the framework’s potential: RL agents successfully learned control policies from user interactions, achieving robust performance across datasets. However, a critical finding emerged from the game-based p

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data Identification Optimal control for Quantized Linear Systems under DoS Attacks

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wang, Xianming Li, Liwei Shen, Mouquan Zhao, Xudong Wang, Qing-Guo Zhu, Zheng Hong Nanjing Tech University School of Mechanical and Power Engineering Nanjing211816 China Nanjing Tech University College of Electrical Engineering and Control Science Nanjing211816 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116024 China Beijing Normal University Institute of Ai and Future Networks Zhuhai519087 China BNU-HKBU United International College Guangdong Provincial Key Laboratory Irads Department of Computer Science Zhuhai519087 China York University Department of Mechanical Engineering TorontoONM3J 1P3 Canada

This paper is devoted to data identification optimal control for quantized linear systems under denial of service (DoS) attacks. A least-squares algorithm is provided to identify the unknown system matrices using a data-based representation. An output estimation algorithm utilizing identified matrices is supplied to offset DoS attacks. Consequently, an optimal controller is built on the quantized and attacked data by adaptive dynamic programming. Sufficient conditions are presented to guarantee that the resultant closed-loop system is ultimately uniformly bounded. An example is produced to verify the validity of the proposed approach. © 1965-2011 IEEE.

关键词： Optimal control systems

来源：评论

学校读者我要写书评

暂无评论

Sim4EndoR: A Reinforcement Learning Centered Simulation Platform for Task Automation of Endovascular robotics

arXiv

引用

arXiv 2025年

作者： Yao, Tianliang Ban, Madaoji Lu, Bo Pei, Zhiqiang Qi, Peng Department of Control Science and Engineering College of Electronics and Information Engineering Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Department of Electrical and Electronic Engineering Faculty of Engineering The University of Hong Kong 999077 Hong Kong Robotics and Microsystems Center School of Mechanical and Electric Engineering Soochow University Jiangsu Suzhou China School of Oriental Pan-Vascular Devices Innovation College University of Shanghai for Science and Technology 516 Jungong Road Shanghai200093 China State Key Laboratory of Cardiovascular Diseases Medical Innovation Center Shanghai East Hospital School of Medicine Tongji University Shanghai200092 China

Robotic-assisted percutaneous coronary intervention (PCI) holds considerable promise for elevating precision and safety in cardiovascular procedures. Nevertheless, current systems heavily depend on human operators, resulting in variability and the potential for human error. To tackle these challenges, Sim4EndoR, an innovative reinforcement learning (RL) based simulation environment, is first introduced to bolster task-level autonomy in PCI. This platform offers a comprehensive and risk-free environment for the development, evaluation, and refinement of potential autonomous systems, enhancing data collection efficiency and minimizing the need for costly hardware trials. A notable aspect of the groundbreaking Sim4EndoR is its reward function, which takes into account the anatomical constraints of the vascular environment, utilizing the geometric characteristics of vessels to steer the learning process. By seamlessly integrating advanced physical simulations with neural network-driven policy learning, Sim4EndoR fosters efficient sim-to-real translation, paving the way for safer, more consistent robotic interventions in clinical practice, ultimately improving patient outcomes. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High-precision micro-nano fabrication using two-photon etching and spatial light modulators

引用

Optics Communications 2025年 587卷

作者： Xu, Ke Li, Xianru Gong, Haifeng Li, Yunpeng Wang, Xiaoduo School of Electrical & Control Engineering Shenyang Jianzhu University Shenyang110168 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China School of Mechanical Engineering and Automation Northeastern University Shenyang110819 China School of Public Security Information Technology and Intelligence Criminal Investigation Police University of China Shenyang110854 China

Dynamic encoding of Spatial Light Modulators (SLM) to achieve patterned light fields for efficient, high-precision, and flexibly controllable fabrication remains a significant challenge. This study introduces a novel approach by integrating the flat-top beam algorithm into the Modified Random Phase Amplitude Filter (MRAF) algorithm. This integration optimizes the initial phase distribution, generating a more uniform flat-top light field while avoiding phase singularities, thereby reducing speckle noise and enhancing the quality of microstructures fabricated via two-photon etching. The fabricated structures were analyzed using a white light interferometer, demonstrating that the improved MRAF algorithm significantly enhances fabrication precision compared to the traditional MRAF algorithm. The proposed method not only improves surface quality but also reduces edge distortion, achieving higher fabrication precision and stability. These results validate the practical feasibility and application potential of the improved method. © 2025 Elsevier B.V.

关键词： Light modulation

来源：评论

学校读者我要写书评

暂无评论

Selected Problems of Reverse Logistics in the Multiple Processing of Polymer Recyclates

引用

Transportation Research Procedia 2025年 87卷 50-59页

作者： Jachowicz Tomasz Woźniak Waldemar Sąsiadek Michał Niedziela Maciej Jajczyk Jarosław Naumowicz Magdalena Lublin University of Technology Faculty of Mechanical Engineering 38 Nadbystrzycka Str. 20-618 Lublin Poland University of Zielona Góra； Institute of Materials and Biomedical Engineering 4 Prof. Z. Szafran Str. 65-516 Zielona Góra Poland University of Zielona Góra Institute of Mechanical Engineering 4 Prof. Z. Szafran Str. 65-516 Zielona Góra Poland University of Zielona Góra Institute of Mathematics 4 Prof. Z. Szafran Str. 65-516 Zielona Góra Poland Poznań University of Technology Faculty of Control Robotics and Electrical Engineering 3A Piotrowo Str. 60-965 Poznań Poland Polipak Ltd. R&D 7 Fabryczna Str. 63-000 Środa Wielkopolska Poland

The article presents a solution introduced in an industrial enterprise to recover low-density polyethylene from production waste and reintroduce it as a secondary raw material into a separate production cycle, thus obtaining a closed cycle: primary plastic – production – waste – secondary plastic – production. The production assortment consisted of bags, with primary raw material being used to make bags for contact with food (e.g. for freezing), while secondary raw material was used to make garbage bags. The applied technology of extrusion with free blowing, enabled the production of multi-layer film in which primary raw material, secondary raw material obtained from own production waste and secondary raw material from external suppliers, were used. The mutual proportions of raw materials allowed the production of three-layer film with a wide range of performance properties, with a significant group of products constituting a film containing at least 55% of waste polyethylene. The conducted experimental tests were carried out under industrial conditions. The tubular film made from three-layer polyethylene were subjected to testing based on several dozen formulations defining the raw material composition, which relates to the total content of polyethylene regranulate. The results of the studies on selected properties of the secondary raw material and the selected mechanical properties of the three-layer film, which was subsequently used to produce garbage bags in the next stage of the production process, are presented. Based on the results obtained, the effectiveness of the qualification system adopted for polyethylene regranulates was assessed in relation to the formulation scheme developed, ensuring efficient production of three-layer film with appropriate user properties, regardless of random changes in the properties of secondary raw materials recovered internally or sourced externally.

关键词： Free-blowing extrusion multi-layer film polyethylene polyethylene regranulate

来源：评论

学校读者我要写书评

暂无评论

Fine- and hyperfine structure semi-empirical studies of singly ionized niobium. Odd-parity configurations system

引用

Journal of Quantitative Spectroscopy and Radiative Transfer 2025年 344卷

作者： J. Ruczkowski M. Elantkowska M. Klempka Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering Poznan University of Technology Piotrowo 3a 60-965 Poznan Poland Institute of Materials Research and Quantum Engineering Faculty of Materials Engineering and Technical Physics Poznan University of Technology Piotrowo 3 60-965 Poznan Poland

We report the results of semi-empirical calculations of the fine structure ( fs ) and the hyperfine structure ( hfs ) for the odd-parity level system of the niobium ion (Nb II), using all available experimental data. The calculations performed showed, in most cases, a very good agreement, within the experimental uncertainty or slightly above it, between the total of 156 experimental hfs A values and the calculated ones. The predicted energies of electronic levels, together with their Landé g J factors, as well as the magnetic dipole A hfs constants for unknown levels, are also presented.

关键词： Crystal atomic structure

来源：评论

学校读者我要写书评

暂无评论

Temporal-spatial cross-correlation analysis of non-stationary near-surface wind speed time series

引用

Journal of Central South University 2017年第3期24卷 692-698页

作者： ZENG Ming LI Jing-hai MENG Qing-hao ZHANG Xiao-nei Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control （School of Electrical Automation and Information Engineering Tianjin University） Tianjin 300072 China

Temporal-spatial cross-correlation analysis of non-stationary wind speed time series plays a crucial role in wind field reconstruction as well as in wind pattern ***,the near-surface wind speed time series recorded at different locations are studied using the detrended fluctuation analysis(DFA),and the corresponding scaling exponents are larger than *** indicates that all these wind speed time series have non-stationary ***,concerning this special feature( i.e.,non-stationarity)of wind signals,a cross-correlation analysis method,namely detrended cross-correlation analysis(DCCA) coefficient,is employed to evaluate the temporal-spatial cross-correlations between non-stationary time series of different anemometer ***,experiments on ten wind speed data synchronously collected by the ten anemometers with equidistant arrangement illustrate that the method of DCCA cross-correlation coefficient can accurately analyze full-scale temporal-spatial cross-correlation between non-stationary time series and also can easily identify the seasonal component,while three traditional cross-correlation techniques(i.e.,Pearson coefficient,cross-correlation function,and DCCA method) cannot give us these information directly.

关键词： temporal-spatial cross-correlation near-surface wind speed time series detrended cross-correlation analysis （DCCA） cross-correlation coefficient Pearson coefficient cross-correlation function

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Stability and Robust Stability of Switched Positive Linear Systems With All Modes Unstable

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 167-176页

作者： Shaoxia Feng Juan Wang Jun Zhao Shanxi Institute of Mechanical and Electrical Engineering the College of Information Scienceand Engineering Northeastern University the Faculty of Information and Control Engineering Shenyang Jianzhu University the State Key Laboratory of Synthetical Automationfor Process Industries (Northeastern University) the Collegeof Information Science and Engineering Northeastern University

This paper is concerned with the stability and robust stability of switched positive linear systems(SPLSs) whose subsystems are all unstable. By means of the mode-dependent dwell time approach and a class of discretized co-positive Lyapunov functions, some stability conditions of switched positive linear systems with all modes unstable are derived in both the continuous-time and the discrete-time cases, respectively. The copositive Lyapunov functions constructed in this paper are timevarying during the dwell time and time-invariant afterwards. In addition, the above approach is extended to the switched interval positive systems. A numerical example is proposed to illustrate our approach.

关键词： Discretized co-positive Lyapunov functions mode-dependent dwell time robust stability switched positive linear systems (SPLSs) unstable subsystem

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：