检索结果-内蒙古大学图书馆

23rd International Semantic Web Conference, ISWC 2024

作者： Wang, Zhichun Shao, Yifeng Peng, Boci Li, Bangui Li, Yun Wang, Qianren Li, Nijun School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China School of Intelligence Science and Technology Peking University Beijing China School of Computer Science and Engineering Beihang University Beijing China Advanced Cognitive AI Lab Shanghai Huawei Technologies Shanghai China

ISBN: (纸本)9783031778438

Prerequisite learning is the task of identifying prerequisite relations among concepts, which is important for many AI-based educational applications. Previous approaches explore different kinds of learning resources to obtain useful features for predicting prerequisites. Early approaches use handcrafted features while recent approaches use neural networks to encode information of concepts. To further improve the results of prerequisite learning, we build concept graphs to include comprehensive information about concepts from open data and learning resources, and propose a Multi-view Transformer-based Network (MTN) to encode multi-view features of concepts in the graph. Multi-view features are fused to make accurate predictions of concept prerequisites. We evaluate our approach on four public datasets and compare it with recently published approaches. The results show that our approach can achieve state-of-the-art results in the task of prerequisite learning. The source code and data are available at https://***/kg-bnu/MTN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-layer Fusion Transformer Network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy NBFC National Biodiversity Future Center Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral image (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification (CLS) token that is randomly initialized and often struggles to generalize effectively. In this paper, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism (HyCrossAttention) for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in - depth experiments on commonly - used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park (MUUFL) dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshone them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Elastic Spectrum Sensing: An Adaptive Sensing Method for Non-Terrestrial Communication Under Highly Dynamic Channels

引用

IEEE Transactions on Wireless Communications 2025年第5期24卷 3868-3881页

作者： Xu, Tianheng Xu, Yinjun Zhou, Ting Zhang, Haijun Hu, Honglin Leung, Victor C. M. Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai201210 China Shanghai Frontier Innovation Research Institute Shanghai201100 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China Shanghai University School of Microelectronics Shanghai200444 China Institute of Artificial Intelligence Beijing Advanced Innovation Center for Materials Genome Engineering Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing100083 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T1Z4 Canada

With the rapid development of space technology, the role of satellite communications has become progressively significant. Non-terrestrial communication is deemed a critical scenario in the sixth generation (6G) communication systems, which showcases seamless connectivity, minimal geographic constraints and substantial communication capacity. Simultaneously, satellites and terminals spring up, spatial density increases, which further emphasizes the scarcity of spectrum resources. Consequently, to improve spectrum utilization for non-terrestrial communication is a significant concern. Spectrum sensing, which allows dynamic resource reuse, plays an important role in 6G. However, high mobility in non-terrestrial scenarios poses great challenges, such as fast time-varying channels, Doppler effect, etc., which seriously affect sensing accuracy and cannot well support optimal spectrum utilization. Motivated by such circumstances, this paper proposes an elastic sensing method for the downlink non-terrestrial communication scenario. Firstly, we design the system architecture and sensing workflow. To overcome the negative effects raised by high mobility, we propose the elastic sensing criterion and multi-area dividing scheme for the sensing zone. Thresholds affected by the elastic sensing are derived for different areas. Finally, the numerical results show that from -10 dB to -5 dB, the proposed method can improve the total performance by an average of 28.3% while stabilizing the false alarm probability around 0.1 typical level and demonstrating higher constancy compared with traditional technologies from −10 dB to −5 dB. © 2002-2012 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Port-controllable routing of orbital angular momentum modes using a rotatable diffractive neural network

引用

Science China(Physics,Mechanics & Astronomy) 2025年第6期Mechanics & Astronomy) .卷 158-167页

作者： Junmin Liu Jiafu Chen Qingji Zeng Zemin Liang Xinping Wu Xin Zhao Jiangnan Xiao Huapeng Ye Ze Dong Dianyuan Fan Shuqing Chen Institute of Microscale Optoelectronics Shenzhen University College of New Materials and New Energies Shenzhen Technology University Terahertz Technology Innovation Research Institute Shanghai Key Laboratory of Modern Optical System Terahertz Science Cooperative Innovation Center School of Optical-Electrical Computer Engineering University of Shanghai for Science and Technology Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University School of Information and Electronics Beijing Institute of Technology

Orbital angular momentum(OAM) modes provide an additional orthogonal physical dimension, offering transformative potential for enhancing optical communication capacity. Despite significant progress in mode multiplexing, the development of robust communication networks faces persistent challenges, particularly in effectively routing and controlling these multiplexed channels among network nodes. To tackle these dilemmas, we propose a rotatable diffractive neural network(R-DNN) strategy and demonstrate its capability for port-controllable OAM mode routing. By leveraging the correlation between the orthogonal evolution of OAM modes in free space and phase modulations during propagation, the R-DNN precisely shapes the spatial evolution of mode fields through multiple rotatable phase layers, enabling efficient routing to specific output ports. This approach exploits the interaction of secondary wavelets with the relative states of the rotatable layers, allowing on-demand control of mode evolution paths and enhancing routing flexibility. As a proof of concept, we developed a tri-functional router that successfully directs three OAM modes to individually controllable output ports. This router achieves an average intermode crosstalk of less than-16.4 dB across three functional states, one-dimensional, two-dimensional, and cross-connected switching, while supporting the routing of 5.85 Tbit/s quadrature phase-shift keying signals. These results highlight the R-DNN's effectiveness in achieving precise and controllable OAM mode manipulation, paving the way for advanced applications in mode-multiplexed communication networks and beyond.

关键词： orbital angular momentum mode mode routing diffractive neural network

来源：评论

学校读者我要写书评

暂无评论

Feature of water: A practical concept in water reuse

Water Cycle

引用

Water Cycle 2025年 6卷 300-305页

作者： Chen, Xiao-Wen Xu, Yu-Qing Wang, Wen-Long Huang, Nan State Key Laboratory of Regional Environment and Sustainability Key Laboratory of Microorganism Application and Risk Control Ministry of Ecology and Environment School of Environment Tsinghua University Beijing100084 China Key Laboratory of Microorganism Application and Risk Control of Shenzhen Guangdong Provincial Engineering Research Center for Urban Water Recycling and Environmental Safety Institute of Environment and Ecology Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Department of Environmental Engineering Faculty of Environment and Life Beijing University of Technology Beijing100124 China

The increasing stringency of standards has highlighted challenges in high-standard wastewater treatment and water reuse. Current water quality assessment primarily relies on bulk properties like chemical oxygen demand (COD) and biological oxygen demand (BOD), which fail to capture the intricate characteristics of wastewater contaminants. The novel concept of "feature of water", a multidimensional assessment system encompassing four primary indicators: quantitative concentration, compositional characteristics, transformation potential, and toxicological effects, is applied in the study. Unlike conventional linear approaches, feature of water provides a holistic perspective on wastewater composition, examining pollutant variations across temporal and spatial dimensions. applications of the feature of water concept include the identification of refractory pollutants, evaluation of treatment processes, and the design of tailored treatment technologies. Case studies demonstrate its effectiveness in improving water treatment efficiency, reducing operational costs, and mitigating ecological risks. By transitioning from traditional linear water quality evaluation to a systems-based approach, the feature of water provides a robust methodology to meet the demands of high-standard wastewater treatment and water reuse, ensuring environmental sustainability and public health protection. © 2025 The Authors

关键词： Water recycling

来源：评论

学校读者我要写书评

暂无评论

Dynamic Access Control in Multi-Layer Satellite Remote Sensing System Using Multi-Agent Deep Reinforcement Learning

引用

IEEE Transactions on Wireless Communications 2025年

作者： Hu, Han Lyu, Yifeng Fan, Rongfei Sui, Xiufeng Zhan, Cheng Niyato, Dusit Beijing Institute of Technology School of Information and Electronics Beijing100081 China Norinco Group Institute of Computer Application Technology Beijing100089 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Beijing Institute of Technology School of Management Beijing100081 China Southwest University School of Computer and Information Science Chongqing400715 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

The Multi-Layer Satellite Remote Sensing (SRS) integrates data collection by Low Earth Orbit (LEO) satellites and data processing assistance from Medium Earth Orbit (MEO) satellites, thereby playing a crucial role in scientific exploration. However, effectively controlling access to LEO satellites for processing data, especially considering the frequent handovers caused by speed differences, presents a significant challenge to achieving high energy efficiency services. To address this challenge, we explore cooperative dynamic access control based on efficient communication mechanisms, with the aim of prioritizing processed data volume and meeting energy consumption requirements for satellites. Specifically, we formulate the access control issue as an optimization problem and integrate it into the framework of partially observable Markov decision process (POMDP), considering MEO satellites' limited observation ability. By employing Multi-agent Deep Reinforcement Learning (MADRL), we propose a novel dynamic access control algorithm named DAC to solve our featured problem. Specifically, for improving performance, communication-efficient cooperation among MEOs is enhanced through modeling decision-relevant information of fellow MEO satellites and maximizing mutual information with their actual data to extract precise awareness and enable the generation of concise message. Finally, we conduct comprehensive experiments and an ablation study spanning the Starlink, OneWeb, and Telesat mega-constellations. The results demonstrate that DAC increases the average system data processing volume by at least 13.5%, while meeting energy consumption constraints and outperforming baseline algorithms. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Disease Detection Using Ensemble Model in Machine Learning

引用

SN computer Science 2025年第3期6卷 1-15页

作者： Mohapatra, Rojalin Giri, Parimala Kumar Sayyad, Irfan Sahu, Amaresh Brahma, Biswajit Kamila, Nilayam Kumar Department of Computer Science and Engineering Gandhi Institute for Technological Advancement Odisha Bhubaneswar India Department of Information Technology and Computer Application Vignan’s Foundation for Science Technology and Research (Deemed to be University) Andhra Pradesh Vadlamudi India Department of MCA Ajay Binay Institute of Technology Odisha Cuttack India McKesson Corporation San Francisco CA United States Capital One Wilmington DE United States

Disease detection is a vital issue in the healthcare system. Few diseases need to be tested early if any patient discovers any disease-related symptoms in their body. Although various methods are used to test several diseases based on the symptoms, it is necessary to improve the experimental testing for disease detection through various machine learning (ML) methods. Thus, the ensemble ML Model is proposed to enhance the experimental performance per the methods. Different machine learning methods such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Gaussian Naive Bayes (GNB) and Logistic Regression (LR) are used to make ensemble models based on the combination of two or three methods. The experiment is demonstrated on the proposed ensemble model using a diabetes data set and performed with various evaluation metrics. As per the performance of the ensemble method, (SVM + RF) performed well than other methods with an accuracy of 99%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ensemble model Logistic regression Machine learning Naïve Bayes Random forest SVM Voting classifier

来源：评论

学校读者我要写书评

暂无评论

Performance of CRA-40 reanalysis in representing the Antarctic winter stratospheric circulation: a comparison with ERA-5 and MERRA-2

引用

Earth and Planetary Physics 2025年第2期9卷 452-459页

作者： ZiXu Wang JingGao Hu Jing-Jia Luo Jian Rao ZongZe Li LiuChi Yan Key Laboratory of Meteorological Disaster Ministry of Education(KLME)Joint International Research Laboratory of Climate and Environment Change(ILCEC)Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD)Nanjing University of Information Science&TechnologyNanjing 210044China Institute for Climate and Application Research(ICAR) Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics(LASG) Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China University of Chinese Academy of Sciences Beijing 100049China

This paper evaluates a representation of winter stratospheric circulation in the Antarctic that is based on CRA-40, a 40-year global reanalysis dataset released by the China Meteorological Administration, and compares it with representations based on two other state-of-the-art reanalysis datasets: the fifth-generation atmospheric reanalysis provided by the European Centre for Medium-Range Weather Forecasts(ERA-5) and the Modern-Era Retrospective analysis for research and applications, version 2(MERRA-2). In terms of climatology, we find that CRA-40 portrays a stronger and colder polar vortex in the middle and lower stratosphere than ERA-5, but a weaker and warmer one than MERRA-2. However, disagreement among the three reanalyses is confined mainly to the period before1999, and is largely reduced after that time. On the interannual timescale, portrayals of the intensity and area of the 10-hPa polar vortex are quite consistent among the three reanalyses, with correlation coefficients greater than 0.9 between each pair of reanalyses. In addition, the central dates of most sudden stratospheric deceleration(SSD) events at 10 hPa in the three reanalyses differ by less than one day, indicating that CRA-40 is also highly consistent with the other two reanalysis datasets regarding daily evolution. Our analyses suggest that CRA-40 performs comparably to ERA-5 and MERRA-2 in characterizing winter circulation in the Antarctic middle and lower stratosphere.

关键词： CRA-40 ERA-5 MERRA-2 Antarctic stratosphere reanalysis intercomparison

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Multidimensional Resource Allocation for Semantic-Assisted High-Speed Railway with Multi-access MEC 3rd

Task Offloading and Multidimensional Resource Allocation for...

引用

3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2024

作者： Qu, Jiaming Guo, Qichang Yuan, Jiabin Zhang, Wei Beijing University of Posts and Telecommunications School of Electronic Engineering Beijing China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Jiangsu Nanjing China China Datang Corporation Science and Technology General Research Institute Ltd. Beijing China

ISBN: (纸本)9789819624676

In high-speed railway communication scenarios, most of the computing tasks generated by trains are compute-intensive and delay-sensitive. Multi-access mobile edge computing (MEC) technology is very promising in resolving the contradiction between this situation and the limited local resources. Traditionally, MEC servers are deployed at base stations along the railway. We introduce dynamic MEC servers assisted by unmanned aerial vehicles (UAVs) additionally to deal with excessive server loads and the real-time nature of trains and tasks. Moreover, to complete real-time tasks, trains usually need abundant resources to transmit a large amount of raw data to MECs. However, limited local resources cannot meet the needs. Therefore, we propose a semantic-assisted communication model, introducing semantic encoding, decoding, extraction and feature aggregation to reduce resource overhead and computing delay while ensuring the accuracy of semantic understanding. Next, we conduct research on multi-dimensional resource allocation with the goal of minimizing delays and maximizing cache resource utilization by presenting our problem formulation. We propose a scheme based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to enable MEC agents to collaborate in offloading tasks and allocate resources. Lastly, we conduct simulation experiments and compare with two schemes: centralized resource management and random offloading resource allocation, verifying that the proposed scheme can achieve higher resource utilization and QoS satisfaction rate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Communication Countermeasure Strategy Decision-Making Based on Incomplete Information Game

Communication Countermeasure Strategy Decision-Making Based ...

引用

International Conference on Advanced Communication technology (ICACT)

作者： Jinyue Liu Xiang Gao Haowei Yang Jihao Zhang Yuhan Liu Peng Gong National Key Laboratory of Mechatronic Engineering and Control School of Mechatronical Engineering Beijing Institute of Technology Beijing China Institute of Computer Application Technology Norinco Group Beijing China

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

In modern battlefields, the stability of wireless communications is crucial for intelligence transmission, command coordination, and maintaining strategic advantage. However, with the rapid advancement of communication technologies, the electromagnetic environment has become increasingly complex, making intelligent decision-making in communication countermeasures a prominent research focus. However, most existing studies adopt deep learning and reinforcement learning methods, which require extensive data samples and computational resources. To address these limitations, this paper proposes a game-theoretic model for intelligent radio communication countermeasures under incomplete information. It quantitatively evaluates common attack and defense tactcis used in communication countermeasures and explores the mixed-strategy equilibrium of the game when both the attackers and defenders consist of multiple types. Furthermore, simulation-based comparative analyses are conducted to assess the factors influencing the utility of both the attacker and defender. The findings offer theoretical insights and decision-making support for the deployment of communication countermeasure strategies in practical military operations, contributing to significant strategic value.

关键词： Wireless communication Military communication Deep learning Decision making Games Reinforcement learning Communications technology Stability analysis Radio communication countermeasures Electromagnetics

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：